In order to make industrial robotic arms adaptively accomplish the uniform grinding tasks for tubular workpieces of different sizes, spatial orientations and surface characteristics, a parameterized planning framework is proposed in this paper. In this framework, Moving-Circle-Determination(MCD)-based geometric parameter calculation is designed for two types of tubular workpieces (both elbow and tee tube). Then the Adaptive Uniform Grouping (AUG) mechanism is designed and applied in path cost calculation module to make all points evenly grouped, and results in a minimal computational complexity of optimization algorithm in the framework. And then Two-stage Progressive Optimization (TPO) algorithm, containing both Experience Generalization Ant Colony System (EGACS) and Double Deep Q-Network (DDQN), is designed to calculate the optimal grinding order in the maximal convergence rate, where optimization capabilities of both EGACS and DDQN are enhanced with accumulation of uniform grinding task based on optimization experiences generalization mechanism applied in TPO algorithm. Finally Parameterized Velocity Vector Summation (PVVS) is designed and applied in the path planning and tracking control module to drive robotic arms to accomplish uniform grinding tasks. Compared to the state-of-the-art methods and algorithms, performance advantages of the planning framework proposed are at least 16.94%, 21.60%, 28.78%, 4.59% and 48.68% in terms of size estimation, spatial orientation estimation, convergence rate, solution quality and computational complexity respectively.

This paper presents a novel approach for visual servoing using neuromorphic event-based cameras. We extend the photometric Gaussian mixture model framework from frame-based to event-based vision by developing a mathematical formulation that bridges conventional models with the sparse, temporally-precise nature of event data. Our method transforms raw event streams into effective visual features through time surface representations, enabling visual servoing that leverages the microsecond temporal resolution and high dynamic range of event cameras. Evaluation using the N-Caltech101 dataset demonstrates excellent convergence characteristics and a high success rate (96.9%) across diverse object categories. Results confirm that our event-based photometric Gaussian mixture approach effectively exploits the temporal precision of event cameras while providing reliable performance for robot control tasks.

Mechanical weeding has grown in popularity and importance in intelligent agriculture as technology and research develop and people become more concerned with environmental preservation and organic farming. The crop’s location is crucial for the technology, which includes object detection and trajectory tracking. The former is responsible for determining the crop’s accurate location, while the latter is in charge of reducing the impact from the environment. In this research, we developed a collection of intelligent weeding equipment based on the YOLOv5 object detection model. To optimize the performance of detection while applying our model to embedded device for real-time weeding application, we incorporated DeepSORT trajectory tracking into YOLO method. We also built a collection of datasets based on corn seedling centers to train the model work properly in the actual world. The results of the investigation demonstrate that occlusion could be resolved and weeding can be implemented more effectively by incorporating trajectory tracking into the object detection model.

Infrared and visible images are captured using different sensors, resulting in various differences between the two modalities. However, current image fusion methods mainly focus on retaining global information, while neglecting to preserve the salient objects of the two source images. Additionally, existing evaluation metrics fail to measure whether the salient objects are preserved in the fused image from the two original modalities. To this end, we propose a novel image fusion method for infrared and visible images called SCFusion, which maintains salient objects consistency between the original two modalities and the fused image. Specifically, we designed a new module called the saliency decision (SD) to separate the unique and common saliency maps from the infrared and visible images for target enhancement in the final fused image. We then introduce a new metric called saliency information weight (SIW) to evaluate the preservation of salient objects by calculating the overlap between the saliency map of the fused image and those of the original modalities. To validate the practical application of our fusion algorithm, we establish a physical visible-infrared fusion system integrating SCFusion to provide real-time service, including a dual-sensor camera and an AI edge platform. Quantitative and qualitative experiments demonstrate the superiority of SCFusion over state-of-the-art methods in terms of salient objects preservation from the original two modalities.

Semantic bird-eye-view (BEV) map is an efficient data representation for environment perception in autonomous driving. In real driving scenarios, the collected sensory data usually exhibit class imbalance. For example, road layouts are often the majority classes and road objects are the minority. Such imbalanced data could lead to inferior performance in BEV map generation, particularly for minority objects due to insufficient learning samples. This work attempts to mitigate this issue from the perspective of network and loss function design. To this end, a diffusion-guided semantic BEV map generation network with a boundary-aware loss is proposed. The network learns the underlying distribution of the data, including the relationship between majority and minority classes. The boundary-aware loss increases weighting for minority classes during training, making the network focus on these classes. Experimental results on a public dataset demonstrate our superiority over the state-of-the-art methods, and our effectiveness in addressing the class imbalance issue.

