Gesture and posture recognition using a depth camera with applications in employment interview behavior analysis

With the recent success of depth cameras such as Kinect, gesture and posture recognition in indoor environments has become easier. From the depth image, the 3D locations of body-joints can be reliably extracted and using a statistical pattern recognition framework, specific gestures or posture can be modelled and inferred. In this preliminary work, we show the application of this work for behavior analysis in job-interview and meeting scenarios, and also for Yoga posture recognition. From a training view-point, both applications are extremely interesting and relevant.