Behavior detection method and system, machine readable medium and equipment

Abstract

The invention provides a behavior detection method and system, a machine readable medium and equipment. The behavior detection method comprises the following steps: acquiring a to-be-detected continuous frame image containing a target behavior; representing the continuous frame images to be detected by using a neural network, so that each frame image can sense the target behavior characteristic information of the current frame image and the target behavior characteristic information of other frame images; classifying the represented continuous frame images to be detected according to a classifier 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, eachframe of image can perceive all information contained in the video, and the scores are generated according to the image, and the scores are sorted, and the generation candidate time domain and regionwith high score values are selected, and missing detection and false detection are not caused. Meanwhile, boundary adjustment is performed on the classification result so that the starting time of thetarget 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, machine-readable medium and equipment 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...

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