Semantic Bird-Eye-View (BEV) map is a straightforward data representation for environment perception. It can be used for downstream tasks, such as motion planning and trajectory prediction. However, taking as input a front-view image from a single camera, most existing methods can only provide V-shaped semantic BEV maps, which limits the field-of-view for the BEV maps. To provide a solution to this problem, we propose a novel end-to-end network to generate semantic BEV maps in full view by taking as input the equidistant sequential images. Specifically, we design a self-adapted sequence fusion module to fuse the features from different images in a distance sequence. In addition, a road-aware view transformation module is introduced to wrap the front-view feature map into BEV based on an attention mechanism. We also create a dataset with semantic labels in full BEV from the public nuScenes data. The experimental results demonstrate the effectiveness of our design and the superiority over the state-of-the-art methods.

Abstract: Since the emergence of deep learning, the configuration of hyperparameters has been one of the most significant problems that people have paid attention to. However, traditional hyperparameter optimization techniques typically have drawbacks such as expensive calculation consumption and lengthy training time. With the development of large language models (LLMs), particularly models such as generative pre-trained transformer (GPT), it is achievable to utilize the models’ analysis ability to guide parameter space search. This paper investigates the use of LLMs for hyperparameter optimization in machine learning problems. To evaluate the effectiveness of this strategy, four object detection models, including YOLOv5, YOLOv8, Faster R-CNN, and R-FCN, were used to conduct experiments. At the same time, we compared the distinctions between this approach and traditional ways. The experimental results indicate that combining LLMs with the hyperparameter optimization process can perform comparably or better than conventional methods.

Convolutional Neural Networks (CNNs) are the most widely used and successful approaches for accomplishing the Facial Expression Recognition (FER) task. However, these technologies appear to have reached a bottleneck since the networks are becoming increasingly complex and heavier, yet the performance improvements remain minimal. The "black box" nature of CNNs makes it challenging to identify and address this crux. This paper aims to address the issue by utilizing the principles of data compression and discriminative representation within a plausible theoretical framework. We are employing an innovative computational framework, drawing inspiration from feedback loop control systems, to develop an interpretable closed-loop transcription model to generate a Linear Discriminative Representation (LDR) for multi-class real-world datasets. This model, comprised of an encoder and decoder that facilitates data mapping between the data space and the feature space, employs the output of the transcription system as feedback or guidance, with the objective of improving the accuracy and efficiency of the transcription process. The optimal LDR is learned jointly for all data classes through a two-player minimax game between the encoder and decoder for the learned representation over a single rate reduction-based objective. The studies conducted on the FER2013 dataset show promising results for the proposed closed-loop formulation. The visual quality of the learned decoder and the classification performance of the encoder are comparable to those of large and complex networks. An accuracy of 70.97% was attained on the FER2013 dataset by applying Principal Component Analysis (PCA) to the learned representation.

Human action generation has shown critical value in both industry application and academic research, especially fine-grained skeleton-based action generation. At present, there are several main ways to achieve fine-grained skeleton-based action generation. In this work, we utilize a generative adversarial network with in-betweening, in order to generate natural and continuous skeleton sequences and better capture complex motion details. In-betweening can be viewed as a prediction task based on the past and future context. Besides, it is convenient to control the result in a personalized way and combine the framework with other network structures to further improve the performance. In particular, two simple discriminators are applied on different timescales and LSTM serves as the foundation of the action generator because of its capability of effectively capturing long-term dependencies and processing sequence data of different lengths. The target noise added to the input of the generator can contribute to the robustness of the system and further improve the performance. Moreover, a novel Tai Chi dataset composed of fine-grained skeleton-based action data is created using high quality motion capture technology. The model is evaluated on two fine-grained skeleton-based datasets, LaFAN1 and Tai Chi, which contain common daily actions and professional sports actions respectively, and it achieves superior performance both qualitatively and quantitatively.

