Gait recognition system and method based on visual and tactile fusion

Abstract

The invention discloses a gait recognition system and method based on visual and tactile fusion. The system comprises a Kinect skeleton tracking system, a plantar pressure test system, an upper computer data processing system, a photoelectric detection switch and an identity card recognition device; the Kinect skeleton tracking system, the plantar pressure test system, the photoelectric detectionswitch and the identity card recognition device are connected with the upper computer data processing system separately; the upper computer data processing system comprises a filter, a detection dataregister, a visual and tactile data fusion processor, a gait characteristic register, an input register, a matching register and an individual gait characteristic database. According to the method, the Kinect skeleton tracking system is adopted to collect visual data and the plantar pressure test system is adopted to collect plantar pressure tactile data, so that the visual sense and the plantar pressure tactile sense are combined, and the cardinal number of characteristic elements is increased; the instability of the visual data is reduced or even eliminated by utilizing the certainty of thetactile data, and therefore the gaits of the human body are quickly and accurately recognized.

Description

technical field [0001] The invention relates to human body identification technology, in particular to a visual-tactile fusion gait recognition system and a recognition method. Background technique [0002] Gait recognition is an emerging biometric technology that aims to identify people through their walking posture. Compared with other biometric technologies, gait recognition has the advantages of non-contact, long-distance and difficult to camouflage. In the field of intelligent video surveillance, it has more advantages than face recognition. [0003] Research by Professor Mark Nixon of the Department of Electronics and Computer Science at the University of Southampton in the United Kingdom has shown that everyone has a completely different walking posture, because people have different levels of muscle strength, tendon and bone length, bone density, visual sensitivity, coordination, and experience. Subtle differences in body weight, center of gravity, degree of muscle...

AI Technical Summary

Problems solved by technology

Video data is greatly influenced by the outside world. Clothes, background, carrying conditions, and walking speed will all affect the accuracy of video data, but video data can extract rich features; plantar pressure analysis will also be affected by whether you wear shoes or not. Moreover, there are relatively few feature quantities that can be extracted, but the spatial position and acquired data of plantar pressure analysis are accurate.

Images