Behavior detection method, system and device and machine readable medium

Abstract

The invention provides a behavior detection method, system and device and a machine readable medium. The behavior detection method comprises the steps: obtaining one or more proposal containing targetbehaviors; classifying the proposal containing the target behavior according to one or more classifiers to obtain at least two classification results; and combining the at least two classification results to obtain a target behavior detection result. According to the behavior detection method, a continuous frame image can perceive all information contained in the video, and scores are generated according to the continuous frame image, and the scores are sorted, and generation candidate time domains and regions with high score values are selected, so that missing detection and false detectioncannot be caused. And meanwhile, boundary adjustment is performed on the proposal, so that the starting time of the target behavior can be accurately positioned, and the behavior detection method is suitable for diversified human behaviors and human behaviors of different time scales.

Description

technical field [0001] The present invention relates to the technical field of data processing, in particular to a behavior detection method, system, device and machine-readable medium for behavior detection. Background technique [0002] With the rapid development of the Internet industry and the popularity of high-definition cameras, millions of videos are produced every day. Whether it is video content auditing or public security monitoring, automated video processing techniques are required to analyze the content of these videos and detect human behavior. At present, most human behaviors are detected by using the perception ability of artificial intelligence technology to detect human behaviors by perceiving video content information. Existing human behavior detection workflows can be divided into two categories: (1) detection based on sliding windows; (2) detection based on behavior scores. [0003] However, sliding window detection is likely to cause two important pr...

AI Technical Summary

Problems solved by technology

[0003] However, sliding window detection is likely to cause two important problems and defects: 1) the boundary of behavior detection is not accurate, that is, the start and end time of behavior cannot be accurately located; 2) it cannot adapt to diverse human behaviors, that is, it cannot be applied to different time scales at the same time human behavior

And the behavior score detection is extremely dependent on the scoring mechanism, resulting in two problems: 1) The current scoring mechanism only focuses on the current content and cannot perceive the global context information, resulting in poor scoring quality; 2) Based on poor quality behaviors Score generation of candidate temporal region proposals is likely to cause problems such as missed detection and false detection

Images