In recent years, humanoid robotics have achieved significant advancements, including those embodied by muscle-skeleton robots. Due to the nonlinear characteristics of these robots, reinforcement learning is a popular method for muscle-skeleton robot control. However, the design of the reward function and the adjustment of hyper parameters is a difficult task when using reinforcement learning. In this paper, we combine reinforcement learning with a large language model to achieve precise control of a humanoid muscle-skeleton robotic arm. We first tell the large language model task, states, and hyper parameters, and then continuously feedback the training results. We can finally get a controller that can control the robot to complete the target-tracking task. The experimental results show that the large language model can propose a suitable reward function based on experience, and adjust the hyper parameters to better training results within several questions and answers.

Correctly understanding surrounding environments is a fundamental capability for autonomous driving. Semantic forecasting of bird-eye-view (BEV) maps can provide semantic perception information in advance, which is important for environment understanding. Currently, the research works on combining semantic forecasting and semantic BEV map generation is limited. Most existing work focuses on individual tasks only. In this work, we attempt to forecast semantic BEV maps in an end-to-end framework for future front-view (FV) images. To this end, we predict depth distributions and context features for FV input images and then forecast depth-context features for the future. The depth-context features are finally converted to the future semantic BEV maps. We conduct ablation studies and create baselines for evaluation and comparison. The results demonstrate that our network achieves superior performance.

Detection of road obstacles is important for autonomous driving. However, road obstacles, like pedestrians, usually account for quite a small portion compared with other semantics, such as road layouts. This leads to the class-imbalance problem in real-world driving datasets and hinders environment perception for autonomous driving. In this paper, we propose an obstacle-sensitive network to improve the semantic Bird-Eye-View (BEV) map generation performance for minority classes. To this end, a context-depth attention module and a boundary-aware loss are introduced. We conduct ablation studies to verify the effectiveness of the proposed network. We also compare our network with other semantic BEV map generation methods. The results demonstrate that our network achieves better performance in terms of semantic BEV map generation, especially for minority classes.

In challenging low-light and adverse weather conditions, thermal vision algorithms, especially object detection, have exhibited remarkable potential, contrasting with the frequent struggles encountered by visible vision algorithms. Nevertheless, the efficacy of thermal vision algorithms driven by deep learning models remains constrained by the paucity of available training data samples. To this end, this paper introduces a novel approach termed the edge-guided conditional diffusion model (ECDM). This framework aims to produce meticulously aligned pseudo thermal images at the pixel level, leveraging edge information extracted from visible images. By utilizing edges as contextual cues from the visible domain, the diffusion model achieves meticulous control over the delineation of objects within the generated images. To alleviate the impacts of those visible-specific edge information that should not appear in the thermal domain, a two-stage modality adversarial training (TMAT) strategy is proposed to filter them out from the generated images by differentiating the visible and thermal modality. Extensive experiments on LLVIP demonstrate ECDM's superiority over existing state-of-the-art approaches in terms of image generation quality. The pseudo thermal images generated by ECDM also help to boost the performance of various thermal object detectors by up to 7.1 mAP. Code is available at https://github.com/lengmo1996/ECDM.

Satellite video single object tracking (SVSOT) stands as a pivotal research area. However, it faces significant challenges in low-light environments, particularly when dealing with dark and weak vehicles. Previous studies have predominantly focused on tracking methods under favorable lighting conditions, neglecting the complexities introduced by inadequate illumination. The difficulty in extracting features from targets in low-light environments, coupled with the susceptibility of dark and weak targets to background noise, exacerbates these challenges. In low-light environments, dark and weak vehicles exhibit less distinctive features and are more susceptible to background interference due to the reduced contrast. To tackle the above challenges, this work proposes an innovative correlation filter (CF)-based tracker (RETrack) that incorporates a retinex-inspired target enhancement. This enhancer integrates an effective low-light enhancement within the CF-based tracker, enhancing target visibility by reallocating target energy based on the characteristics of target motion. Moreover, to mitigate background interference and leverage background information efficiently, an adaptive label update mechanism is developed to suppress background disturbance. Furthermore, this work constructs a satellite video low-light tracking benchmark SATDark, which comprises 120 sequences of dark and weak vehicles. Comprehensive experiments show that RETrack surpasses current leading trackers on the SATDark, providing innovative insights and advancing the field of satellite video object tracking. Additionally, RETrack achieves real-time processing speeds exceeding 30 frames/s on a single CPU, underscoring its practical applicability and efficiency.

