Gait energy volumes and frontal gait recognition using depth images

Gait energy images (GEIs) and its variants form the basis of many recent appearance-based gait recognition systems. The GEI combines good recognition performance with a simple implementation, though it suffers problems inherent to appearance-based approaches, such as being highly view dependent. In this paper, we extend the concept of the GEI to 3D, to create what we call the gait energy volume, or GEV. A basic GEV implementation is tested on the CMU MoBo database, showing improvements over both the GEI baseline and a fused multi-view GEI approach. We also demonstrate the efficacy of this approach on partial volume reconstructions created from frontal depth images, which can be more practically acquired, for example, in biometric portals implemented with stereo cameras, or other depth acquisition systems. Experiments on frontal depth images are evaluated on an in-house developed database captured using the Microsoft Kinect, and demonstrate the validity of the proposed approach.

High Quality Photometric Reconstruction using a Depth Camera

In this paper we present a depth-guided photometric 3D reconstruction method that works solely with a depth camera like the Kinect. Existing methods that fuse depth with normal estimates use an external RGB camera to obtain photometric information and treat the depth camera as a black box that provides a low quality depth estimate. Our contribution to such methods are two fold. Firstly, instead of using an extra RGB camera, we use the infra-red (IR) camera of the depth camera system itself to directly obtain high resolution photometric information. We believe that ours is the first method to use an IR depth camera system in this manner. Secondly, photometric methods applied to complex objects result in numerous holes in the reconstructed surface due to shadows and self-occlusions. To mitigate this problem, we develop a simple and effective multiview reconstruction approach that fuses depth and normal information from multiple viewpoints to build a complete, consistent and accurate 3D surface representation. We demonstrate the efficacy of our method to generate high quality 3D surface reconstructions for some complex 3D figurines.

Reconocimiento de posturas mediante Kinect en ROS

Proyecto de Fin de Grado, especialidad en Computación. Se ha desarrollado un software en ROS para detectar posturas y movimientos de personas. Para ello, se utiliza la información del esqueleto proporcionada por el sensor Kinect y la biblioteca OpenNI. Se ha realizado un enfoque basado en técnicas de aprendizaje supervisado para generar modelos que clasifiquen posturas estáticas. En el caso de los movimientos, el enfoque se ha basado en clustering. Estos modelos, una vez generados, se incluyen como parte del software, que reacciona ante las posturas y gestos que realice un usuario.

Feedback on the Rate and Depth of Chest Compressions during Cardiopulmonary Resuscitation Using Only Accelerometers

Background Quality of cardiopulmonary resuscitation (CPR) is key to increase survival from cardiac arrest. Providing chest compressions with adequate rate and depth is difficult even for well-trained rescuers. The use of real-time feedback devices is intended to contribute to enhance chest compression quality. These devices are typically based on the double integration of the acceleration to obtain the chest displacement during compressions. The integration process is inherently unstable and leads to important errors unless boundary conditions are applied for each compression cycle. Commercial solutions use additional reference signals to establish these conditions, requiring additional sensors. Our aim was to study the accuracy of three methods based solely on the acceleration signal to provide feedback on the compression rate and depth. Materials and Methods We simulated a CPR scenario with several volunteers grouped in couples providing chest compressions on a resuscitation manikin. Different target rates (80, 100, 120, and 140 compressions per minute) and a target depth of at least 50 mm were indicated. The manikin was equipped with a displacement sensor. The accelerometer was placed between the rescuer's hands and the manikin's chest. We designed three alternatives to direct integration based on different principles (linear filtering, analysis of velocity, and spectral analysis of acceleration). We evaluated their accuracy by comparing the estimated depth and rate with the values obtained from the reference displacement sensor. Results The median (IQR) percent error was 5.9% (2.8-10.3), 6.3% (2.9-11.3), and 2.5% (1.2-4.4) for depth and 1.7% (0.0-2.3), 0.0% (0.0-2.0), and 0.9% (0.4-1.6) for rate, respectively. Depth accuracy depended on the target rate (p < 0.001) and on the rescuer couple (p < 0.001) within each method. Conclusions Accurate feedback on chest compression depth and rate during CPR is possible using exclusively the chest acceleration signal. The algorithm based on spectral analysis showed the best performance. Despite these encouraging results, further research should be conducted to asses the performance of these algorithms with clinical data.

