Research in human gait has contributed to clinical applications in physiotherapy and preventative medicine by improving the understanding and measurement of human gait patterns. In this context, characterization of gait events and kinematic models are essential for medical intervention. This paper proposes a novel gait event detection method, using deep learning for the kinematic model. The setup uses two IMU sensors from which the angles of the kinematic model are computed, and a FSR sensor to detect the Heel Strike event (HS). A microcontroller digitally processed the signals from these sensors in real-time, and saved the gait data. We collected data from healthy subjects representing various age groups (young, adolescent, and elderly), selected by a medical specialist. Firstly, a kinematic curve pattern was created using three types of deep networks. Secondly, the pattern was subsequently applied to detect Heel Strike (HS) events using Dynamic Time Warping (DTW). A detection average of 96.64% was obtained using a single kinematic model, compared to 76.82% obtained in other studies for HS detection. Furthermore, our research provides medical specialists with a kinematic gait curve to develop tools to automatically detect critical points in gait impairments.

Autonomous driving requires information such as the velocity of other vehicles to prevent potential hazards. This work proposes a real-time deep learning-based framework to estimate vehicle speeds from image captures through an onboard camera. Vehicles are detected and tracked by the proposed deep neural networks and a tracking algorithm, which analyzes the trajectories. Finally, a linear regression model estimates the speed of a vehicle based on its position and size in the camera frame. This proposal has been tested with two sequences of the Prevention dataset with satisfactory results. The system can estimate the speed of multiple vehicles simultaneously. It can be integrated easily with onboard computer systems, thus allowing to development of a low-cost solution for speed estimation in an everyday vehicle. The potential applications include vehicle safety systems, driver assistance, and autonomous driving technologies.

Human activity recognition is an application of machine learning with the aim of identifying activities from the gathered activity raw data acquired by different sensors. In medicine, human gait is commonly analyzed by doctors to detect abnormalities and determine possible treatments for the patient. Monitoring the patient's activity is paramount in evaluating the treatment's evolution. This type of classification is still not enough precise, which may lead to unfavorable reactions and responses. A novel methodology that reduces the complexity of extracting features from multimodal sensors is proposed to improve human activity classification based on accelerometer data. A sliding window technique is used to demarcate the first dominant spectral amplitude, decreasing dimensionality and improving feature extraction. In this work, we compared several state-of-art machine learning classifiers evaluated on the HuGaDB dataset and validated on our dataset. Several configurations to reduce features and training time were analyzed using multimodal sensors: all-axis spectrum, single-axis spectrum, and sensor reduction.

Abstract In the area of medical imaging, one of the factors that can negatively influence the performance of prediction algorithms is the limited number of observations for each class within a labeled dataset. Usually, in order to increase the samples, a second set of unlabeled images is used. However, this set adds two new problems (i) finding patient observations with different pathologies than those observed in the labeled data set and (ii) finding images belonging to a different distribution from the dataset used in the model training process. This way, merging datasets from different sources can have an adverse effect on the distribution of features. Encountering this type of data (better known as out-of-distribution data) within the deployment environments may also lead to varying degrees of performance degradation as can be seen in the different experimental results obtained. In this research, a study of the behavior of Feature Density is made, as a mathematical model for the estimation of predictive uncertainty in supervised classification algorithms, in order to improve the behavior when out-of-distribution data are presented in the dataset. The Feature Density method is based on the estimation of feature density by means of histogram calculation (or Probability Density Function). The advantage of this method over the baseline approach (Mahalanobis distance) is that it does not assume a Gaussian-type distribution of sample characteristics and serves to estimate the uncertainty. This work focuses on the binary classification of mammography X-ray images from three different datasets simulating the condition of a different degree of contamination with out-of-distribution sample. According to the obtained results, the performance of the proposed method depends directly on the architecture of the implemented neural network.