Smart agriculture requires an extensive convergence of information technology and agriculture. Attaining intelligence mandates an enormous amount of data to train models. However, it is challenging to acquire a large number of crop image data, limiting the application and growth of computer vision technology in agriculture. To address this problem, we designed a crop image generation system that combines a large language model with visual language multi-modal large models to augment the scale, variety, and resolution of crop image data. First, the system inputs existing real crop images into the visual language multimodal model to extract features and represent crop images in text form. Then, the system passes the crop text representation to the language model for cleaning and processing, which generates prompts to create crop images. The prompts are input into the visual language multi-modal model to generate crop images based on text representation of crops. The resulting crop images undergo image quality evaluation in the visual language multimodal model, and high-quality crop images are saved to the crop image dataset based on the quality evaluation. These steps lead to the formation of the final generated crop image dataset. The experimental results indicate that the crop images generated using the proposed system are similar to but different from the example images. This characteristic enables the expansion of crop data while circumventing redundancy and allowing for resolution control, which is crucial for dense segmentation tasks. Using this method, the existing data can be enlarged up to 7.5 times.

Recently, low-rank representation (LRR) methods have been widely applied for hyperspectral anomaly detection, due to their potentials in separating the backgrounds and anomalies. However, existing LRR models generally convert 3-D hyperspectral images (HSIs) into 2-D matrices, inevitably leading to the destruction of intrinsic 3-D structure properties in HSIs. To this end, we propose a novel tensor low-rank and sparse representation (TLRSR) method for hyperspectral anomaly detection. A 3-D TLR model is expanded to separate the LR background part represented by a tensorial background dictionary and corresponding coefficients. This representation characterizes the multiple subspace property of the complex LR background. Based on the weighted tensor nuclear norm and the$L_{F,1}$sparse norm, a dictionary is designed to make its atoms more relevant to the background. Moreover, a principal component analysis (PCA) method can be assigned as one preprocessing step to exact a subset of HSI bands, retaining enough the HSI object information and reducing computational time of the postprocessing tensorial operations. The proposed model is efficiently solved by the well-designed alternating direction method of multipliers (ADMMs). A comparison with the existing algorithms via experiments establishes the competitiveness of the proposed method with the state-of-the-art competitors in the hyperspectral anomaly detection task.

Due to the Hughes phenomenon, hyperspectral image (HSI) classification under small sample size situation is still a key challenging problem. To alleviate this issue, we propose a novel spectral–spatial prototype learning-based nearest neighbor classifier (SSPLNN) for HSI in this article. The local spectral–spatial neighbor set is first constructed for each sample based on both spectral similarity and spatial structural context to accurately explore the local spectral–spatial information. Then, a spectral–spatial prototype learning model is designed to learn a set of spectral–spatial prototypes, which can optimally utilize both the similarity and variance of samples within each spectral–spatial set and excavate the unseen spectral–spatial variations. The learned spectral–spatial prototypes offer more complementary information to improve the classification accuracy remarkably under small sample size situation. In addition, a linear discriminative projection is simultaneously learned to make each test local spectral–spatial set to be optimally classified to the same class with its nearest neighbor (NN) spectral–spatial prototype set in the projected target subspace. Finally, the NN classifier based on measuring the minimum geometric distance between the projected test spectral–spatial set and the projected spectral–spatial prototype sets is employed to determine the label. Experimental results demonstrate that the proposed SSPLNN method outperforms several well-known classification methods by a large margin on three widely analyzed HSI datasets.

In the past decade, object detection tasks are defined mostly by large public datasets. However, building object detection datasets is not scalable due to inefficient image collecting and labeling. Furthermore, most labels are still in the form of bounding boxes, which provide much less information than the real human visual system. In this paper, we present a method to synthesize object-in-scene images, which can preserve the objects' detailed features without bringing irrelevant information. In brief, given a set of images containing a target object, our algorithm first trains a model to find an approximate center of the object as an anchor, then makes an outline regression to estimate its boundary, and finally blends the object into a new scene. Our result shows that in the synthesized image, the boundaries of objects blend very well with the background. Experiments also show that SOTA segmentation models work well with our synthesized data.

