Behavior recognition method and system based on attention mechanism double-flow network

Abstract

The invention provides a behavior recognition method and system based on an attention mechanism double-flow network, and belongs to the technical field of behavior recognition, and the method comprises the steps: dividing an obtained whole video segment into a plurality of video segments with the same length, extracting an RGB image and an optical flow gray-scale image of each frame of each videosegment, and carrying out the preprocessing of the RGB images and the optical flow gray-scale images; carrying out random sampling on the preprocessed image to obtain an RGB image and an optical flowgrayscale image of each video clip; extracting appearance features and time dynamic features of the sampled images by using a double-flow network model introducing an attention mechanism, fusing the appearance features and the time dynamic features according to the types of a time domain network and a space domain network respectively, and performing weighted fusion on a fusion result of the timedomain network and a fusion result of the space domain network to obtain an identification result of the whole video. According to the invention, the video data can be fully utilized, the local key features of the video frame image can be better extracted, the foreground area where the action occurs is highlighted, the influence of irrelevant information in the background environment is inhibited,and the behavior recognition accuracy is improved.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine

Login to View More

AI Technical Summary

Benefits of technology

This technology allows videos captured by cameras or sensors to be analyzed effectively without being affected by external factors such as lighting conditions or other environmental variables that may affect their performance. It achieves this through dividing them up evenly across different parts of space based on time and frequency channels. By doing these techniques, it can extract important visual characteristics from frames and create high-quality animation sequences. Overall, this innovation enhances how people recognize actions accurately due to its ability to analyze large amounts of real world content efficiently over long periods of time.

Problems solved by technology

This patented technical problem addressed in this patents relates to improving performance for analyzing visual content captured through cameras or similar devices like webcams (web). Dual-flow Networks have shown promise but they face challenges with capturing full range view imagery without distortion caused by objects obscured during camera angles. Additionally, there are issues associated with identifying relevant areas within the scene where no target can be detected while also considering how different types of noise contribute to the overall quality of the video signal being processed.

Images