Single camera pose estimation using Bayesian filtering and Kinect motion priors

Traditional approaches to upper body pose estimation using monocular vision rely on complex body models and a large variety of geometric constraints. We argue that this is not ideal and somewhat inelegant as it results in large processing burdens, and instead attempt to incorporate these constraints through priors obtained directly from training data. A prior distribution covering the probability of a human pose occurring is used to incorporate likely human poses. This distribution is obtained offline, by fitting a Gaussian mixture model to a large dataset of recorded human body poses, tracked using a Kinect sensor. We combine this prior information with a random walk transition model to obtain an upper body model, suitable for use within a recursive Bayesian filtering framework. Our model can be viewed as a mixture of discrete Ornstein-Uhlenbeck processes, in that states behave as random walks, but drift towards a set of typically observed poses. This model is combined with measurements of the human head and hand positions, using recursive Bayesian estimation to incorporate temporal information. Measurements are obtained using face detection and a simple skin colour hand detector, trained using the detected face. The suggested model is designed with analytical tractability in mind and we show that the pose tracking can be Rao-Blackwellised using the mixture Kalman filter, allowing for computational efficiency while still incorporating bio-mechanical properties of the upper body. In addition, the use of the proposed upper body model allows reliable three-dimensional pose estimates to be obtained indirectly for a number of joints that are often difficult to detect using traditional object recognition strategies. Comparisons with Kinect sensor results and the state of the art in 2D pose estimation highlight the efficacy of the proposed approach.

A Kinect Based Indoor Navigation System for the Blind

Team NAVIGATE aims to create a robust, portable navigational aid for the blind. Our prototype uses depth data from the Microsoft Kinect to perform realtime obstacle avoidance in unfamiliar indoor environments. The device augments the white cane by performing two signi cant functions: detecting overhanging objects and identifying stairs. Based on interviews with blind individuals, we found a combined audio and haptic feedback system best for communicating environmental information. Our prototype uses vibration motors to indicate the presence of an obstacle and an auditory command to alert the user to stairs ahead. Through multiple trials with sighted and blind participants, the device was successful in detecting overhanging objects and approaching stairs. The device increased user competency and adaptability across all trials.

Modeling and worst-case dimensioning of cluster-tree wireless sensor networks

Time-sensitive Wireless Sensor Network (WSN) applications require finite delay bounds in critical situations. This paper provides a methodology for the modeling and the worst-case dimensioning of cluster-tree WSNs. We provide a fine model of the worst-case cluster-tree topology characterized by its depth, the maximum number of child routers and the maximum number of child nodes for each parent router. Using Network Calculus, we derive “plug-and-play” expressions for the endto- end delay bounds, buffering and bandwidth requirements as a function of the WSN cluster-tree characteristics and traffic specifications. The cluster-tree topology has been adopted by many cluster-based solutions for WSNs. We demonstrate how to apply our general results for dimensioning IEEE 802.15.4/Zigbee cluster-tree WSNs. We believe that this paper shows the fundamental performance limits of cluster-tree wireless sensor networks by the provision of a simple and effective methodology for the design of such WSNs.

Efeitos especiais mediados por Kinect em contexto de espetáculo de dança ao vivo

A dança e os espetáculos foram atividades desenvolvidas e praticadas pelo homem desde praticamente a sua existência. Ao longo de todo esse período de tempo e até aos dias atuais estas atividades foram sofrendo evoluções que as fizeram manterem-se relevantes e de grande importância na sociedade humana e na sua cultura. A evolução não se fez sentir apenas no estilo das danças e espetáculos mas também nos acessórios e efeitos que estas implementam de forma a torna-las mais atrativas para quem as vê. Apesar desta evolução, a maioria dos efeitos não permite um nível de interação com a dança ou espetáculo, fazendo com que exista uma clara separação entre a componente pura da dança e o cenário do espetáculo no que diz respeito á componente acessória de efeitos. Com o intuito de colmatar esta clara divisão de componentes, iniciamos um estudo no sentido de criar um sistema que permitisse derrubar essa barreira e juntar as duas componentes com o intuito de criar efeitos que interajam com a própria dança tornando o espetáculo mais interativo, e que não seja apenas mais um componente acessório, isto ao mesmo tempo torna todo o espetáculo mais apelativo para o público em geral. Para conseguir criar tal sistema, recorremos às tecnologias de sensores de movimento atuais para que a ponte de ligação entre o artista e os efeitos fosse conseguida. No mercado existem diversas ofertas de sensores de movimentos que serviriam para criar o sistema, mas apenas um poderia ser escolhido, então para tal numa primeira parte foi feito um estudo para determinar qual destes sensores seria o mais adequado para ser utilizado no sistema, tendo em conta uma diversidade de fatores. Após a escolha do sensor foi então desenvolvido o sistema MoveU e tendo no final sido feitos uma série de testes que permitiram validar o protótipo e verificar se os objetivos propostos foram atingidos. Por fim, o MoveU foi demonstrado a uma série de pessoas (dançarinos e espectadores), para que pudessem opinar sobre ele e indicar possíveis melhoramentos. Foram também criados uma série de questionários para que o público a quem foi demonstrado o protótipo, com a finalidade de realizar uma análise estatística para determinar se este sistema seria do agrado das pessoas e também permitir retirar conclusões sobre este trabalho.