Recognizing new action categories from a few reference samples is an encouraging research field because the cost of labeling data is expensive. This work presents a method for few-shot (or one-shot) skeleton-based action recognition by fusing temporal and spatial features of actions. Trajectory primitives are proposed to characterize the temporal features, which can be obtained by segmenting and clustering the trajectories of joints. After that, we modify the original dynamic time warping (DTW) algorithm and use it to measure the similarity between trajectory primitive sequences. Besides, we compute the joint angles as spatial feature vectors. Support vector machines (SVM) are used to classify the joint angle vectors. In this way, the temporal distance matrix can be calculated by modified DTW, and the spatial distance matrix can be obtained by trained SVM. Finally, we fuse temporal and spatial distance matrices by adjusting a parameter to improve recognition accuracy. Furthermore, extensive experiments are conducted on three small-scale datasets to verify the effectiveness of our proposed method.

Human action recognition is a quite hugely investigated area where most remarkable action recognition networks usually use large-scale coarse-grained action datasets of daily human actions as inputs to state the superiority of their networks. We intend to recognize our small-scale fine-grained Tai Chi action dataset using neural networks and propose a transfer-learning method using NTU RGB+D dataset to pre-train our network. More specifically, the proposed method first uses a large-scale NTU RGB+D dataset to pre-train the Transformer-based network for action recognition to extract common features among human motion. Then we freeze the network weights except for the fully connected (FC) layer and take our Tai Chi actions as inputs only to train the initialized FC weights. Experimental results show that our general model pipeline can reach a high accuracy of small-scale fine-grained Tai Chi action recognition with even few inputs and demonstrate that our method achieves the state-of-the-art performance compared with previous Tai Chi action recognition methods.

For weeding, compared to satellite navigation, using the location information of crops in the field to directly navigate the weeding robot is more accurate, so navigation line extraction is a key point in weeding robot autonomous navigation in the field. Though deep learning and neural network has developed fast in recent years, it does not run fast enough to be used in real time scenarios, so an image processing based navigation line extraction algorithm is proposed in this paper. We used a camera to take RGB images, of which the top and the bottom portion would be cut out and the middle portion would be remained to reduce the impact of distance between the crops and the robot. The green in the original image would be found out by transforming the image into the HSV color and then the morphological operation would be used to remove the noises for further image processing. Generally there are more than one ridges in the image, so it is necessary to find out the ridge in the middle for navigation. We clustered the crops according to the distance between them and chose the cluster in the middle to extract the navigation line. At last, the least square algorithm was used to calculate the navigation line. We used the slope of the navigation line and the distance between it and the center point of the image to control the direction of the robot. Experiments of the weeding robot on a simulated farm field showed that the algorithm can achieve the desired navigation effect and further experiments in the field also showed its good performance.

Due to sensor malfunction and atmosphere disturbances, high-dimensional optical remote sensing (HORS) images often suffer from information missing, such as dead pixels and thick clouds. Tensor decomposition methods have been used to estimate the missing data of HORS images. However, most existing models hardly consider the inherent properties and effective structural information of HORS images. To this end, we propose a novel total variation (TV) regularized weighted tensor ring (TR) decomposition model to recover the missing content of HORS images. The TR decomposition has the powerful low-rank (LR) representation ability to recover the HORS data by employing three low-dimensional tensors, i.e., TR factors. An initialization step and proper weights are designed to enhance the flexibility for exploring different LR properties of TR factors. To further preserve the spatial smoothness, the local spatial TV from three directions is incorporated into the TR decomposition framework. Furthermore, an augmented Lagrange multiplier (ALM) algorithm is designed for solving the resulting optimization problem. Experiments on HORS images demonstrate the performances of the proposed method over the current state-of-the-art baselines.

To improve the classification accuracies of hyperspectral images (HSIs), especially when using a limited number of training samples, a novel superpixel-based multiple statistical feature extraction (SPMSFE) method is proposed in this article. For each dimension-reduced pixel obtained by maximum noise fraction (MNF), the most similar superpixel-based neighbors of different sizes are first identified based on the spatial structures of the HSIs to exploit contextual spatial information accurately. Then, multiple statistical features, including the mean, covariance descriptor, and the Gaussian feature, are extracted for the set of superpixel-based neighbors to fully explore the spatial geometry information, tight correlations between different spectral bands, and spatial–spectral variations from different perspectives, respectively. In addition, these three statistical features of the pixels share the same size and can be utilized for uniform classification without any dimensionality obstacles even though the sizes of the superpixel-based neighbors for different pixels may be different. Next, we construct multiple kernels to map these multiple statistical features in the Euclidean and Riemannian manifold spaces to a uniform Hilbert space and embed them into a multitask kernelized sparse representation classification (MTKSRC) model. The constructed MTKSRC model provides a natural method to effectively fuse the multiple statistical features for excellent classification performance and robustness, especially when using limited numbers of training samples. The experimental results for three widely used HSI data sets demonstrate that the classification accuracy of the proposed SPMSFE method outperforms several latest and state-of-the-art classification methods by a large margin.

