Large and diverse image datasets have facilitated the recent advances in deep-learning-based computer vision applications. Whereas datasets with images depicting normal-weather scenes are plentiful, datasets with images depicting inclement weather conditions, such as haze, remain scarce due to collection difficulties. In response to this problem, we present a novel domain flow adaptation network (DFA-Net) that can control the haze density and facilitate the generation of realistic and diverse hazy images. DFA-Net employs a density variable to direct the network to learn and yield the desired images and is composed of four modules: a semantic extraction (SE) module, a haze extraction (HE) module, an image production (IP) module, and an image assessment (IS) module. The SE and HE modules are used to capture the semantic structure and style representation of clear and hazy images, respectively, and provide them to the IP module for refining the output images. The IP module is adopted to yield hazy images in a coarse-to-fine fashion, while the IS module is responsible for examining the realism of the synthesized results. Experiments on multiple benchmark datasets confirm the effectiveness of the proposed DFA-Net, which outperforms competing approaches by achieving improvements of up to 147% in quality, 237% in fidelity, and 354% in the diversity of generated images.

Large-scale datasets centered on images have driven advancements in deep learning-based computer vision applications. While there is an abundance of datasets containing images depicting favorable weather scenes, datasets featuring images of adverse weather conditions, especially the presence of haze, are scarce due to challenges in their collection. In response, we leverage the advantages of deep learning techniques to introduce a novel approach for facilitating the rendering of realistic and diverse hazy images, named RenHaze. To be specific, RenHaze adopts a denseness parameter \(\omega\) to control the haze level of output images and consists of five subnets, including a content exploitation (CE) subnet, a depth exploitation (DE) subnet, a haze exploitation (HE) subnet, an image generation (IG) subnet, and an image discernment (ID) subnet. The CE, DE, and HE subnets are responsible for extracting features from the source clear image, depth image, and reference hazy image, respectively, and then providing them for the IG subnet. The IG subnet is used to perform image translation in a coarse-to-fine manner, while the ID subnet is employed to discern the realism of the rendered image and provide feedback to the IG subnet for generating the desired output. Extensive experiments demonstrate the superiority of the proposed model over competing IG methods in terms of the realism and diversity of synthesized hazy images, as well as its effectiveness in boosting the performance of computer vision tasks such as object detection and semantic segmentation in real-world hazy environments.

Pretraining large language models is a complex endeavor influenced by multiple factors, including model architecture, data quality, training continuity, and hardware constraints. In this paper, we share insights gained from the experience of training DMaS-LLaMa-Lite, a fully open source, 1.7-billionparameter, LLaMa-based model, on approximately 20 billion tokens of carefully curated data. We chronicle the full training trajectory, documenting how evolving validation loss levels and downstream benchmarks reflect transitions from incoherent text to fluent, contextually grounded output. Beyond pretraining, we extend our analysis to include a post-training phase focused on instruction tuning, where the model was refined to produce more contextually appropriate, user-aligned responses. We highlight practical considerations such as the importance of restoring optimizer states when resuming from checkpoints, and the impact of hardware changes on training stability and throughput. While qualitative evaluation provides an intuitive understanding of model improvements, our analysis extends to various performance benchmarks, demonstrating how high-quality data and thoughtful scaling enable competitive results with significantly fewer training tokens. By detailing these experiences and offering training logs, checkpoints, and sample outputs, we aim to guide future researchers and practitioners in refining their pretraining strategies.

The integration of sensing, communication, and computation (ISCC) is a critical technology that will support various emerging wireless services in future 6G networks. The unmanned aerial vehicles (UAVs) equipped with edge servers can be used as an aerial service platform in intelligent transportation systems (ITSs) to offer ISCC services to vehicles. This article studies an aerial UAV network comprising a central UAV and secondary UAVs to realize sensing of the global ITS environment and data fusion computation through collaborative UAVs. To enhance the service performance of ISCC, we maximize the success rate of ISCC services and the energy efficiency of UAVs by jointly optimizing bandwidth allocation, power allocation, and computing capacity control while ensuring the sensing and data processing latency requirements. Leveraging the network architecture and collaboration requirements of UAVs, we propose the multi-UAV collaborative Air-ISCC (MCAI) algorithm based on the asynchronous advantage actor-critic algorithm, which obtains the optimal ISCC service policy by co-training a deep reinforcement learning model with multiple UAVs. Sufficient experimental results show that MCAI enhances energy efficiency by 10.51% to 80.12% compared with the baselines. Moreover, MCAI exhibits good scalability, strengthening its feasibility in real scenarios.

In recent years, object detection has significantly advanced by using deep learning, especially convolutional neural networks. Most of the existing methods have focused on detecting objects under favorable weather conditions and achieved impressive results. However, object detection in the presence of rain remains a crucial challenge owing to the visibility limitation. In this article, we introduce an amalgamating knowledge network (AK-Net) to deal with the problem of detecting objects hampered by rain. The proposed AK-Net obtains performance improvement by associating object detection with visibility enhancement, and it is composed of five subnetworks: rain streak removal (RSR) subnetwork, raindrop removal (RDR) subnetwork, foggy rain removal (FRR) subnetwork, feature transmission (FT) subnetwork, and object detection (OD) subnetwork. Our approach is flexible; it can adopt different object detection models to construct the OD subnetwork for the final inference of objects. The RSR, RDR, and FRR subnetworks are responsible for producing clean features from rain streak, raindrop, and foggy rain images, respectively, and offer them to the OD subnetwork through the FT subnetwork for efficient object prediction. Experimental results indicate that the mean average precision (mAP) achieved by our proposed AK-Net was up to 19.58% and 26.91% higher than those produced using competitive methods on published iRain and RID datasets, respectively, while preserving the fast-running time of the baseline detector.

Unmanned aerial vehicle (UAV)-based edge computing has been widely applied in intelligent transportation systems (ITSs) owing to its ease of deployment and high mobility. In this article, we study intelligent over-the-air computation (AirComp) in UAV swarm-assisted ITS. To develop a holistic service framework for UAV swarm, we consider the heterogeneity of Internet of Things Devices (IoTDs) and UAVs. We model the 3-D deployment of UAVs, service configuration, bandwidth allocation, the control of computing capacity, and transmission power as a joint optimization problem. To tackle this complex problem, we first propose a dual time-scale architecture based on deep reinforcement learning (DRL). This architecture enables UAVs to achieve seamless coverage of IoTDs on larger time scales, while collaborative UAVs dynamically provide services on smaller time scales. Next, we propose an intelligent AirComp algorithm D2IAC based on distributed DRL to obtain the optimal UAV deployment and dynamic service policies on different time scales. The D2IAC algorithm consists of three subalgorithms, i.e., TD3-based UAV deployment (TBUD), UAV services configuration (USC), and REINFORCE-based dynamic service (RBDS). Sufficient experimental results show that the proposed algorithm can achieve 3-D deployment of UAVs with coverage improvement from 9% to 36% compared to clustering, center layout, and random algorithms. Regarding dynamic services, compared with the deep deterministic policy gradient algorithm, greedy, fixed, and random strategies, the service durations of UAV swarm are improved by 32.95%–93.72% and the resource utilization is improved by 36.19%–49.61%.