Détection de chute à l'aide d'une caméra de profondeur

Les chutes chez les personnes âgées représentent un problème important de santé publique. Des études montrent qu’environ 30 % des personnes âgées de 65 ans et plus chutent chaque année au Canada, entraînant des conséquences néfastes sur les plans individuel, familiale et sociale. Face à une telle situation la vidéosurveillance est une solution efficace assurant la sécurité de ces personnes. À ce jour de nombreux systèmes d’assistance de services à la personne existent. Ces dispositifs permettent à la personne âgée de vivre chez elle tout en assurant sa sécurité par le port d'un capteur. Cependant le port du capteur en permanence par le sujet est peu confortable et contraignant. C'est pourquoi la recherche s’est récemment intéressée à l’utilisation de caméras au lieu de capteurs portables. Le but de ce projet est de démontrer que l'utilisation d'un dispositif de vidéosurveillance peut contribuer à la réduction de ce fléau. Dans ce document nous présentons une approche de détection automatique de chute, basée sur une méthode de suivi 3D du sujet en utilisant une caméra de profondeur (Kinect de Microsoft) positionnée à la verticale du sol. Ce suivi est réalisé en utilisant la silhouette extraite en temps réel avec une approche robuste d’extraction de fond 3D basée sur la variation de profondeur des pixels dans la scène. Cette méthode se fondera sur une initialisation par une capture de la scène sans aucun sujet. Une fois la silhouette extraite, les 10% de la silhouette correspondant à la zone la plus haute de la silhouette (la plus proche de l'objectif de la Kinect) sera analysée en temps réel selon la vitesse et la position de son centre de gravité. Ces critères permettront donc après analyse de détecter la chute, puis d'émettre un signal (courrier ou texto) vers l'individu ou à l’autorité en charge de la personne âgée. Cette méthode a été validée à l’aide de plusieurs vidéos de chutes simulées par un cascadeur. La position de la caméra et son information de profondeur réduisent de façon considérable les risques de fausses alarmes de chute. Positionnée verticalement au sol, la caméra permet donc d'analyser la scène et surtout de procéder au suivi de la silhouette sans occultation majeure, qui conduisent dans certains cas à des fausses alertes. En outre les différents critères de détection de chute, sont des caractéristiques fiables pour différencier la chute d'une personne, d'un accroupissement ou d'une position assise. Néanmoins l'angle de vue de la caméra demeure un problème car il n'est pas assez grand pour couvrir une surface conséquente. Une solution à ce dilemme serait de fixer une lentille sur l'objectif de la Kinect permettant l’élargissement de la zone surveillée.

Analyse quantifiée de l'asymétrie de la marche par application de Poincaré

La marche occupe un rôle important dans la vie quotidienne. Ce processus apparaît comme facile et naturel pour des gens en bonne santé. Cependant, différentes sortes de maladies (troubles neurologiques, musculaires, orthopédiques...) peuvent perturber le cycle de la marche à tel point que marcher devient fastidieux voire même impossible. Ce projet utilise l'application de Poincaré pour évaluer l'asymétrie de la marche d'un patient à partir d'une carte de profondeur acquise avec un senseur Kinect. Pour valider l'approche, 17 sujets sains ont marché sur un tapis roulant dans des conditions différentes : marche normale et semelle de 5 cm d'épaisseur placée sous l'un des pieds. Les descripteurs de Poincaré sont appliqués de façon à évaluer la variabilité entre un pas et le cycle complet de la marche. Les résultats montrent que la variabilité ainsi obtenue permet de discriminer significativement une marche normale d'une marche avec semelle. Cette méthode, à la fois simple à mettre en oeuvre et suffisamment précise pour détecter une asymétrie de la marche, semble prometteuse pour aider dans le diagnostic clinique.

