With the increase in the number of stroke survivors, there is an urgent need for designing appropriate home-based rehabilitation tools to reduce health-care costs. The objective is to empower the rehabilitation of post-stroke patients at the comfort of their homes by supporting them while exercising without the physical presence of the therapist. A novel low-cost home-based training system is introduced. This system is designed as a composition of two linked applications: one for the therapist and another one for the patient. The therapist prescribes personalized exercises remotely, monitors the home-based training and re-adapts the exercises if required. On the other side, the patient loads the prescribed exercises, trains the prescribed exercise while being guided by color-based visual feedback and gets updates about the exercise performance. To achieve that, our system provides three main functionalities, namely: 1) Feedback proposals guiding a personalized exercise session, 2) Posture monitoring optimizing the effectiveness of the session, 3) Assessment of the quality of the motion. The proposed system is evaluated on 10 healthy participants without any previous contact with the system. To analyze the impact of the feedback proposals, we carried out two different experimental sessions: without and with feedback proposals. The obtained results give preliminary assessments about the interest of using such feedback. Obtained results on 10 healthy participants are promising. This encourages to test the system in a realistic clinical context for the rehabilitation of stroke survivors.

Human Action recognition (HAR) is largely used in the field of Ambient Assisted Living (AAL) to create an interaction between humans and computers. In these applications, it cannot be asked to people to act non-naturally. The algorithm has to adapt and the interaction has to be as quick as possible to make this interaction fluent. To improve the existing algorithms with regards to that points, we propose a novel method based on skeleton information provided by RGB-D cameras. This approach is able to carry out early action recognition and is more robust to viewpoint variability. To reach this goal, a new descriptor called Body Directional Velocity is proposed and a real-time classification is performed. Experimental results on four benchmarks show that our method competes with various skeleton-based HAR algorithms. We also show the suitability of our method for early recognition of human actions.

Over the last few decades, action recognition applications have attracted the growing interest of researchers, especially with the advent of RGB-D cameras. These applications increasingly require fast processing. Therefore, it becomes important to include the computational latency in the evaluation criteria. In this paper, we propose a novel human action descriptor based on skeleton data provided by RGB-D cameras for fast action recognition. The descriptor is built by interpolating the kinematics of skeleton joints (position, velocity and acceleration) using a cubic spline algorithm. A skeleton normalization is done to alleviate anthropometric variability. To ensure rate invariance which is one of the most challenging issue in action recognition, a novel temporal normalization algorithm called Time Variable Replacement (TVR) is proposed. It is a change of variable of time by a variable that we call Normalized Action Time (NAT) varying in a fixed range and making the descriptors less sensitive to execution rate variability. To map time with NAT, increasing functions (called Time Variable Replacement Function (TVRF)) are used. Two different Time Variable Replacement Functions (TVRF) are proposed in this paper: the Normalized Accumulated kinetic Energy (NAE) of the skeleton and the Normalized Pose Motion Signal Energy (NPMSE) of the skeleton. The action recognition is carried out using a linear Support Vector Machine (SVM). Experimental results on five challenging benchmarks show the effectiveness of our approach in terms of recognition accuracy and computational latency.

The Dense Trajectories concept is one of the most successful approaches in action recognition, suitable for scenarios involving a significant amount of motion. However, due to noise and background motion, many generated trajectories are irrelevant to the actual human activity and can potentially lead to performance degradation. In this paper, we propose Localized Trajectories as an improved version of Dense Trajectories where motion trajectories are clustered around human body joints provided by RGB-D cameras and then encoded by local Bag-of-Words. As a result, the Localized Trajectories concept provides an advanced discriminative representation of actions. Moreover, we generalize Localized Trajectories to 3D by using the depth modality. One of the main advantages of 3D Localized Trajectories is that they describe radial displacements that are perpendicular to the image plane. Extensive experiments and analysis were carried out on five different datasets.

This paper presents a novel descriptor based on skeleton information provided by RGB-D videos for human action recognition. These features are obtained, considering the motion as continuous trajectories of skeleton joints. With the discrete information of skeleton joints position, a cubic-spline interpolation is applied to joints position, velocity and acceleration components. The training and classification steps are done using a linear SVM. In the literature, many human motion descriptors based on RGB-D cameras had already been proposed with good accuracy, but with a high computational time. The main interest of this proposed approach is its ability to calculate human motion descriptors with a low computation cost while such a descriptor leads to an acceptable accuracy of recognition. Thus, this approach can be adapted to human computer interaction applications. For the purpose of validation, we apply our method to the challenging benchmark MSR-Action3D and introduce a new indicator which is the ratio between accuracy and execution time per descriptor. Using this criterion, we show that our algorithm outperforms the state-of-art methods in terms of the combined information of rapidity and accuracy.