Action Recognition in Physical Rehabilitation - A review

Abstract

Recognizing actions from film clips or images is a difficult procedure due to difficulties such as crowded backgrounds, occlusions, differences in scale, viewpoint, colour, and look.Various technologies, such as surveillance cameras, human - machine interface, and robotics for human activity description, requires a simultaneous action recognition system. A standard colour camera can identify a moving silhouette in the foreground, but precise assessment of human movements is difficult due to lack of complete three dimensional knowledge of the scene(1). Cameras like RGB-D can combine a depth map based on a colour image and the reflection of an infra red sensor light; they can help in solving the problem. The main aim in rehabilitation is correctness of a movement may be certified without being exceedingly accurate. The precise of skeleton estimation wasalso tested in order to better comprehend the potential clinical applications. The motion detection is a promising area for advancement in fields such as physiotherapy(2).