A Kinect-Based Interactive System for Home-Assisted Active Aging.

Virtually every country in the world is facing an unprecedented challenge: society is aging. Assistive technologies are expected to play a key role in promoting healthy lifestyles in the elderly. This paper presents a Kinect-based interactive system for home-assisted healthy aging, which guides, supervises, and corrects older users when they perform scheduled physical exercises. Interactions take place in gamified environments with augmented reality. Many graphical user interface elements and workflows have been designed considering the sensory, physical and technological shortcomings of the elderly, adapting accordingly the interaction methods, graphics, exercises, tolerance margins, physical goals, and scoring criteria. Experiments involved 57 participants aged between 65 and 80 who performed the same physical routine six times during 15 days. After each session, participants completed a usability survey. Results provided significant evidence that support (1) the effectiveness of the system in assisting older users of different age ranges, (2) the accuracy of the system in measuring progress in physical achievement of the elderly, and (3) a progressive acceptance of the system as it was used. As a main conclusion, the experiments verified that despite their poor technological skills, older people can adapt positively to the use of an interactive assistance tool for active aging if they experience clear benefits.

Roadmap on 3D integral imaging: sensing, processing, and display.

This Roadmap article on three-dimensional integral imaging provides an overview of some of the research activities in the field of integral imaging. The article discusses various aspects of the field including sensing of 3D scenes, processing of captured information, and 3D display and visualization of information. The paper consists of a series of 15 sections from the experts presenting various aspects of the field on sensing, processing, displays, augmented reality, microscopy, object recognition, and other applications. Each section represents the vision of its author to describe the progress, potential, vision, and challenging issues in this field.

Remotely Sensed Data Fusion for Spatiotemporal Geostatistical Analysis of Forest Fire Hazard.

Forest fires are a natural phenomenon which might have severe implications on natural and anthropogenic ecosystems. Future projections predict that, under a climate change environment, the fire season would be lengthier with higher levels of droughts, leading to higher fire severity. The main aim of this paper is to perform a spatiotemporal analysis and explore the variability of fire hazard in a small Greek island, Skiathos (a prototype case of fragile environment) where the land uses mixture is very high. First, a comparative assessment of two robust modeling techniques was examined, namely, the Analytical Hierarchy Process (AHP) knowledge-based and the fuzzy logic AHP to estimate the fire hazard in a timeframe of 20 years (1996-2016). The former technique was proven more representative after the comparative assessment with the real fire perimeters recorded on the island (1984-2016). Next, we explored the spatiotemporal dynamics of fire hazard, highlighting the risk changes in space and time through the individual and collective contribution of the most significant factors (topography, vegetation features, anthropogenic influence). The fire hazard changes were not dramatic, however, some changes have been observed in the southwestern and northern part of the island. The geostatistical analysis revealed a significant clustering process of high-risk values in the southwestern and northern part of the study area, whereas some clusters of low-risk values have been located in the northern territory. The degree of spatial autocorrelation tends to be greater for 1996 rather than for 2016, indicating the potential higher transmission of fires at the most susceptible regions in the past. The knowledge of long-term fire hazard dynamics, based on multiple types of remotely sensed data, may provide the fire and land managers with valuable fire prevention and land use planning tools.

Human gesture recognition under degraded environments using 3D-integral imaging and deep learning.

In this paper, we propose a spatio-temporal human gesture recognition algorithm under degraded conditions using three-dimensional integral imaging and deep learning. The proposed algorithm leverages the advantages of integral imaging with deep learning to provide an efficient human gesture recognition system under degraded environments such as occlusion and low illumination conditions. The 3D data captured using integral imaging serves as the input to a convolutional neural network (CNN). The spatial features extracted by the convolutional and pooling layers of the neural network are fed into a bi-directional long short-term memory (BiLSTM) network. The BiLSTM network is designed to capture the temporal variation in the input data. We have compared the proposed approach with conventional 2D imaging and with the previously reported approaches using spatio-temporal interest points with support vector machines (STIP-SVMs) and distortion invariant non-linear correlation-based filters. Our experimental results suggest that the proposed approach is promising, especially in degraded environments. Using the proposed approach, we find a substantial improvement over previously published methods and find 3D integral imaging to provide superior performance over the conventional 2D imaging system. To the best of our knowledge, this is the first report that examines deep learning algorithms based on 3D integral imaging for human activity recognition in degraded environments.

A RGBD-Based Interactive System for Gaming-Driven Rehabilitation of Upper Limbs.

Current physiotherapy services may not be effective or suitable for certain patients due to lack of motivation, poor adherence to exercises, insufficient supervision and feedback or, in the worst case, refusal to continue with the rehabilitation plan. This paper introduces a novel approach for rehabilitation of upper limbs through KineActiv, a platform based on Microsoft Kinect v2 and developed in Unity Engine. KineActiv proposes exergames to encourage patients to perform rehabilitation exercises prescribed by a specialist, controls the patient's performance, and corrects execution errors on the fly. KineActiv comprises a web platform where the physiotherapist can review session results, monitor patient health, and adjust rehabilitation routines. We recruited 10 patients for assessing the system usability as well as the system performance. Results show that KineActiv is a usable, enjoyable and reliable system, that does not cause any negative feelings.