The total variation (TV) regularization has been widely used in various applications related to hyperspectral (HS) signal and image processing due to its potential in modeling the underlying smoothness of HS data. However, most existing TV norms usually tend to generate spatial oversmoothing or artifacts. To this end, we propose a novel l0- l1hybrid TV ( l0- l1HTV) regularization with the applications to HS mixed noise removal and compressed sensing (CS). More specifically, l0- l1HTV can be regarded as a globally and locally integrated TV regularizer, where the l0gradient constraint is incorporate into the l1spatial-spectral TV ( l1-SSTV). l1-SSTV is capable of exploiting the local structure information across both spatial and spectral domains, while the l0gradient can promote a globally spectral-spatial smoothness by directly controlling the number of nonzero gradients of HS images. This efficient combination considers more comprehensive prior knowledge of HS images, yielding sharper edge preservation and resolving the above drawbacks of existing pure TV norms. More significantly, l0- l1HTV can be easily injected into HS-related processing models, and an effective algorithm based on the alternating direction method of multipliers (ADMM) is developed to solve the optimization problems. Extensive experiments conducted on several HS data sets substantiate the superiority and effectiveness of the proposed method in comparison with many state-of-the-art methods.

Conventional low-rank (LR)-based hyperspectral image (HSI) denoising models generally convert high-dimensional data into 2-D matrices or just treat this type of data as 3-D tensors. However, these pure LR or tensor low-rank (TLR)-based methods lack flexibility for considering different correlation information from different HSI directions, which leads to the loss of comprehensive structure information and inherent spatial-spectral relationship. To overcome these shortcomings, we propose a novel multidirectional LR modeling and spatial-spectral total variation (MLR-SSTV) model for removing HSI mixed noise. By incorporating the weighted nuclear norm, we obtain the weighted sum of weighted nuclear norm minimization (WSWNNM) and the weighted sum of weighted tensor nuclear norm minimization (WSWTNNM) to estimate the more accurate LR tensor, especially, to remove the dead-line noise better. Gaussian noise is further denoised and the local spatial-spectral smoothness is preserved effectively by SSTV regularization. We develop an efficient algorithm for solving the derived optimization based on the alternating direction method of multipliers (ADMM). Extensive experiments on both synthetic data and real data demonstrate the superior performance of the proposed MLR-SSTV model for HSI mixed noise removal.

Bayesian methods are attracting increasing attention in the field of compressive sensing (CS), as they are applicable to recover signals from random measurements. However, these methods have limited use in many tensor-based cases such as hyperspectral Kronecker compressive sensing (HKCS), because they exploit the sparsity in only one dimension. In this paper, we propose a novel Bayesian model for HKCS in an attempt to overcome the above limitation. The model exploits multi-dimensional block-sparsity such that the information redundancies in all dimensions are eliminated. Laplace prior distributions are employed for sparse coefficients in each dimension, and their coupling is consistent with the multi-dimensional block-sparsity model. Based on the proposed model, we develop a tensor-based Bayesian reconstruction algorithm, which decouples the hyperparameters for each dimension via a low-complexity technique. Experimental results demonstrate that the proposed method is able to provide more accurate reconstruction than existing Bayesian methods at a satisfactory speed. Additionally, the proposed method can not only be used for HKCS, it also has the potential to be extended to other multi-dimensional CS applications and to multi-dimensional block-sparse-based data recovery.

The multiway greedy algorithm is widely used for reconstructions of Tucker-decomposition-based compressive sensing. However, its practicability is limited by the fact that only one support can be updated in most iterations, which increases the required number of iterations and influences the reconstruction speed. To address this problem, in this letter, we propose a strategy for accelerating the multiway greedy reconstruction. The proposed strategy allows all supports to be updated in an iteration such that an over-estimated greedy solution can be obtained through only a few iterations, and the superfluous indexes of each support are removed in subsequent iterations. The computational complexity of the proposed strategy is significantly reduced, comparing to that of the standard multiway greedy algorithm. Simulation results demonstrate that the proposed strategy can expedite the multiway greedy reconstruction without loss of accuracy.

