Physically Consistent Whole-Body Kinematics Assessment Based on an RGB-D Sensor. Application to Simple Rehabilitation Exercises.

This work proposes to improve the accuracy of joint angle estimates obtained from an RGB-D sensor. It is based on a constrained extended Kalman Filter that tracks inputted measured joint centers. Since the proposed approach uses a biomechanical model, it allows physically consistent constrained joint angles and constant segment lengths to be obtained. A practical method that is not sensor-specific for the optimal tuning of the extended Kalman filter covariance matrices is provided. It uses reference data obtained from a stereophotogrammetric system but it has to be tuned only once since it is task-specific only. The improvement of the optimal tuning over classical methods in setting the covariance matrices is shown with a statistical parametric mapping analysis. The proposed approach was tested with six healthy subjects who performed four rehabilitation tasks. The accuracy of joint angle estimates was assessed with a reference stereophotogrammetric system. Even if some joint angles, such as the internal/external rotations, were not well estimated, the proposed optimized algorithm reached a satisfactory average root mean square difference of 9.7 ∘ and a correlation coefficient of 0.8 for all joints. Our results show that an affordable RGB-D sensor can be used for simple in-home rehabilitation when using a constrained biomechanical model.

A gait analysis method based on a depth camera for fall prevention.

This paper proposes a markerless system whose purpose is to help preventing falls of elderly people at home. To track human movements, the Microsoft Kinect camera is used which allows to acquire at the same time a RGB image and a depth image. Several articles show that the analysis of some gait parameters could allow fall risk assessment. We developed a system which extracts three gait parameters (the length and the duration of steps and the speed of the gait) by tracking the center of mass of the person. To check the validity of our system, the accuracy of the gait parameters obtained with the camera is evaluated. In an experiment, eleven subjects walked on an actimetric carpet, perpendicularly to the camera which filmed the scene. The three gait parameters obtained by the carpet are compared with those of the camera. In this study, four situations were tested to evaluate the robustness of our model. The subjects walked normally, making small steps, wearing a skirt and in front of the camera. The results showed that the system is accurate when there is one camera fixed perpendicularly. Thus we believe that the presented method is accurate enough to be used in real fall prevention applications.

Human activities recognition with RGB-Depth camera using HMM.

Fall detection remains today an open issue for improving elderly people security. It is all the more pertinent today when more and more elderly people stay longer and longer at home. In this paper, we propose a method to detect fall using a system made up of RGB-Depth cameras. The major benefit of our approach is its low cost and the fact that the system is easy to distribute and install. In few words, the method is based on the detection in real time of the center of mass of any mobile object or person accurately determining its position in the 3D space and its velocity. We demonstrate in this paper that this information is adequate and robust enough for labeling the activity of a person among 8 possible situations. An evaluation has been conducted within a real smart environment with 26 subjects which were performing any of the eight activities (sitting, walking, going up, squatting, lying on a couch, falling, bending and lying down). Seven out of these eight activities were correctly detected among which falling which was detected without false positives.

A support system for ECG segmentation based on Hidden Markov Models.

Pharmaceutic studies require to analyze thousands of ECGs in order to evaluate the side effects of a new drug. In this paper we present a new support system based on the use of probabilistic models for automatic ECG segmentation. We used a bayesian HMM clustering algorithm to partition the training base, and we improved the method by using a multi-channel segmentation. We present a statistical analysis of the results where we compare different automatic methods to the segmentation of the cardiologist as a gold standard.

Factored interval particle filtering for gait analysis.

Commercial gait analysis systems rely on wearable sensors. The goal of this study is to develop a low cost marker less human motion capture tool. Our method is based on the estimation of 3d movements using video streams and the projection of a 3d human body model. Dynamic parameters only depend on human body movement constraints. No trained gait model is used which makes this approach generic. The 3d model is characterized by the angular positions of its articulations. The kinematic chain structure allows to factor the state vector representing the configuration of the model. We use a dynamic bayesian network and a modified particle filtering algorithm to estimate the most likely state configuration given an observation sequence. The modified algorithm takes advantage of the factorization of the state vector for efficiently weighting and resampling the particles.

Dynamic optimization over infinite-time horizon: web-building strategy in an orb-weaving spider as a case study.

Dynamic state-dependent models have been widely developed since 1990s for solving questions in evolutionary ecology. Up to now, these models were mainly run over finite-time horizon. However, for many biological questions an infinite-time horizon perspective could be more appropriate, especially when the end of the modeled period is state- rather than time-dependent. Despite this approach is widely used in the field of economics and operational research, thus far no work has been providing biologists with a general method to solve infinite-time horizon problems. Here we present such a method, through the exhaustive description of an algorithm that we implement to determine the strategy an organism should follow to reach a particular state as fast as possible while limiting mortality risk. To illustrate that method we explored web-building behavior in an orb-weaving spider. How are adult females predicted to build their successive webs to gain energy, grow, and lay their first clutch as fast as possible, without suffering from either predation or starvation? From this example, we first show how an optimal strategy over infinite-time horizon can be processed and selected. Second, we analyse variations of the optimal web-building strategy along with the spider's body weight and predation risk during web building. Our model yields two main predictions: (1) spiders reduce their web size as they are gaining weight due to body-mass-dependent cost of web-building behavior, and (2) this reduction in web size starts at lower weight under higher predation risk.

Automated medical diagnosis with fuzzy stochastic models: monitoring chronic diseases.

As the world population ages, the patients per physician ratio keeps on increasing. This is even more important in the domain of chronic pathologies where people are usually monitored for years and need regular consultations. To address this problem, we propose an automated system to monitor a patient population, detecting anomalies in instantaneous data and in their temporal evolution, so that it could alert physicians. By handling the population of healthy patients autonomously and by drawing the physicians' attention to the patients-at-risk, the system allows physicians to spend comparatively more time with patients who need their services. In such a system, the interaction between the patients, the diagnosis module, and the physicians is very important. We have based this system on a combination of stochastic models, fuzzy filters, and strong medical semantics. We particularly focused on a particular tele-medicine application: the Diatelic Project. Its objective is to monitor chronic kidney-insufficient patients and to detect hydration troubles. During two years, physicians from the ALTIR have conducted a prospective randomized study of the system. This experiment clearly shows that the proposed system is really beneficial to the patients' health.