Object detection techniques have been widely studied, utilized in various works, and have exhibited robust performance on images with sufficient luminance. However, these approaches typically struggle to extract valuable features from low-luminance images, which often exhibit blurriness and dim appearence, leading to detection failures. To overcome this issue, we introduce an innovative unsupervised feature domain knowledge distillation (KD) framework. The proposed framework enhances the generalization capability of neural networks across both low- and high-luminance domains without incurring additional computational costs during testing. This improvement is made possible through the integration of generative adversarial networks and our proposed unsupervised KD process. Furthermore, we introduce a region-based multiscale discriminator designed to discern feature domain discrepancies at the object level rather than from the global context. This bolsters the joint learning process of object detection and feature domain distillation tasks. Both qualitative and quantitative assessments shown that the proposed method, empowered by the region-based multiscale discriminator and the unsupervised feature domain distillation process, can effectively extract beneficial features from low-luminance images, outperforming other state-of-the-art approaches in both low- and sufficient-luminance domains.

In recent years, deep convolutional neural networks (CNNs) have been widely applied and have gained considerable success in object detection (OD). However, most of the CNN-based object detectors have been developed to operate under favorable weather conditions, limiting their ability to accurately detect objects in rainy nighttime (RNT) scenes, thereby resulting in low performance. In this work, we introduce a multilevel knowledge transmission network (MKT-Net) to overcome the challenges of detecting objects with the interference of rain and night. Our proposed model accomplishes this objective by collaborating OD with rain removal (RR) and low-illumination enhancement (LE) tasks. Specifically, the MKT-Net is composed of three main subnetworks that share some shallow layers with each other: an OD subnetwork for performing object classification and localization, an RR subnetwork, and an LE subnetwork for generating clear features. To aggregate and transmit multiscale features generated by the RR and LE subnetworks to the OD subnetwork for boosting detection accuracy, we introduce two feature transmission modules with identical architectures. Extensive evaluation on various datasets has demonstrated the effectiveness of our proposed model, which outperformed competing methods by up to 25.43% and 15.26% in mean average precision on a collected RNT dataset and the published rain in driving dataset, respectively, while maintaining high detection speed.

Distributed machine learning methods like Federated Learning (FL) and Split Learning (SL) meet the growing demands of processing large-scale datasets under privacy restrictions. Recently, FL and SL are combined in hybrid SLFL (SFL) frameworks to exploit both methods’ advantages to facilitate ubiquitous intelligence in the Internet of Things (IoT), for example, smart finance. Despite its significant impact on the performance and costs of SFL, model decomposition that splits an ML model into the client-server pair has not been sufficiently studied, especially for SFL in a large-scale dynamic IoT environment. In this paper, we propose a new SFL framework HSFL with a lightweight model decomposition method to offload a part of model training to the edge server. Specifically, we develop a method for estimating the training latency of HSFL and designed a metric for measuring privacy leakage in HSFL, based on which we formulate model decomposition in HSFL as an optimization problem with privacy protection as a constraint. Then, we transform the formulated problem into a contextual bandit problem and design an efficient algorithm to solve it. We have conducted thorough evaluations of the proposed HSFL framework through extensive experiments on a prototype testbed and a simulation platform. The experimental results validate the superiority of HSFL over the state-of-the-art benchmarks in terms of training latency, efficiency, scalability, and privacy protection.

While population aging has sharply increased the demand for nursing staff, it has also increased the workload of nursing staff.Although some nursing homes use robots to perform part of the work, such robots are the type of robots that perform set tasks.The requirements in actual application scenarios often change, so robots that perform set tasks cannot effectively reduce the workload of nursing staff.In order to provide practical help to nursing staff in nursing homes, we innovatively combine the LightGBM algorithm with the machine learning interpretation framework SHAP (Shapley Additive exPlanations) and use comprehensive data analysis methods to propose a service demand prediction model Fidan (Forecast service demand model).This model analyzes and predicts the demand for elderly services in nursing homes based on relevant health management data (including physiological and sleep data), ward round data, and nursing service data collected by IoT devices.We optimise the model parameters based on Grid Search during the training process.The experimental results show that the Fidan model has an accuracy rate of 86.61% in predicting the demand for elderly services.

Numerous lightweight detection models have been presented in recent years, yet these detectors are inclined to develop for operating under normal weather conditions without adequate studies for rainy conditions. This is one of the causes leads drastically performance degradation of object detectors due to the decrease in visibility. To address above insufficiency, we propose a new and effective approach, named 3FL-Net, to elevate the performance of lightweight object detectors in the presence of rain. Our approach fulfills the goal by closely incorporating four subnetworks, namely feature enhancement subnetwork, feature extraction subnetwork, feature adaptation subnetwork, and lightweight detection subnetwork. The lightweight detection subnetwork achieved the accuracy improvement by learning diverse features from the feature enhancement subnetwork and feature extraction subnetwork via the feature adaptation subnetwork. To further drive the development in object detection induced by rain, we introduce a large-scale driving dataset, called iRain. The full iRain consists of 17,950 real-world rain images, which covers most of the driving scenarios and 85,081 instances explaining five prevalent object classes. Experiment results on divergent rain datasets expose that our 3FL-Net considerably improves the performance of lightweight detectors and surpasses that of the combination models between rain removal and object detection methods.

In recent years, object detection approaches using deep convolutional neural networks (CNNs) have derived major advances in normal images. However, such success is hardly achieved with rainy images due to lack of visibility. Aiming to bridge this gap, in this article, we present a novel selective features absorption network (SFA-Net) to improve the performance of object detection not only in rainy weather conditions but also in favorable weather conditions. SFA-Net accomplishes this objective by utilizing three subnetworks, where the feature selection subnetwork is concatenated with the object detection subnetwork through the feature absorption subnetwork to form a unified model. To promote further advancement in object detection impaired by rain, we propose a large-scale rainy image dataset, named srRain, which contains both synthetic rainy images and real-world rainy images for training and testing purposes. srRain is comprised of 25 900 rainy images depicting diverse driving scenarios in the presence of rain with a total of 181 164 instances interpreting five common object categories. Experimental results display that our SFA-Net reaches the highest mean average precision (mAP) of 77.53% on a normal image set, 62.52% on a synthetic rainy image set, 37.34% on a collected natural rainy image set, and 32.86% on a published real rainy image set, surpassing current state-of-the-art object detectors and the combination of image deraining and object detection models while retaining a high speed.

Despite the recent improvement of object detection techniques, many of them fail to detect objects in low-luminance images. The blurry and dimmed nature of low-luminance images results in the extraction of vague features and failure to detect objects. In addition, many existing object detection methods are based on models trained on both sufficient- and low-luminance images, which also negatively affect the feature extraction process and detection results. In this article, we propose a framework called Self-adaptive Feature Transformation Network (SFT-Net) to effectively detect objects in low-luminance conditions. The proposed SFT-Net consists of the following three modules: (1) feature transformation module, (2) self-adaptive module, and (3) object detection module. The purpose of the feature transformation module is to enhance the extracted feature through unsupervisely learning a feature domain projection procedure. The self-adaptive module is utilized as a probabilistic module producing appropriate features either from the transformed or the original features to further boost the performance and generalization ability of the proposed framework. Finally, the object detection module is designed to accurately detect objects in both low- and sufficient- luminance images by using the appropriate features produced by the self-adaptive module. The experimental results demonstrate that the proposed SFT-Net framework significantly outperforms the state-of-the-art object detection techniques, achieving an average precision (AP) of up to 6.35 and 11.89 higher on the sufficient- and low- luminance domain, respectively.

