Active detection and recognition system and method for human gait behavior based on semantic folding

Abstract

The invention discloses an active detection and recognition system and method for a human gait behavior based on semantic folding. Embedded gait behavior detection and recognition system hardware with low power consumption is built by using a three-dimensional sound field positioning system, a sole force field positioning system, an HDMI high-definition camera, a high-definition video acquisition system, a microcomputer Raspberry and the like. Gait semantic energy diagrams with timing characteristics provided by the invention contain gait time information under different situations, and the learning and prediction ability of a gait behavior cognition system can be enhanced according to a lot of gait semantic energy diagrams with timing characteristics. Meanwhile, the active detection and recognition technology for a human gait behavior based on semantic folding has extensive application prospects in various fields which mainly comprises the fields such as long-distance identity recognition, abnormal gait behavior detection, pedestrian behavior prediction and mass video retrieval, and has excellent economical and social benefits.

Description

technical field [0001] The invention relates to a system and method for active detection and recognition of human gait behavior based on semantic folding. Background technique [0002] Gait behavior detection and recognition is the detection, analysis, understanding and prediction of human behavior based on the main features of human gait, action posture and shape. [0003] Gait behavior detection and recognition technology has shown broad application prospects in various fields of life, such as (1) long-distance identification: the identification and authentication of personnel identity can be completed without contact at a long distance; (2) abnormal gait behavior detection : Mainly screen and analyze abnormal behaviors, warn dangerous behaviors, and improve the level of security in public places; (3) Pedestrian behavior prediction: Real-time prediction of pedestrian behavior, providing decision-making basis for unmanned driving and other systems; 4) Massive video retriev...

AI Technical Summary

Problems solved by technology

[0006] The use of wearable sports equipment to detect and identify human gait behavior has many shortcomings: it is not suitable for wide-scale use, especially criminals will not wear it; due to the size and comfort of wearable equipment, people are unwilling to wear it; only Human body motion data can be obtained, but visual information such as human body images cannot be obtained, thus lacking effective visual analysis methods

Its disadvantage is that it cannot handle the influence of various covariant factors (occlusion, clothing, viewing angle, etc.) well, and the detection and recognition effects are poor in complex scenes.

Model-based methods will perform better when dealing with perspective and covariate factors, but the human models used in current research (stick models, hinge models, ellipse models, joint skeleton models and surface shell models) either lack physical features, Either the accuracy is poor, and the dimension of video and image as a kind of unstructured data is too high, which greatly affects the effect of gait behavior detection and recognition

[0009] In short, although the research on gait and behavior recognition has achieved many results, the walking and movement posture of the human body are affected by various factors, such as data loss caused by deliberately avoiding camera shooting, complex scene changes increase the difficulty of human body segmentation, and clothing conditions The superposition of subjective and objective factors such as change, occlusion interference, and different viewing angles makes the versatility and recognition rate of the gait behavior recognition algorithm still not high, far from being comparable to the human brain

Images