Neural rendering is a relatively new field of research that aims to produce high quality perspectives of a 3D scene from a reduced set of sample images. This is done with the help of deep artificial neural networks that model the geometry and color characteristics of the scene. The NeX model relies on neural basis expansion to yield accurate results with a lower computational load than the previous NeRF model. In this work, a procedure is proposed to further enhance the quality of the perspectives generated by NeX. Our proposal is based on the combination of the outputs of several NeX models by a consensus mechanism. The approach is compared to the original NeX for a wide range of scenes. It is found that our method significantly outperforms the original procedure, both in quantitative and qualitative terms.

Social conflicts appearing in the media are increasing public awareness about security issues, resulting in a higher demand of more exhaustive environment monitoring methods. Automatic video surveillance systems are a powerful assistance to public and private security agents. Since the arrival of deep learning, object detection and classification systems have experienced a large improvement in both accuracy and versatility. However, deep learning-based object detection and classification systems often require expensive GPU-based hardware to work properly. This paper presents a novel deep learning-based foreground anomalous object detection system for video streams supplied by panoramic cameras, specially designed to build power efficient video surveillance systems. The system optimises the process of searching for anomalous objects through a new potential detection generator managed by three different multivariant homoscedastic distributions. Experimental results obtained after its deployment in a Jetson TX2 board attest the good performance of the system, postulating it as a solvent approach to power saving video surveillance systems.

Skin cancer is one of the most prevalent diseases among people. Physicians have a challenge every time they have to determine whether a diseased skin is benign or malign. There exist clinical diagnosis methods (such as the ABCDE rule), but they depend mainly on the physician's experience and might be imprecise. Deep learning models are very extended in medical image analysis, and several deep models have been proposed for moles classification. In this work, a convolutional neural network is proposed to support the diagnosis procedure. The proposed MobileNetV2-based model is improved by a shifting technique, providing better performance than raw transfer learning models for moles classification. Experiments show that this technique could be applied to the state-of-the-art deep models to improve their results and outperform the training phase.

Gait analysis is widely used by doctors to detect anomalies and conclude possible treatments to patient. Conventionally, the gait analysis has been considered subjectively and now is use the technology to improve the data information. The sensors noises, however, causes errors in kinematic data to analyze any waveform, and this analysis requires a large amount of noiseless data for using artificial intelligent. In contrast, this paper presents an initial study about acquiring human gait parameters and data to get a model using computer learning. Therefore, we developed a portable acquisition system noninvasive using an online recursive algorithm in a micro-controller for processing and filtering signals of wearable sensors. The Data Acquisition Signal (DAS) system utilizes a Force Sensitive Resistor (FSR) on the heel and two inertial sensors, one in the thigh and one in the leg, to measure the knee angle; such system calibrates automatically the inertial sensors in each experiment. DAS system has a user-interface that includes intelligent algorithms to normalize, interpolate, and obtain the model curve with fitting of the data showing the gait phases. Our experiments were tested on non-pathology patients with different ages (young, adult and elder) with normal gait pattern selected by a physiotherapist. To know the reliability of the kinematic model, we altered the gait of each patient by shifting the floor and footwear. The results and the gait models seen by the physiotherapist were displayed on an interface.

Clustering is one of the most common applications of unsupervised learning, being present in many statistical data analysis processes performed by scientists and engineers. Because of their special features, some categories of Artificial Neural Networks have demonstrated to be specially efficient when it comes to clustering. The Growing Neural Gas (GNG) is a good example of these networks, not only because its capability for revealing the clusters underlying in a certain distribution with an optimized number of neurons, but to faithfully describe the topological relations among the different clusters of a dataset. However, because of their intrinsic nature, there will be some data distributions with regions where no data can be found. Aiming to perform a clustering process on these datasets, this paper presents the design of a Growing Neural Gas-inspired model that keeps its neuron prototypes out of a set of regions previously specified, namely Forbidden Region Growing Neural Gas (FRGNG). Experimental results illustrate how this model can represent an alternative, in terms of accuracy, to one of the most recent region avoiding clustering algorithms such as the Forbidden Region Self-Organizing Map (FRSOFM).