In the past half of the decade, object detection approaches based on the convolutional neural network have been widely studied and successfully applied in many computer vision applications. However, detecting objects in inclement weather conditions remains a major challenge because of poor visibility. In this article, we address the object detection problem in the presence of fog by introducing a novel dual-subnet network (DSNet) that can be trained end-to-end and jointly learn three tasks: visibility enhancement, object classification, and object localization. DSNet attains complete performance improvement by including two subnetworks: detection subnet and restoration subnet. We employ RetinaNet as a backbone network (also called detection subnet), which is responsible for learning to classify and locate objects. The restoration subnet is designed by sharing feature extraction layers with the detection subnet and adopting a feature recovery (FR) module for visibility enhancement. Experimental results show that our DSNet achieved 50.84 percent mean average precision (mAP) on a synthetic foggy dataset that we composed and 41.91 percent mAP on a public natural foggy dataset (Foggy Driving dataset), outperforming many state-of-the-art object detectors and combination models between dehazing and detection methods while maintaining a high speed.

In this paper, we present a simple, efficient, and highly modularized network architecture for single-image snow-removal. To address the challenging snow-removal problem in terms of network interpretability and computational complexity, we employ a pyramidal hierarchical design with lateral connections across different resolutions. This design enables us to incorporate high-level semantic features with other feature maps at different scales to enrich location information and reduce computational time. In addition, a refinement stage based on recently introduced generative adversarial networks (GANs) is proposed to further improve the visual quality of the resulting snow-removed images and make a refined image and a clean image indistinguishable by a computer vision algorithm to avoid the potential perturbations of machine interpretation. Finally, atrous spatial pyramid pooling (ASPP) is adopted to probe features at multiple scales and further boost the performance. The proposed DesnowGAN (DS-GAN) performs significantly better than state-of-the-art methods quantitatively and qualitatively on the Snow100K dataset.

Light is scattered and absorbed when travelling through atmosphere particles, leading to visibility attenuation for images captured, especially in hazy scenes. In addition, hazy images may suffer from color distortion caused by haze or sandstorm, resulting in a poor visual quality. In order to effectively enhance visibility and correct possible color casts for such images, we propose a new image dehazing algorithm based on an improved haze optical model, which consists of three modules: airlight white correction (AWC), local light filter (LLF), and aerial perspective prior (APP). In the proposed algorithm, the AWC module detects and corrects possible color cast, the LLF module downplays non-hazy bright pixels (e.g., headlight and white objects) for more accurate airlight estimation, and the APP module uses the minimum/maximum channel and their difference for scene transmission estimation. The experimental results demonstrate that the proposed method outperforms other state-of-the-art dehazing methods in three ways: 1) our results have better visual quality; 2) our method performs the best in terms of color restoration; and 3) our method is very efficient at removing haze and color casts.

Images are often corrupted by natural obscuration (e.g., snow, rain, and haze) during acquisition in bad weather conditions. The removal of snowflakes from only a single image is a challenging task due to situational variety and has been investigated only rarely. In this article, we propose a novel snow removal framework for a single image, which can be separated into a sparse image approximation module and an adaptive tolerance optimization module. The first proposed module takes the advantage of sparsity-based regularization to reconstruct a potential snow-free image. An auto-tuning mechanism for this framework is then proposed to seek a better reconstruction of a snow-free image via the time-varying inertia weight particle swarm optimizers in the second proposed module. Through collaboration of these two modules iteratively, the number of snowflakes in the reconstructed image is reduced as generations progress. By the experimental results, the proposed method achieves a better efficacy of snow removal than do other state-of-the-art techniques via both objective and subjective evaluations. As a result, the proposed method is able to remove snowflakes successfully from only a single image while preserving most original object structure information.

In metropolitan areas, drivers share their vehicles with people who commute daily via carpooling. In this paper, we first defined a multiobjective carpool service problem with time windows (MOCSPTW) by considering four optimized objectives; subsequently, we propose a coevolutionary algorithm for two solution sets, population and archive, using objective-wise local search and set-based simulated binary operation in order to address the MOCSPTW. In the evolution module of the proposed algorithm, three different methods, namely, objective-wise local search in an archive, set-based simulated binary operation in a population, and set-based simulated binary operation both in a population and in an archive, were used to generate the offspring. Meanwhile, the E-domination and normal domination in the update module were adopted to control the convergence and diversity of the population and archive. In the experimental result, 48 sets of tests, including three moving patterns in a metropolitan area for the MOCSPTW, were prepared. The results of the quantitative comparison and objective visualization showed that the proposed algorithm can obtain superior Pareto-optimal solutions regarding convergence and diversity compared with a fast nondominated sorting genetic algorithm.

In recent years, the number of yoga practitioners has been drastically increased and there are more men and older people practice yoga than ever before. Internet of Things (IoT)-based yoga training system is needed for those who want to practice yoga at home. Some studies have proposed RGB/Kinect camera-based or wearable device-based yoga posture recognition methods with a high accuracy; however, the former has a privacy issue and the latter is impractical in the long-term application. Thus, this paper proposes an IoT-based privacy-preserving yoga posture recognition system employing a deep convolutional neural network (DCNN) and a low-resolution infrared sensor-based wireless sensor network (WSN). The WSN has three nodes (x, y, and z-axes) where each integrates 8 × 8 pixels' thermal sensor module and a Wi-Fi module for connecting the deep learning server. We invited 18 volunteers to perform 26 yoga postures for two sessions each lasted for 20 s. First, recorded sessions are saved as .csv files, then preprocessed and converted to grayscale posture images. Totally, 93200 posture images are employed for the validation of the proposed DCNN models. The tenfold cross-validation results revealed that F1-scores of the models trained with xyz (all 3-axes) and y (only y-axis) posture images were 0.9989 and 0.9854, respectively. An average latency for a single posture image classification on the server was 107 ms. Thus, we conclude that the proposed IoT-based yoga posture recognition system has a great potential in the privacy-preserving yoga training system.

Sharing vehicle journeys with other passengers can provide many benefits, such as reducing traffic congestion and making urban transportation more environmentally friendly. For the procedure of sharing empty seats, we need to consider increased ridership and driving distances incurred by carpool detours resulting from matching passengers to drivers, as well as maximizing the number of simultaneous matches. In accordance with these goals, this paper proposes and defines the multiobjective optimization carpool service problem (MOCSP). Previous studies have used evolutionary algorithms by combining multiple objectives into a single objective through a weighted linear or/and nonlinear combination of different objectives, thus turning to a single-objective optimization problem. These single-objective problems are optimized, but there is no guarantee of the performance of the respective objectives. By improving the individual representation and genetic operation, we developed a set-based simulated binary and multiobjective carpool matching algorithm that can more effectively solve MOCSP. Furthermore, the proposed algorithm can provide better driver-passenger matching results than can the binary-coded and set-based nondominated sorting genetic algorithms.

