The ability for vision systems to accurately recognize humans based on movement as well as still images has become an increasing area of high interest and research in many aspects of technology and industry, including security.
Computer Vision broadly refers to the discipline where extraction of useful 2D and/or 3D information from one or more images is of interest. Since the human visual system works by extracting information from the images formed on the retina of the eye, developments in computer vision are inevitably compared to the abilities of the human vision system. One of the basic tasks of the human visual system is to recognize humans and objects and spatial relationships among them. Similarly, one of the main goals of computer vision researchers is to develop methods for localization and recognition of objects in a scene. A special case of this general problem is the recognition of humans and their activities. In this lecture, the authors outline some of the methods that have been recently developed towards achieving this goal, and describe present research in this area. The recognition problem in two parts - human identification using face and gait, and human activity recognition.