Microsoft Kinect, a low-cost motion sensing device, enables users to interact with computers or game consoles naturally through gestures and spoken commands without any other peripheral equipment. As such, it has commanded intense interests in research and development on the Kinect technology. In this paper, we present, a comprehensive survey on Kinect applications, and the latest research and development on motion recognition using data captured by the Kinect sensor. On the applications front, we review the applications of the Kinect technology in a variety of areas, including healthcare, education and performing arts, robotics, sign language recognition, retail services, workplace safety training, as well as 3D reconstructions. On the technology front, we provide an overview of the main features of both versions of the Kinect sensor together with the depth sensing technologies used, and review literatures on human motion recognition techniques used in Kinect applications. We provide a classi¯cation of motion recognition techniques to highlight the di®erent approaches used in human motion recognition. Furthermore, we compile a list of publicly available Kinect datasets. These datasets are valuable resources for researchers to investigate better methods for human motion recognition and lowerlevel computer vision tasks such as segmentation, object detection and human pose estimation.

No abstract

No abstract

No abstract

This article describes a novel approach to realtime motion assessment for rehabilitation exercises based on the integration of comprehensive kinematic modeling with fuzzy inference. To facilitate the assessment of all important aspects of a rehabilitation exercise, a kinematic model is developed to capture the essential requirements for static poses, dynamic movements, as well as the invariance that must be observed during an exercise. The kinematic model is expressed in terms of a set of kinematic rules. During the actual execution of a rehabilitation exercise, the similarity between the measured motion data and the model is computed in terms of their distances, which are then used as inputs to a fuzzy interference system to derive the overall quality of the execution. The integrated approach provides both a detailed categorical assessment of the overall execution of the exercise and the degree of adherence to individual kinematic rules.