A temporal sequence action recognition method based on deep learning

Abstract

The invention discloses a time series action recognition method based on deep learning, including video feature extraction and time boundary regression model construction. Aiming at the problem of insufficient validity of long motion feature expression in the boundary detection process, the inter-frame information and intra-frame information are simultaneously extracted through a dual-stream network to obtain the feature sequence of the video unit, and a multi-scale short motion segment interception scheme combined with context information is proposed. Effectively improve the subsequent regression accuracy, use the feature sequence to train the time boundary model, reduce the model training time, and improve the calculation efficiency. Aiming at the inaccurate problem of long motion boundary regression, the present invention proposes an improved temporal boundary regression model, including an improved multi-task multi-layer perceptron and a brand-new splicing mechanism for long motions, on the basis of ensuring the accuracy of motion categories , effectively improve the accuracy of long action time boundary regression, increase the overlap between the predicted action segment and the actual action segment, and realize the improvement of the sequence action recognition rate.

Description

technical field [0001] The invention belongs to the field of computer vision and pattern recognition, and relates to a time sequence action recognition method based on deep learning. Background technique [0002] With the rapid development of smart phones and the Internet, video data has begun to show a blowout phenomenon, so research in the field of computer vision is also gradually expanding in the direction of video data. The basis of video processing is action recognition. Although traditional action recognition has achieved a high recognition rate, because the original data must be a short video with a fixed frame number after cropping, it is required to include a single action tag. Such cropping requirements are too harsh. , but in practical applications, actions appear randomly in long videos, so traditional action recognition algorithms cannot meet the actual application scenarios. Time-sequence motion detection is a specific study of such uncropped original long vi...

AI Technical Summary

Problems solved by technology

On the basis of accurate detection of action categories, in order to solve the problems of insufficient expression of long action features and inaccurate regression of long action boundaries in the process of boundary detection, a time-series action recognition method based on deep learning is proposed to effectively improve the accuracy of predicted action segments. The degree of overlap of action segments

Images