Elderly population (over the age of 60) is predicted to be 1.2 billion by 2025. Most of the elderly people would like to stay alone in their own house due to the high eldercare cost and privacy invasion. Unobtrusive activity recognition is the most preferred solution for monitoring daily activities of the elderly people living alone rather than the camera and wearable devices based systems. Thus, we propose an unobtrusive activity recognition classifier using deep convolutional neural network (DCNN) and anonymous binary sensors that are passive infrared motion sensors and door sensors. We employed Aruba annotated open data set that was acquired from a smart home where a voluntary single elderly woman was living inside for eight months. First, ten basic daily activities, namely, Eating, Bed_to_Toilet, Relax, Meal_Preparation, Sleeping, Work, Housekeeping, Wash_Dishes, Enter_Home, and Leave_Home are segmented with different sliding window sizes, and then converted into binary activity images. Next, the activity images are employed as the ground truth for the proposed DCNN model. The 10-fold cross-validation evaluation results indicated that our proposed DCNN model outperforms the existing models with F1-score of 0.79 and 0.951 for all ten activities and eight activities (excluding Leave_Home and Wash_Dishes), respectively.

Traffic congestion often incurs environmental problems. One of the most effective ways to mitigate this is carpooling transportation, which substantially reduces automobile demands. Due to the popularization of smartphones and mobile applications, a carpool service can be conveniently accessed via the intelligent carpool system. In this system, the service optimization required to intelligently and adaptively distribute the carpool participant resources is called the carpool service problem (CSP). Several previous studies have examined viable and preliminary solutions to the CSP by using exact and metaheuristic optimization approaches. For CSP-solving, evolutionary computation (e.g., metaheuristics) is a more promising option in comparison to exact-type approaches. However, all the previous state-of-the-art approaches use pure optimization to solve the CSP. In this paper, we employ the framework of neuroevolution to propose the self-organizing map-based neuroevolution (SOMNE) solver by which the SOM-like network represents the abstract CSP solution and is well-trained by using neural learning and evolutionary mechanism. The experimental section of this paper investigates the comparisons and analyses of two objective functions of the CSP and demonstrates that the proposed SOMNE solver achieves superior results when compared against those the other approaches produce, especially in regard to the optimization of the primary objective functions of the CSP. Finally, the visual results of the SOM are illustrated to show the effectiveness and efficiency of the evolutionary neural learning process.

Human posture recognition is the foundation of the human activity monitoring. The activity monitoring system is in high demand for the elderly living alone to monitor their health status and accidental fall since the world elderly population will be doubled by 2050. Researchers have developed many camera or wearable device-based human recognition systems; however, they are considered to be privacy-invasive and/or not practical for the long-term monitoring. We propose a device-free unobtrusive indoor human posture recognition system leveraging a low-resolution infrared sensor-based wireless sensor network and deep convolutional neural network (DCNN). We integrated AMG8833 sensor module with 8×8 thermal sensors for sensing the human body temperature and WiFi module for a wireless sensor network. Three wireless sensor nodes are used to capture 3-axis human thermal image. Totally, 15063 samples are collected from four volunteers while they had performed eight human postures as the ground truth for the 10-fold cross-validation of DCNN models. Experimental results indicate that the highest average F1-score for the eight postures was 0.9981. Thus, the proposed system has the high potential for monitoring elderly daily activities, exercise, and fall in emergency cases. Moreover, we believe that our proposed system will be a milestone in the device-free unobtrusive sensing technology.

Existing learning-based atmospheric particle-removal approaches such as those used for rainy and hazy images are designed with strong assumptions regarding spatial frequency, trajectory, and translucency. However, the removal of snow particles is more complicated because they possess additional attributes of particle size and shape, and these attributes may vary within a single image. Currently, hand-crafted features are still the mainstream for snow removal, making significant generalization difficult to achieve. In response, we have designed a multistage network named DesnowNet to in turn deal with the removal of translucent and opaque snow particles. We also differentiate snow attributes of translucency and chromatic aberration for accurate estimation. Moreover, our approach individually estimates residual complements of the snow-free images to recover details obscured by opaque snow. Additionally, a multi-scale design is utilized throughout the entire network to model the diversity of snow. As demonstrated in the qualitative and quantitative experiments, our approach outperforms state-of-the-art learning-based atmospheric phenomena removal methods and one semantic segmentation baseline on the proposed Snow100K dataset. The results indicate our network would benefit applications involving computer vision and graphics.

An intelligent carpool system provides convenience to both drivers and passengers who access carpool services to enjoy their ridesharing. The foundation of carpool-related issues is defined as the carpool service problem. This paper investigates a solution for this fundamental problem, more specifically described as the carpool service problem featuring high-occupancy-vehicle itineraries, which takes into consideration the enhancement of vehicular space occupancy for each portion of the ridesharing itinerary involving multiple objectives. As such, we propose the heuristic multi-objective optimization algorithm to solve the carpool service problem featuring high-occupancy-vehicle itineraries. This approach is based on the non-dominated sorting genetic algorithm and comprised of two modules: heuristics search operation and multi-objective individual selection. In the experimental section, the non-dominated sorting genetic algorithm without the heuristics mechanism is considered an important competitor to the proposed heuristic multi-objective optimization algorithm (HMO-CSPHI). Experimental results demonstrate that HMO-CSPHI can generate superior performance to other compared methods in terms of quantitative analysis and visualization comparison.

Outdoor images captured during hazy conditions have degraded visibility. The lack of both a medium transmission and atmospheric lights in a single haze image cause an ill-posed problem in the atmospheric scattering model. This paper proposes a novel haze density estimation model with a universal atmospheric-light extractor for single-image dehazing. The proposed method employs exponential inference to construct an exponential inference model to more accurately estimate haze density compared with the state-of-the-art methods. The coefficients in the proposed haze density estimation model are learned using a turbulent particle swarm optimization technique to obtain the best approximation of medium transmission. Moreover, a novel universal atmospheric-light extractor based on support vector data description is utilized to resolve the problem caused by a lack of atmospheric light. The overall results obtained by conducting qualitative and quantitative evaluations demonstrated that the proposed method has substantially higher dehazing efficacy and produces fewer artifacts than the state-of-the-art haze removal methods.

Restoration of visibility in hazy images is the first relevant step of information analysis in many outdoor computer vision applications. To this aim, the restored image must feature clear visibility with sufficient brightness and visible edges, while avoiding the production of noticeable artifacts. In this paper, we propose a haze removal approach based on the radial basis function (RBF) through artificial neural networks dedicated to effectively removing haze formation while retaining not only the visible edges but also the brightness of restored images. Unlike traditional haze-removal methods that consist of single atmospheric veils, the multiatmospheric veil is generated and then dynamically learned by the neurons of the proposed RBF networks according to the scene complexity. Through this process, more visible edges are retained in the restored images. Subsequently, the activation function during the testing process is employed to represent the brightness of the restored image. We compare the proposed method with the other state-of-the-art haze-removal methods and report experimental results in terms of qualitative and quantitative evaluations for benchmark color images captured in typical hazy weather conditions. The experimental results demonstrate that the proposed method is able to produce brighter and more vivid haze-free images with more visible edges than can the other state-of-the-art methods.