Small robots have numerous interesting applications in domains like industry, education, scientific research, and services. For most applications vision is important, however, the limitations of the computing hardware make this a challenging task. In this paper, we address the problem of real-time object recognition and propose the Fast Regions of Interest Search (FROIS) algorithm to quickly find the ROIs of the objects in small robots with low-performance hardware. Subsequently, we use two methods to analyze the ROIs. First, we develop a Convolutional Neural Network on a desktop and deploy it onto the low-performance hardware for object recognition. Second, we adopt the Histogram of Oriented Gradients descriptor and linear Support Vector Machines classifier and optimize the HOG component for faster speed. The experimental results show that the methods work well on our small robots with Raspberry Pi 3 embedded 1.2 GHz ARM CPUs to recognize the objects. Furthermore, we obtain valuable insights about the trade-offs between speed and accuracy.

Automatic video surveillance systems are usually designed to detect anomalous objects being present in a scene or behaving dangerously. In order to perform adequately, they must incorporate models able to achieve accurate pattern recognition in an image, and deep learning neural networks excel at this task. However, exhaustive scan of the full image results in multiple image blocks or windows to analyze, which could make the time performance of the system very poor when implemented on low cost devices. This paper presents a system which attempts to detect abnormal moving objects within an area covered by a PTZ camera while it is planning. The decision about the block of the image to analyze is based on a mixture distribution composed of two components: a uniform probability distribution, which represents a blind random selection, and a mixture of Gaussian probability distributions. Gaussian distributions represent windows in the image where anomalous objects were detected previously and contribute to generate the next window to analyze close to those windows of interest. The system is implemented on a Raspberry Pi microcontroller-based board, which enables the design and implementation of a low-cost monitoring system that is able to perform image processing.

Enhancing resolution is a permanent goal in magnetic resonance (MR) imaging, in order to keep improving diagnostic capability and registration methods. Super-resolution (SR) techniques are applied at the postprocessing stage, and their use and development have progressively increased during the last years. In particular, example-based methods have been mostly proposed in recent state-of-the-art works. In this paper, a combination of a deep-learning SR system and a random shifting technique to improve the quality of MR images is proposed, implemented and tested. The model was compared to four competitors: cubic spline interpolation, non-local means upsampling, low-rank total variation and a three-dimensional convolutional neural network trained with patches of HR brain images (SRCNN3D). The newly proposed method showed better results in Peak Signal-to-Noise Ratio, Structural Similarity index, and Bhattacharyya coefficient. Computation times were at the same level as those of these up-to-date methods. When applied to downsampled MR structural Tl images, the new method also yielded better qualitative results, both in the restored images and in the images of residuals.

Abstract The construction of a model of the background of a scene still remains as a challenging task in video surveillance systems, in particular for moving cameras. This work presents a novel approach for constructing a panoramic background model based on the neural gas network and a subsequent piecewise linear interpolation by Delaunay triangulation. Furthermore, an ensemble model of neural gas networks is also proposed. The approach can handle arbitrary camera directions and zooms for a pan‐tilt‐zoom camera‐based surveillance system. After testing the proposed approach on several indoor sequences, the results demonstrate that the proposed methods are effective and suitable to use for real‐time video surveillance applications.

One of the most important challenges in computer vision applications is the background modeling, especially when the background is dynamic and the input distribution might not be stationary, i.e. the distribution of the input data could change with time (e.g. changing illuminations, waving trees, water, etc.). In this work, an unsupervised learning neural network is proposed which is able to cope with progressive changes in the input distribution. It is based on a dual learning mechanism which manages the changes of the input distribution separately from the cluster detection. The proposal is adequate for scenes where the background varies slowly. The performance of the method is tested against several state-of-the-art foreground detectors both quantitatively and qualitatively, with favorable results.

