A software package for personal identification by step cycle characteristics

Recently, methods of identifying an individual by gait signs have gained particular interest due to active using of video surveillance systems. A significant advantage of this method is the fact that conducting examinations can be contactless and convenient from the point of view of collecting material. Nowadays, various methods of identifying an individual by gait characteristics are being actively developed. However, due to the large number of conditions affecting the movement manner, the task of identifying a person by gait still does not have a sufficiently accurate solution, so the problem of developing new methods is relevant. The article describes the method of identifying an individual in video shooting frames by such a kinematic indicator as a step cycle. The essence of the method consists in digitizing and quantifying the following step cycle parameters: the duration of double support and transfer periods, the step frequency and the pace of walking. The analysis of the listed indicators will make it possible to draw an expert conclusion about the similarity or difference of two individuals in the videos. To implement the proposed method, the authors have developed a software package for calculating step cycle characteristics. The software package includes the following modules: a module for entering primary information, a module for calculating the main step cycle characteristics, a module for generating a report. The main advantage of this technique and the software package is the ability to process video information from various angles, as well as in the case of fixing an object at a remote distance. The software package can be used in the development of a computer system for hybrid identity identification that includes modules for reading and analyzing biometric information, gait analysis modules for various shooting features.