Many elderly persons prefer to stay alone in a single-resident house for seeking an independent life and reducing the cost of health care. However, the independent life cannot be maintained if the resident develops dementia. Thus, an early detection of dementia is essential for the elderly to extend their independent lifetime. One of the early symptoms of dementia is forgetting something when the person leaves the house. In this study, we introduce a novel front-door events (exit, enter, visitor, other, and brief-return-and-exit (BRE)) and their classification scheme that validated by using open datasets (n = 10) collected from ten single-resident testbeds by anonymous binary sensors. BRE events occur when four consecutive events (exit-enter-exit-enter) happen in some certain time intervals (t1, t2, and t3), and some of them may be the forget events. Each testbed had one older adult (aged 73 years and over) during the experimental period (μ = 583.1 ± 297.3 days). The algorithm automatically classifies the resident's front-door events and ignores visitor's entrance and exit events. The experimental results reveal the significance of the tiparameters for the number of BRE events. Since BRE events may include forget events, the proposed algorithm could be a useful tool for the forget event detection.

Fishery surveys that call for the use of single or multiple underwater cameras have been an emerging technology as a nonextractive mean to estimate the abundance of fish stocks. Tracking live fish in an open aquatic environment posts challenges that are different from general pedestrian or vehicle tracking in surveillance applications. In many rough habitats, fish are monitored by cameras installed on moving platforms, where tracking is even more challenging due to inapplicability of background models. In this paper, a novel tracking algorithm based on the deformable multiple kernels is proposed to address these challenges. Inspired by the deformable part model technique, a set of kernels is defined to represent the holistic object and several parts that are arranged in a deformable configuration. Color histogram, texture histogram, and the histogram of oriented gradients (HOGs) are extracted and serve as object features. Kernel motion is efficiently estimated by the mean-shift algorithm on color and texture features to realize tracking. Furthermore, the HOG-feature deformation costs are adopted as soft constraints on kernel positions to maintain the part configuration. Experimental results on practical video set from underwater moving cameras show the reliable performance of the proposed method with much less computational cost comparing with state-of-the-art techniques.

In this paper we represent our proposed novel morphological filter developed under the scope of Taiwan-Mongolian co-project. We applied the implemented filter in vehicle detection from CCTV video signal. Our goalwas to develop a filter that can reduce the noise in background subtracted binary image, which created by camera shake, and unnecessary moving objects such as wave of the tree etc. We compared our filter performance with morphological open, close, erosion, dilation, and median filters. PSNR (Peak Signal to Noise Ratio) is employed for evaluating the performance of the filters, our filter's PSNR was relatively higher (21.39) than the other method. Furthermore, we used our filter for vehicle detection, and detection rate was 100% as the other methods. Thus, we conclude the new filter is sufficient for denoising binary image, and suitable for vehicle detection.

Efficient image reconstruction, which removes high-density impulse noise from a single corrupted image, is the key technology of computer-vision systems such as for people counting, crowd analysis, action recognition, and human tracking. Recently, a surge in state-of-the-art sparse approximation approaches has occurred in the area of impulse noise removal using corrupted texture information or remnant noise-free information to recover a corrupted image. However, these sparse approximation approaches are recognized to fail when used for an image corrupted with high-density impulse noise. This is because there is insufficient noise-free information within each cropped window for these state-of-the-art sparse approximation approaches to make a sparse approximation. Thus, we propose a novel image restoration approach based on inverse-distance weighting with sparse approximation for high-density impulse noise removal from a single image. The proposed method uses an inverse-distance weighting-based prediction model to produce potential noise-free pixels. Unlike other recent noise removal methods, it does not utilize the corrupted texture information to recover the corrupted image. Evaluations on popular image benchmark datasets show that our image restoration approach has much better performance than the previous state-of-the-art methods, which are more complex and require either corrupted texture or remnant noise-free pixel information.

Recently, the development of automatic face annotation techniques in online social networks has become a promising research area for the purpose of management of the large numbers of photographs uploaded to social network platforms. In this study, the authors first construct the personalised pyramid database units for each member in the pyramid database access control module by effectively making use of various types of social network context to drastically reduce time expenditure and further boost the accuracy of face identification. Next, they train and optimise the personalised multiple‐kernel learning (MKL) classifier unit for each member, which utilises the MKL algorithm to locally adapt to each member, resulting in the production of high‐quality face identification results for the current owner in the MKL face recognition module. Experimental results demonstrate that their proposed face annotation approach provides a substantially higher level of efficacy and efficiency than other face annotation approaches for real‐life personal photographs with pose variations.

The growing ubiquity of vehicles has led to increased concerns about environmental issues. These concerns can be mitigated by implementing an effective carpool service. In an intelligent carpool system, an automated service process assists carpool participants in determining routes and matches. It is a discrete optimization problem that involves a system-wide condition as well as participants' expectations. In this paper, we solve the carpool service problem (CSP) to provide satisfactory ride matches. To this end, we developed a particle swarm carpool algorithm based on stochastic set-based particle swarm optimization (PSO). Our method introduces stochastic coding to augment traditional particles, and uses three terminologies to represent a particle: 1) particle position; 2) particle view; and 3) particle velocity. In this way, the set-based PSO (S-PSO) can be realized by local exploration. In the simulation and experiments, two kind of discrete PSOs-S-PSO and binary PSO (BPSO)-and a genetic algorithm (GA) are compared and examined using tested benchmarks that simulate a real-world metropolis. We observed that the S-PSO outperformed the BPSO and the GA thoroughly. Moreover, our method yielded the best result in a statistical test and successfully obtained numerical results for meeting the optimization objectives of the CSP.

Carpooling is a means of vehicle sharing by which drivers share their cars with one or more riders whose travel itineraries are similar to their own. As such, carpooling can be an effective way to ease traffic congestion. In this paper, we first present an intelligent carpool system based on the service-oriented architecture. Second, we propose a fuzzy-controlled genetic-based carpool algorithm by using the combined approach of the genetic algorithm and the fuzzy control system, with which to optimize the route and match assignments of the providers and the requesters in the intelligent carpool system. In regard to the quality of the match solutions and processing time, the exhaustive algorithm, the random matching algorithm, and the standard genetic algorithm are applied and their results compared with those produced by our proposed algorithm. Our experimental results proved that the proposed fuzzy-controlled genetic-based carpool algorithm is capable of consistently finding carpool route and matching results that are among the most optimal solutions that can be obtained via the exhaustive algorithm and, thus, outperforming all other compared methods in regard to match quality. In addition, the proposed algorithm is also able to operate with significantly less computational time than does the exhaustive algorithm and random matching algorithm.