Evaluation of the Power Consumption of Routing Protocols for Wireless Sensor Networks

Sensor networks are one of the fastest growing areas in broad of a packet is in transit at any one time. In GBR, each node in the network can look at itsneighbors wireless ad hoc networking (? Eld. A sensor node, typically'hop count (depth) and use this to decide which node to forward contains signal-processing circuits, micro-controllers and a the packet on to. If the nodes' power level drops below a wireless transmitter/receiver antenna. Energy saving is one certain level it will increase the depth to discourage trafiE of the critical issue for sensor networks since most sensors are equipped with non-rechargeable batteries that have limitedlifetime. Routing schemes are used to transfer data collectedby sensor nodes to base stations. In the literature many routing protocols for wireless sensor networks are suggested. In this work, four routing protocols for wireless sensor networks viz Flooding, Gossiping, GBR and LEACH have been simulated using TinyOS and their power consumption is studied using PowerTOSSIM. A realization of these protocols has beencarried out using Mica2 Motes.

Evaluation of the Power Consumption of Routing Protocols for Wireless Sensor Networks

Sensor networks are one of the fastest growing areas in broad of a packet is in transit at any one time. In GBR, each node in the network can look at itsneighbors wireless ad hoc networking (? Eld. A sensor node, typically'hop count (depth) and use this to decide which node to forward contains signal-processing circuits, micro-controllers and a the packet on to. If the nodes' power level drops below a wireless transmitter/receiver antenna. Energy saving is one certain level it will increase the depth to discourage trafiE of the critical issue forfor sensor networks since most sensors are equipped with non-rechargeable batteries that have limited lifetime.

Patent DE10 2004 037 519 B4 “Sensor Process and Device for Determining a Physical Value“. A Proof of Concept

At present, a fraction of 0.1 - 0.2% of the patients undergoing surgery become aware during the process. The situation is referred to as anesthesia awareness and is obviously very traumatic for the person experiencing it. The reason for its occurrence is mostly an insufficient dosage of the narcotic Propofol combined with the incapability of the technology monitoring the depth of the patient’s anesthetic state to notice the patient becoming aware. A solution can be a highly sensitive and selective real time monitoring device for Propofol based on optical absorption spectroscopy. Its working principle has been postulated by Prof. Dr. habil. H. Hillmer and formulated in DE10 2004 037 519 B4, filed on Aug 30th, 2004. It consists of the exploitation of Intra Cavity Absorption effects in a two mode laser system. In this Dissertation, a two mode external cavity semiconductor laser, which has been developed previously to this work is enhanced and optimized to a functional sensor. Enhancements include the implementation of variable couplers into the system and the implementation of a collimator arrangement into which samples can be introduced. A sample holder and cells are developed and characterized with a focus on compatibility with the measurement approach. Further optimization concerns the overall performance of the system: scattering sources are reduced by re-splicing all fiber-to-fiber connections, parasitic cavities are eliminated by suppressing the Fresnel reflexes of all one fiber ends by means of optical isolators and wavelength stability of the system is improved by the implementation of thermal insulation to the Fiber Bragg Gratings (FBG). The final laser sensor is characterized in detail thermally and optically. Two separate modes are obtained at 1542.0 and 1542.5 nm, tunable in a range of 1nm each. Mode Full Width at Half Maximum (FWHM) is 0.06nm and Signal to Noise Ratio (SNR) is as high as 55 dB. Independent of tuning the two modes of the system can always be equalized in intensity, which is important as the delicacy of the intensity equilibrium is one of the main sensitivity enhancing effects formulated in DE10 2004 037 519 B4. For the proof of concept (POC) measurements the target substance Propofol is diluted in the solvents Acetone and DiChloroMethane (DCM), which have been investigated for compatibility with Propofol beforehand. Eight measurement series (two solvents, two cell lengths and two different mode spacings) are taken, which draw a uniform picture: mode intensity ratio responds linearly to an increase of Propofol in all cases. The slope of the linear response indicates the sensitivity of the system. The eight series are split up into two groups: measurements taken in long cells and measurements taken in short cells.

Omnidirectional Depth Computation from a Single Image

Omnidirectional cameras offer a much wider field of view than the perspective ones and alleviate the problems due to occlusions. However, both types of cameras suffer from the lack of depth perception. A practical method for obtaining depth in computer vision is to project a known structured light pattern on the scene avoiding the problems and costs involved by stereo vision. This paper is focused on the idea of combining omnidirectional vision and structured light with the aim to provide 3D information about the scene. The resulting sensor is formed by a single catadioptric camera and an omnidirectional light projector. It is also discussed how this sensor can be used in robot navigation applications

Accuracy estimation of a new omnidirectional 3D vision sensor

We present a computer vision system that associates omnidirectional vision with structured light with the aim of obtaining depth information for a 360 degrees field of view. The approach proposed in this article combines an omnidirectional camera with a panoramic laser projector. The article shows how the sensor is modelled and its accuracy is proved by means of experimental results. The proposed sensor provides useful information for robot navigation applications, pipe inspection, 3D scene modelling etc