Location is a fundamental service for mobile computing. Typical GPS receivers, although widely available for navigation purposes, may consume too much energy to be useful for many applications. Observing that in many sensing scenarios, the location information can be post-processed when the data is uploaded to a server, we design a cloud-offloaded GPS (CO-GPS) solution that allows a sensing device to aggressively duty-cycle its GPS receiver and log just enough raw GPS signal for post-processing. Leveraging publicly available information such as GNSS satellite ephemeris and an Earth elevation database, a cloud service can derive good quality GPS locations from a few milliseconds of raw data. Using our design of a portable sensing device platform called CLEON, we evaluate the accuracy and efficiency of the solution. Compared to more than 30 seconds of heavy signal processing on standalone GPS receivers, we can achieve three orders of magnitude lower energy consumption per location tagging.

Recently, many researchers have attempted to exploit spectral–spatial features and sparsity-based hyperspectral image classifiers for higher classification accuracy. However, challenges remain for efficient spectral–spatial feature generation and combination in the sparsity-based classifiers. This paper utilizes the empirical mode decomposition (EMD) and morphological wavelet transform (MWT) to gain spectral–spatial features, which can be significantly integrated by the sparse multitask learning (MTL). In the feature extraction step, the sum of the intrinsic mode functions extracted by an optimized EMD is taken as spectral features, whereas the spatial features are formed by the low-frequency components of one-level MWT. In the classification step, a kernel-based sparse MTL solved by the accelerated proximal gradient is applied to analyze both the spectral and spatial features simultaneously. Experiments are conducted on two benchmark data sets with different spectral and spatial resolutions. It is found that the proposed methods provide more accurate classification results compared to the state-of-the-art techniques with various ratio of training samples.

Location is a fundamental service for mobile computing. Typical GPS receivers, although widely available, consume too much energy to be useful for many applications. Observing that in many sensing scenarios, the location information can be post-processed when the data is uploaded to a server, we design a Cloud-Offloaded GPS (CO-GPS) solution that allows a sensing device to aggressively duty-cycle its GPS receiver and log just enough raw GPS signal for post-processing. Leveraging publicly available information such as GNSS satellite ephemeris and an Earth elevation database, a cloud service can derive good quality GPS locations from a few milliseconds of raw data. Using our design of a portable sensing device platform called CLEO, we evaluate the accuracy and efficiency of the solution. Compared to more than 30 seconds of heavy signal processing on standalone GPS receivers, we can achieve three orders of magnitude lower energy consumption per location tagging.

We present the design of the Tempo mote that operates on ambient energy harvested from the environment. Equipped with a ultra low-power timing module that acquires Coordinated Universal Time (UTC) information from a longrange radio transmitter, Tempo can persistently access the global time and is thereby resilient to power outages. A prototype implementation of the Tempo mote shows that it achieves millisecond level accuracy at 100 μA current draw. We argue that one can more generally leverage the access to global time across all nodes of a wireless sensor network to overcome the challenges related to the very tight energy budget that is inherent with harvesting ambient energy.

We introduce the Egs mote platform based on the Cortex M3 microcontroller that focuses on medical sensing applications. Egs uses an Atmel SAM3U microcontroller that runs up to 96 MHz and has up to 52 KB of RAM and 256 KB of Flash. Egs combines this microcontroller with two radios (802.15.4 and Bluetooth), external flash, on board sensors, and a LCD touchscreen to enable a rich set of wireless sensing applications.

The relationship of similarity may be the most universal relationship that exists between every two objects in either the material world or the mental world. Although similarity modeling has been the focus of cognitive science for decades, many theoretical and realistic issues are still under controversy. In this paper, a new theoretical framework that conforms to the nature of similarity and incorporates the current similarity models into a universal model is presented. The new model, i.e., the systematic similarity model, which is inspired by the contrast model of similarity and structure mapping theory in cognitive psychology, is the universal similarity measurement that has many potential applications in text, image, or video retrieval. The text relevance ranking experiments undertaken in this research tentatively show the validity of the new model.