Visibility restoration techniques are widely used for information recovery of hazy images in many computer vision applications. Estimation of haze density is an essential task of visibility restoration techniques. However, conventional visibility restoration techniques often suffer from either the generation of serious artifacts or the loss of object information in the restored images due to uneven haze density, which usually means that the images contain heavy haze formation within their background regions and little haze formation within their foreground regions. This frequently occurs when the images feature real-world scenes with a deep depth of field. How to effectively and accurately estimate the haze density in the transmission map for these images is the most challenging aspect of the traditional state-of-the-art techniques. In response to this problem, this work proposes a novel visibility restoration approach that is based on Bi-Histogram modification, and which integrates a haze density estimation module and a haze formation removal module for effective and accurate estimation of haze density in the transmission map. As our experimental results demonstrate, the proposed approach achieves superior visibility restoration efficacy in comparison with the other state-of-the-art approaches based on both qualitative and quantitative evaluations. The proposed approach proves effective and accurate in terms of both background and foreground restoration of various hazy scenarios.

Background subtraction for motion detection is often used in video surveillance systems. However, difficulties in bootstrapping restrict its development. This article proposes a novel hybrid background subtraction technique to solve this problem. For performance improvement of background subtraction, the proposed technique not only quickly initializes the background model but also eliminates unnecessary regions containing only background pixels in the object detection process. Furthermore, an embodiment based on the proposed technique is also presented. Experimental results verify that the proposed technique allows for reduced execution time as well as improvement of performance as evaluated by Recall, Precision, F1, and Similarity metrics when used with state-of-the-art background subtraction methods.

Traffic congestion has been a serious problem in many urban areas around the world. Carpooling is one of the most effective solutions to traffic congestion. It consists of increasing the occupancy rate of cars by reducing the empty seats in these vehicles effectively. In this paper, an advanced carpool system is described in detail and called the intelligent carpool system (ICS), which provides carpoolers the use of the carpool services via a smart handheld device anywhere and at any time. The carpool service agency in the ICS is integrated with the abundant geographical, traffic, and societal information and used to manage requests. For help in coordinating the ride matches via the carpool service agency, we apply the genetic algorithm to propose the genetic-based carpool route and matching algorithm (GCRMA) for this multiobjective optimization problem called the carpool service problem (CSP). The experimental section shows that the proposed GCRMA is compared with two single-point methods: the random-assignment hill climbing algorithm and the greedy-assignment hill climbing algorithm on real-world scenarios. Use of the GCRMA was proved to result in superior results involving the optimization objectives of CSP than other algorithms. Furthermore, our GCRMA operates with significantly a small amount of computational complexity to response the match results in the reasonable time, and the processing time is further reduced by the termination criteria of early stop.

Carpooling is an effective solution to traffic congestion. It increases the usage rate of vehicles by employing empty seats as a transportation resource. In order to provide carpooling services to users, we developed an intelligent carpool system called BlueNet-Ride. After prospective carpoolers submit their requests through their smart handheld devices, this system provides appropriate matches by using the proposed Low-Complexity and Low-Memory Carpool Matching method. The compact genetic algorithm is applied to our Low-Complexity and Low-Memory Carpool Matching method, which involves three proposed modules: an Evolutionary Model Initialization module, an Evolutionary Process Operation module, and an Evolutionary Model Modification module. The Evolutionary Model Initialization module takes advantage of the manipulation of the evolving population on a probability distribution to achieve low-memory requirements during the evolution process of the carpool match solution. The Evolutionary Process Operation and Evolutionary Model Modification modules simulate genetic operations to accomplish superior matching within a short amount of time. The experimental results demonstrate that our Low-Complexity and Low-Memory Carpool Matching method achieves the highest degree of performance with regard to solution quality, processing time, and memory requirements of all evaluated methods.

Haze removal is the process by which horizontal obscuration is eliminated from hazy images captured during inclement weather. Images captured in natural environments with varied weather conditions frequently exhibit localized light sources or color-shift effects. The occurrence of these effects presents a difficult challenge for hazy image restoration, with which many traditional restoration methods cannot adequately contend. In this article, we present a new image haze removal approach based on Fisher's linear discriminant-based dual dark channel prior scheme in order to solve the problems associated with the presence of localized light sources and color shifts, and thereby achieve effective restoration. Experimental restoration results via qualitative and quantitative evaluations show that our proposed approach can provide higher haze-removal efficacy for images captured in varied weather conditions than can the other state-of-the-art approaches.

The visibility of outdoor images captured in inclement weather is often degraded due to the presence of haze, fog, sandstorms, and so on. Poor visibility caused by atmospheric phenomena in turn causes failure in computer vision applications, such as outdoor object recognition systems, obstacle detection systems, video surveillance systems, and intelligent transportation systems. In order to solve this problem, visibility restoration (VR) techniques have been developed and play an important role in many computer vision applications that operate in various weather conditions. However, removing haze from a single image with a complex structure and color distortion is a difficult task for VR techniques. This paper proposes a novel VR method that uses a combination of three major modules: 1) a depth estimation (DE) module; 2) a color analysis (CA) module; and 3) a VR module. The proposed DE module takes advantage of the median filter technique and adopts our adaptive gamma correction technique. By doing so, halo effects can be avoided in images with complex structures, and effective transmission map estimation can be achieved. The proposed CA module is based on the gray world assumption and analyzes the color characteristics of the input hazy image. Subsequently, the VR module uses the adjusted transmission map and the color-correlated information to repair the color distortion in variable scenes captured during inclement weather conditions. The experimental results demonstrate that our proposed method provides superior haze removal in comparison with the previous state-of-the-art method through qualitative and quantitative evaluations of different scenes captured during various weather conditions.

The development of fully automatic face annotation techniques in online social networks is currently very important for effective management and organization of a large number of personal photos shared on social network platforms. In this paper, we first propose the personalized hierarchical database access architecture for each member by taking advantage of various social network context types to substantially reduce time consumption. Next, we construct the personalized and adaptive fused face recognition (FR) unit for each member, which uses the AdaBoost algorithm to fuse several different types of base classifiers to produce highly reliable face annotation results. Additionally, to efficiently select suitable personalized face recognizers and then effectively merge multiple personalized face recognizer results, we propose two collaborative FR strategies: the owner with a highest priority rule and using a weighted majority rule for query photos within our collaborative FR framework. The experiment results demonstrate that the evaluation methodologies produced F -measure and Similarity accuracy rates that were, respectively, 64.03% and 63.05% higher for the proposed method in comparison to other state-of-the-art face annotation methods, as well as demonstrating that our method can result in a reduction in overall processing time of 78.06%.

