Video behavior identification method based on an Attention-LSTM network

Abstract

The invention discloses a video behavior identification method based on an Attention-LSTM network. The method includes transforming the input RGB image sequence through an optical flow image sequencegeneration module to obtain an optical flow image sequence; inputting the optical flow graph sequence and the original RGB graph sequence into a time domain attention frame taking module, and respectively selecting non-redundant key frames in the two graph sequences; inputting the key frame sequences of the two images into an AlexNet network feature extraction module, respectively extracting timesequence features and spatial features of the two frame images, and performing a feature weight increasing operation with strong action correlation on the feature image output by the last convolutional layer through a feature weight increasing module; and inputting the feature maps output by the two AlexNet network feature extraction modules into an LSTM network behavior identification module, respectively identifying the two pictures, and fusing the two identification results in proportion through a fusion module to obtain a final video behavior identification result. According to the invention, the function of identifying the behavior from the video can be realized, and the identification accuracy can be improved.

Description

technical field [0001] The invention belongs to the field of computer vision, and in particular relates to a video behavior recognition method based on an Attention-LSTM network. Background technique [0002] Intelligent video analysis is currently a very hot and challenging direction in the field of computer vision. The direction of intelligent video analysis includes many sub-research directions, and the main two research directions are behavior recognition and behavior detection. Behavior recognition is similar to image classification. It mainly solves the problem of "what is the behavior in the video". Given a trimmed video containing only one behavior, it is required to classify the video. Behavior detection (or positioning) is consistent with target detection, and mainly solves the problem of "whether there is a corresponding behavior in the video, and if so, in which segment of the video frame sequence and where in each frame", which is mainly divided into two parts:...

AI Technical Summary

Problems solved by technology

In the past, the behavior detection method mostly used the sliding window method, but the action positioning based on the sliding window method is very time-consuming and time-efficient

Images