Cocaine-Induced Preference Conditioning: a Machine Vision Perspective.

Existing work on drug-induced synaptic changes has shown that the expression of perineuronal nets (PNNs) at the cerebellar cortex can be regulated by cocaine-related memory. However, these studies on animals have mostly relied on limited manually-driven procedures, and lack some more rigorous statistical approaches and more automated techniques. In this work, established methods from computer vision and machine learning are considered to build stronger evidence of those previous findings. To that end, an image descriptor is designed to characterize PNNs images; unsupervised learning (clustering) is used to automatically find distinctive patterns of PNNs; and supervised learning (classification) is adopted for predicting the experiment group of the mice from their PNN images. Experts in neurobiology, who were not aware of the underlying computational procedures, were asked to describe the patterns emerging from the automatically found clusters, and their descriptions were found to align surprisingly well with the two types of PNN images revealed from previous studies, namely strong and weak PNNs. Furthermore, when the set of PNN images corresponding to every mice in the saline (control) group and the conditioned (experimental) group were characterized using a bag-of-words representation, and subject to supervised learning (saline vs conditioned mice), the high classification results suggest the ability of the proposed representation and procedures in recognizing these groups. Therefore, despite the limited size of the dataset (1,032 PNN images of 6 saline and 6 conditioned mice), the results support existing evidence on the drug-related brain plasticity, while providing higher objectivity.

Low-cost single-pixel 3D imaging by using an LED array.

We propose a method to perform color imaging with a single photodiode by using light structured illumination generated with a low-cost color LED array. The LED array is used to generate a sequence of color Hadamard patterns which are projected onto the object by a simple optical system while the photodiode records the light intensity. A field programmable gate array (FPGA) controls the LED panel allowing us to obtain high refresh rates up to 10 kHz. The system is extended to 3D imaging by simply adding a low number of photodiodes at different locations. The 3D shape of the object is obtained by using a non-calibrated photometric stereo technique. Experimental results are provided for an LED array with 32 × 32 elements.

Integral imaging techniques for flexible sensing through image-based reprojection.

In this work, a 3D reconstruction approach for flexible sensing inspired by integral imaging techniques is proposed. This method allows the application of different integral imaging techniques, such as generating a depth map or the reconstruction of images on a certain 3D plane of the scene that were taken with a set of cameras located at unknown and arbitrary positions and orientations. By means of a photo-consistency measure proposed in this work, all-in-focus images can also be generated by projecting the points of the 3D plane into the sensor planes of the cameras and thereby capturing the associated RGB values. The proposed method obtains consistent results in real scenes with different surfaces of objects as well as changes in texture and lighting.

Human gesture recognition using three-dimensional integral imaging.

Three-dimensional (3D) integral imaging allows one to reconstruct a 3D scene, including range information, and provides sectional refocused imaging of 3D objects at different ranges. This paper explores the potential use of 3D passive sensing integral imaging for human gesture recognition tasks from sequences of reconstructed 3D video scenes. As a preliminary testbed, the 3D integral imaging sensing is implemented using an array of cameras with the appropriate algorithms for 3D scene reconstruction. Recognition experiments are performed by acquiring 3D video scenes of multiple hand gestures performed by ten people. We analyze the capability and performance of gesture recognition using 3D integral imaging representations at given distances and compare its performance with the use of standard two-dimensional (2D) single-camera videos. To the best of our knowledge, this is the first report on using 3D integral imaging for human gesture recognition.

Band selection in spectral imaging for non-invasive melanoma diagnosis.

A method consisting of the combination of the Synthetic Minority Over-Sampling TEchnique (SMOTE) and the Sequential Forward Floating Selection (SFFS) technique is used to do band selection in a highly imbalanced, small size, two-class multispectral dataset of melanoma and non-melanoma lesions. The aim is to improve classification rate and help to identify those spectral bands that have a more important role in melanoma detection. All the processing steps were designed taking into account the low number of samples in the dataset, situation that is quite common in medical cases. The training/test sets are built using a Leave-One-Out strategy. SMOTE is applied in order to deal with the imbalance problem, together with the Qualified Majority Voting scheme (QMV). Support Vector Machines (SVM) is the classification method applied over each balanced set. Results indicate that all melanoma lesions are correctly classified, using a low number of bands, reaching 100% sensitivity and 72% specificity when considering nine (out of a total of 55) spectral bands.

Multispectral integral imaging acquisition and processing using a monochrome camera and a liquid crystal tunable filter.

This paper presents an acquisition system and a procedure to capture 3D scenes in different spectral bands. The acquisition system is formed by a monochrome camera, and a Liquid Crystal Tunable Filter (LCTF) that allows to acquire images at different spectral bands in the [480, 680]nm wavelength interval. The Synthetic Aperture Integral Imaging acquisition technique is used to obtain the elemental images for each wavelength. These elemental images are used to computationally obtain the reconstruction planes of the 3D scene at different depth planes. The 3D profile of the acquired scene is also obtained using a minimization of the variance of the contribution of the elemental images at each image pixel. Experimental results show the viability to recover the 3D multispectral information of the scene. Integration of 3D and multispectral information could have important benefits in different areas, including skin cancer detection, remote sensing and pattern recognition, among others.