Motion detection, the process which segments moving objects in video streams, is the first critical process and plays an important role in video surveillance systems. Dynamic scenes are commonly encountered in both indoor and outdoor situations and contain objects such as swaying trees, spouting fountains, rippling water, moving curtains, and so on. However, complete and accurate motion detection in dynamic scenes is often a challenging task. This paper presents a novel motion detection approach based on radial basis function artificial neural networks to accurately detect moving objects not only in dynamic scenes but also in static scenes. The proposed method involves two important modules: a multibackground generation module and a moving object detection module. The multibackground generation module effectively generates a flexible probabilistic model through an unsupervised learning process to fulfill the property of either dynamic background or static background. Next, the moving object detection module achieves complete and accurate detection of moving objects by only processing blocks that are highly likely to contain moving objects. This is accomplished by two procedures: the block alarm procedure and the object extraction procedure. The detection results of our method were evaluated by qualitative and quantitative comparisons with other state-of-the-art methods based on a wide range of natural video sequences. The overall results show that the proposed method substantially outperforms existing methods with Similarity and F1 accuracy rates of 69.37% and 65.50%, respectively.

Contrast enhancement is crucial when generating high quality images for image processing applications, such as digital image or video photography, liquid crystal display processing, and medical image analysis. In order to achieve real-time performance for high-definition video applications, it is necessary to design efficient contrast enhancement hardware architecture to meet the needs of real-time processing. In this paper, we propose a novel hardware-oriented contrast enhancement algorithm which can be implemented effectively for hardware design. In order to be considered for hardware implementation, approximation techniques are proposed to reduce these complex computations during performance of the contrast enhancement algorithm. The proposed hardware-oriented contrast enhancement algorithm achieves good image quality by measuring the results of qualitative and quantitative analyzes. To decrease hardware cost and improve hardware utilization for real-time performance, a reduction in circuit area is proposed through use of parameter-controlled reconfigurable architecture. The experiment results show that the proposed hardware-oriented contrast enhancement algorithm can provide an average frame rate of 48.23 frames/s at high definition resolution 1920 × 1080.

The visibility of images of outdoor road scenes will generally become degraded when captured during inclement weather conditions. Drivers often turn on the headlights of their vehicles and streetlights are often activated, resulting in localized light sources in images capturing road scenes in these conditions. Additionally, sandstorms are also weather events that are commonly encountered when driving in some regions. In sandstorms, atmospheric sand has a propensity to irregularly absorb specific portions of a spectrum, thereby causing color-shift problems in the captured image. Traditional state-of-the-art restoration techniques are unable to effectively cope with these hazy road images that feature localized light sources or color-shift problems. In response, we present a novel and effective haze removal approach to remedy problems caused by localized light sources and color shifts, which thereby achieves superior restoration results for single hazy images. The performance of the proposed method has been proven through quantitative and qualitative evaluations. Experimental results demonstrate that the proposed haze removal technique can more effectively recover scene radiance while demanding fewer computational costs than traditional state-of-the-art haze removal techniques.

Automated motion detection technology is an integral component of intelligent transportation systems, and is particularly essential for management of traffic and maintenance of traffic surveillance systems. Traffic surveillance systems using video communication over real-world networks with limited bandwidth often encounter difficulties due to network congestion and/or unstable bandwidth. This is especially problematic in wireless video communication. This has necessitated the development of a rate control scheme which alters the bit-rate to match the obtainable network bandwidth, thereby producing variable bit-rate video streams. However, complete and accurate detection of moving objects under variable bit-rate video streams is a very difficult task. In this paper, we propose an approach for motion detection which utilizes an analysis-based radial basis function network as its principal component. This approach is applicable not only in high bit-rate video streams, but in low bit-rate video streams, as well. The proposed approach consists of a various background generation stage and a moving object detection stage. During the various background generation stage, the lower-dimensional Eigen-patterns and the adaptive background model are established in variable bit-rate video streams by using the proposed approach in order to accommodate the properties of variable bit-rate video streams. During the moving object detection stage, moving objects are extracted via the proposed approach in both low bit-rate and high bit-rate video streams; detection results are then generated through the output value of the proposed approach. The detection results produced through our approach indicate it to be highly effective in variable bit-rate video streams over real-world limited bandwidth networks. In addition, the proposed method can be easily achieved for real-time application. Quantitative and qualitative evaluations demonstrate that it offers advantages over other state-of-the-art methods. For instance, Similarity and F1accuracy rates produced via the proposed approach were up to 86.38% and 89.88% higher than those produced via other compared methods, respectively.

Automated detection of moving objects is an essential task for any intelligent transportation system. However, conventional motion detection techniques often suffer from the loss of moving objects due to bit-rate variation in video streams transmitted via wireless video communication systems. To achieve motion detection that is both reliable and accurate in video streams of variable bit-rate, this paper proposes a novel motion detection approach which is based on grey relational analysis, and which integrates a multi-quality background generation module and a moving object detection module. As our experimental results demonstrate, the proposed approach attained superior motion detection performance compared to other state-of-the-art techniques based on qualitative and quantitative evaluations. Quantitative evaluations produced F1 and Similarity accuracy scores for the proposed approach that were up to 59.96% and 55.42% higher than those of the other compared techniques, respectively.

Haze removal is the process by which horizontal obscuration is eliminated from hazy images captured during inclement weather. Sandstorms present a particularly challenging condition, images captured during sandstorms often exhibit color-shift effects due to inadequate spectrum absorption. In this paper, we present a new type of haze removal approach which uses a combination of hybrid spectrum analysis and dark channel prior in order to repair color shifts and thereby achieve effective restoration of hazy images captured during sandstorms. The restoration results and qualitative evaluation demonstrate that our proposed approach can provide superior restoration results for images captured during sandstorms in comparison with the previous state-of-the-art approach.

Outdoor images captured during inclement weather conditions generally exhibit visibility degradation. Localized light sources often result from activation of streetlights and vehicle headlights and are common scenarios in these conditions. The presence of localized light sources in hazy images may cause the generation of over saturation artifacts when those images are restored by traditional state-of-the-art haze removal techniques. Therefore, we propose a novel haze removal approach based on the proposed hybrid dark channel prior technique in order to remedy the problems associated with localized light sources during image restoration. The overall results show that the proposed haze removal approach can recover haze-free images more effectively than can the other previous state-of-the-art haze removal approach while avoiding over-saturation.

The visibility of outdoor images captured in inclement weather will become degraded due to the presence of haze, fog, mist, and so on. Poor visibility caused by atmospheric phenomenon in turn causes failure in computer vision applications, such as outdoor object recognition systems, obstacle detection systems, video surveillance systems, and intelligent transportation systems. In order to solve this problem, visibility restoration techniques have been developed and play an important role in many computer vision applications. However, complete haze removal from a single image with a complex structure is difficult for visibility restoration techniques to achieve. This paper proposes a novel visibility restoration method which utilizes a combination of the median filter operation and the dark channel prior in order to achieve effective haze removal in a single image with a complex structure. The experimental results demonstrate that our proposed method provides superior haze removal in comparison to the previous state-of-the-art method through visual evaluation of different scenes.

This paper proposes an efficient method to modify histograms and enhance contrast in digital images. Enhancement plays a significant role in digital image processing, computer vision, and pattern recognition. We present an automatic transformation technique that improves the brightness of dimmed images via the gamma correction and probability distribution of luminance pixels. To enhance video, the proposed image-enhancement method uses temporal information regarding the differences between each frame to reduce computational complexity. Experimental results demonstrate that the proposed method produces enhanced images of comparable or higher quality than those produced using previous state-of-the-art methods.

