Human body behavior identification method based on thematic knowledge transfer

Abstract

The invention discloses a human body behavior identification method based on thematic knowledge transfer. The method comprises the steps that a bilingual dictionary at a training visual angle and a test visual angle is built, wherein the bilingual dictionary is used for transforming low-layer features of the same action at the two visual angles to the same representation; three steps of low-layer feature extraction, middle-layer feature extraction and bilingual dictionary obtaining are included; all action videos at the training angle are adopted, lower-layer features of different actions at the training angle are transformed to representations respectively through the bilingual dictionary, and classified models recognizing the different actions are trained; test action videos at the test visual angle are adopted, lower-layer features of actions at the test angle are transformed to representations through the bilingual dictionary, and reorganization results of the actions are obtained through the classified models. The human body behavior identification method based on thematic knowledge transfer significantly improves the recognition rate of human body behaviors at the crossed visual angles, has high robustness for change of the visual angles, and has significant value in video monitoring.

Description

technical field

[0001] The invention belongs to the field of image processing technology and pattern recognition, in particular to a perspective-independent human behavior recognition method based on subject knowledge transfer. Background technique

[0002] Human behavior recognition is a frontier direction that has attracted much attention in the field of computer vision, and the problem of perspective is the bottleneck of its research and application. Research on view-independent human behavior recognition can not only increase the intelligence of video surveillance, but also reduce the cost of multi-view surveillance, which has broad application prospects and economic value. Although the research on human behavior recognition has achieved certain results, most of the work is based on fixed and known perspectives, and the actual captured data is often at any angle due to human movement, camera movement and other reasons. Different shooting angles will not only bring great...

Images