In this paper a controller for PTZ cameras based on an unsupervised neural network model is presented. It takes advantage of the foreground mask generated by a non-parametric foreground detection subsystem. Thus, our aim is to optimize the movements of the PTZ camera to attain the maximum coverage of the observed scene in presence of moving objects. A growing neural gas (GNG) is applied to enhance the representation of the foreground objects. Both qualitative and quantitative results are reported using several widely used datasets, which demonstrate the suitability of our approach.

The construction of a model of the background of a scene still remains as a challenging task in video surveillance systems, in particular for moving cameras. This work presents a novel approach for constructing a panoramic background model based on competitive learning neural networks and a subsequent piecewise linear interpolation by Delaunay triangulation. The approach can handle arbitrary camera directions and zooms for a Pan-Tilt-Zoom (PTZ) camera-based surveillance system. After testing the proposed approach on several indoor sequences, the results demonstrate that the proposed method is effective and suitable to use for real-time video surveillance applications.

The selection of the best color space is a fundamental task in detecting foreground objects on scenes. In many situations, especially on dynamic backgrounds, neither grayscale nor RGB color spaces represent the best solution to detect foreground objects. Other standard color spaces, such as YCbCr or HSV, have been proposed for background modeling in the literature; although the best results have been achieved using diverse color spaces according to the application, scene, algorithm, etc. In this work, a color space and color component weighting selection process is proposed to detect foreground objects in video sequences using self-organizing maps. Experimental results are also provided using well known benchmark videos.

Growing hierarchical self-organizing models are characterized by the flexibility of their structure, which can easily accommodate for complex input datasets. However, most proposals use the Euclidean distance as the only error measure. Here we propose a way to introduce Bregman divergences in these models, which is based on stochastic approximation principles, so that more general distortion measures can be employed. A procedure is derived to compare the performance of networks using different divergences. Moreover, a probabilistic interpretation of the model is provided, which enables its use as a Bayesian classifier. Experimental results are presented for classification and data visualization applications, which show the advantages of these divergences with respect to the classical Euclidean distance.

Self-Organizing Maps (SOM) have some problems related to its fixed topology and its lack of representation of hierarchical relations among input data. Growing Hierarchical SOMs (GHSOM) solve these limitations by generating a hierarchical architecture that is automatically determined according to the input data and reflects the inherent hierarchical relations among them. These advantages can be utilized to perform a compression of an image, where the size of the codebook (leaf neurons in the hierarchy) is automatically established. Moreover, this hierarchy provides a different compression at each layer, where the deeper the layer, the lower the compression rate and the higher the quality of the compressed image. Thus, different trade-offs between compression rate and quality are given by the architecture. Also, the size of the codebooks and the depth of the hierarchy can be controlled by two parameters. In this paper, a new approach for image compression based on the GHSOM model is proposed. Experimental results confirm its good performance.

Background modeling and foreground detection are key parts of any computer vision system. These problems have been addressed in literature with several probabilistic approaches based on mixture models. Here we propose a new kind of probabilistic background models which is based on probabilistic self-organising maps. This way, the background pixels are modeled with more flexibility. On the other hand, a statistical correlation measure is used to test the similarity among nearby pixels, so as to enhance the detection performance by providing a feedback to the process. Several well known benchmark videos have been used to assess the relative performance of our proposal with respect to traditional neural and non neural based methods, with favourable results, both qualitatively and quantitatively. A statistical analysis of the differences among methods demonstrates that our method is significantly better than its competitors. This way, a strong alternative to classical methods is presented.

An anomaly detection system based on a hierarchical self-organizing neural network is presented. The proposed neural network reduces the amount of parameters that a user should define prior to the training to a single parameter. This allows the network to perform more autonomously while maintaining a good performance, which is less dependent on the user experience about the application domain. The experimental results show the behavior of the anomaly detection system when it is applied to the KDD Cup 1999 data set.