Automated motion detection, which segments moving objects from video streams, is the key technology of intelligent transportation systems for traffic management. Traffic surveillance systems use video communication over real-world networks with limited bandwidth, which frequently suffers because of either network congestion or unstable bandwidth. Evidence supporting these problems abounds in publications about wireless video communication. Thus, to effectively perform the arduous task of motion detection over a network with unstable bandwidth, a process by which bit-rate is allocated to match the available network bandwidth is necessitated. This process is accomplished by the rate control scheme. This paper presents a new motion detection approach that is based on the cerebellar-model-articulation-controller (CMAC) through artificial neural networks to completely and accurately detect moving objects in both high and low bit-rate video streams. The proposed approach is consisted of a probabilistic background generation (PBG) module and a moving object detection (MOD) module. To ensure that the properties of variable bit-rate video streams are accommodated, the proposed PBG module effectively produces a probabilistic background model through an unsupervised learning process over variable bit-rate video streams. Next, the MOD module, which is based on the CMAC network, completely and accurately detects moving objects in both low and high bit-rate video streams by implementing two procedures: 1) a block selection procedure and 2) an object detection procedure. The detection results show that our proposed approach is capable of performing with higher efficacy when compared with the results produced by other state-of-the-art approaches in variable bit-rate video streams over real-world limited bandwidth networks. Both qualitative and quantitative evaluations support this claim; for instance, the proposed approach achieves Similarity and F1 accuracy rates that are 76.40% and 84.37% higher than those of existing approaches, respectively.

Motion detection plays an important role in the video surveillance system. Video communications over wireless networks can easily suffer from network congestion or unstable bandwidth, especially for embedded application. A rate control scheme produces various bit-rate video streams to match the available network bandwidth. However, effective detection of moving objects in various bit-rate video streams is a very difficult problem. This paper proposes an advanced approach based on the counter-propagation network through artificial neural networks to achieve effective moving object detection in various bit-rate video streams. We compare our method with other state-of-the-art methods. To demonstrate the performance of our proposed method in regard to object extraction, we analyze qualitative and quantitative comparisons in real-world limited bandwidth networks over a wide range of natural video sequences. The overall results show that our proposed method substantially outperforms other state-of-the-art methods by Similarity and F1 accuracy rates of 73.84% and 84.94%, respectively.

Automated vehicle detection plays an essential role in the traffic video surveillance system. Video communication of these traffic cameras over real-world limited bandwidth networks can frequently suffer network congestion or unstable bandwidth, especially in regard to wireless systems. This often hinders the detection of moving vehicles in variable bit-rate video streams. This paper presents a novel approach for vehicle detection based on probabilistic neural networks through artificial neural networks which can accurately detect moving vehicles not only in high bit-rate video streams but also in low bit-rate video streams. The overall results of detection accuracy analyses demonstrate that the proposed approach has a substantially higher degree of both qualitative and quantitative efficacy than other state-of-the-art methods. For instance, the proposed method achieved Similarity and F1 accuracy rates that were up to 77.69% and 81.85% higher than the other compared methods, respectively.

Motion detection, the process which segments moving objects in video streams, is the first critical process of the automatic video surveillance system. However, the accuracy of this significant process is usually reduced by the dynamic scenes, which are commonly encountered in both indoor and outdoor situations. In this paper, the accurate motion detection is achieved by the proposed method based on a radial basis function neural network. Our method involves a multi-background generation module and a moving object detection module. In the first module, the flexible multi-background model is generated by an unsupervised learning process to fulfil the property of either dynamic or static backgrounds. Next, the moving object detection module computes the binary object detection mask as the final result through the applied suitable threshold value. The detection results of our proposed method were compared with other state-of-the-art methods through qualitative visual inspection and quantitative estimation. The overall results show that the proposed method substantially outperforms existing methods by Similarity and F1accuracy rates of up to 82.08% and 86.75%, respectively.

This paper proposes an efficient histogram modification method for contrast enhancement, which plays a significant role in digital image processing, computer vision, and pattern recognition. We present an automatic transformation technique to improve the brightness of dimmed images based on the gamma correction and probability distribution of the luminance pixel. Experimental results show that the proposed method produces enhanced images of comparable or higher quality than previous state-of-the-art methods.

Motion detection is the first essential process in the extraction of information regarding moving objects and makes use of stabilization in functional areas, such as tracking, classification, recognition, and so on. In this paper, we propose a novel and accurate approach to motion detection for the automatic video surveillance system. Our method achieves complete detection of moving objects by involving three significant proposed modules: a background modeling (BM) module, an alarm trigger (AT) module, and an object extraction (OE) module. For our proposed BM module, a unique two-phase background matching procedure is performed using rapid matching followed by accurate matching in order to produce optimum background pixels for the background model. Next, our proposed AT module eliminates the unnecessary examination of the entire background region, allowing the subsequent OE module to only process blocks containing moving objects. Finally, the OE module forms the binary object detection mask in order to achieve highly complete detection of moving objects. The detection results produced by our proposed (PRO) method were both qualitatively and quantitatively analyzed through visual inspection and for accuracy, along with comparisons to the results produced by other state-of-the-art methods. The analyses show that our PRO method has a substantially higher degree of efficacy, outperforming other methods by an metric accuracy rate of up to 53.43%.

In this paper, we propose a novel background subtraction approach in order to accurately detect moving objects. Our method involves three important proposed modules: a block alarm module, a background modeling module, and an object extraction module. The block alarm module efficiently checks each block for the presence of either a moving object or background information. This is accomplished by using temporal differencing pixels of the Laplacian distribution model and allows the subsequent background modeling module to process only those blocks that were found to contain background pixels. Next, the background modeling module is employed in order to generate a high-quality adaptive background model using a unique two-stage training procedure and a novel mechanism for recognizing changes in illumination. As the final step of our process, the proposed object extraction module will compute the binary object detection mask through the applied suitable threshold value. This is accomplished by using our proposed threshold training procedure. The performance evaluation of our proposed method was analyzed by quantitative and qualitative evaluation. The overall results show that our proposed method attains a substantially higher degree of efficacy, outperforming other state-of-the-art methods bySimilarityandF1accuracy rates of up to 35.50% and 26.09%, respectively.

In this paper, we propose a novel background subtraction approach in order to accurately detect moving objects. Our method involves three important proposed modules: a block alarm module, a background modeling module, and an object extraction module. Our proposed block alarm module efficiently checks each block for the presence of either moving object or background information. This is accomplished by using temporal differencing pixels of the Laplacian distribution model and allows the subsequent background modeling module to process only those blocks found to contain background pixels. For our proposed background modeling module, a unique two-stage background training procedure is performed using Rough Training followed by Precise Training in order to generate a high-quality adaptive background model. As the final step of our process, we present an object extraction module which will compute the binary object detection mask through the applied suitable threshold value. This is accomplished by using our proposed threshold training procedure in order to achieve accurate and complete detection of moving objects. The overall results of these analyses demonstrate that our proposed method attains a substantially higher degree of efficacy, outperforming other state-of-the-art methods by Similarity and F1accuracy rates of up to 57.17% and 48.48%, respectively.