General methods and development actuality of gait recognition

As a new technology of biometrics, gait recognition has recently gained more and more interests from researchers. Gait recognition aimed essentially to recognize person by automatically extracting movement characteristic of walking person in the video. Firstly, this paper introduces gait characteristics and its research background. Secondly, general process of gait recognition method is briefly described and current methods for gait recognition are surveyed. Methods existing in literatures are classified as statistical-based method, model-based method and multi model information fusion based methods. Characteristic extracting algorithms of every category are introduced in detail, and its advantages and shortcomings are pointed out concretely. At last, we indicate problems that have yet been not solved perfectly and future developing tendency in research field of gait.