Bidirectional long short-term memory unit-based behavior identification method for video

Abstract

The invention discloses a bidirectional long short-term memory unit-based behavior identification method for a video. The method comprises the steps of (1) inputting a video sequence and extracting an RGB (Red, Green and Blue) frame sequence and an optical flow image from the video sequence; (2) respectively training a deep convolutional network of an RGB image and a deep convolutional network of the optical flow image; (3) extracting multilayer characteristics of the network, wherein characteristics of a third convolutional layer, a fifth convolutional layer and a seventh fully connected layer are at least extracted, and the characteristics of the convolutional layers are pooled; (4) training a recurrent neural network constructed by use of a bidirectional long short-term memory unit to obtain a probability matrix of each frame of the video; and (5) averaging the probability matrixes, finally fusing the probability matrixes of an optical flow frame and an RGB frame, taking a category with a maximum probability as a final classification result, and thus realizing behavior identification. According to the method, the conventional artificial characteristics are replaced with multi-layer depth learning characteristics, the depth characteristics of different layers represent different pieces of information, and the combination of multi-layer characteristics can improve the accuracy rate of classification; and the time information is captured by use of the bidirectional long short-term memory, many pieces of time domain structural information are obtained and a behavior identification effect is improved.

Description

technical field [0001] The invention relates to a video processing method, in particular to a method for automatically recognizing the behavior of characters in a video. Background technique [0002] Behavior recognition refers to the analysis of the behavior of the target by extracting the feature information in the video or image sequence to identify the behavior patterns of the characters in the video. [0003] Action recognition is an important and difficult subject in computer vision and pattern recognition. It has broad application prospects in many aspects, such as intelligent monitoring, human-computer interaction, virtual reality, intelligent security and so on. In today's society, with the rapid development of the economy, people pay more and more attention to safety issues. More and more places have installed video surveillance cameras, and a large number of surveillance videos are generated every day. Now people generally use manual surveillance. This It needs ...

AI Technical Summary

Problems solved by technology

Videos cannot be accurately desc

Images