Video image classification method based on time-space co-occurrence double-flow network

Abstract

The invention provides a video image classification method based on a time-space co-occurrence double-flow network. The main content of the video image classification method comprises data input, a time-space double-flow network, fusion and an SVM classifier. The process comprises the steps of firstly inputting image and light stream information, performing early fusion by being combined with a time network and a space network, enabling fusion output to act as a feature vector, inputting the feature vector into the SVM classifier, and acquiring a final classification result. According to the invention, a method that the early fusion double-flow network is combined with time information and space information (time-space co-occurrence) is adopted, a video data set of the monkey is utilized, and more frames, namely, more space data, are utilized from each piece of video so as to generate significant improvement in precision; the space information and the time information are combined and form mutual complementation, and the precision reaches 65.8%. A smaller number of separated clusters are formed through using the co-occurrence method, the separated clusters generally stay together more closely, and the time information is better utilized.

Description

technical field [0001] The invention relates to the field of video image classification, in particular to a video image classification method based on a space-time co-occurrence dual-stream network. Background technique [0002] Video image classification is a very challenging problem because pose and appearance variations cause large intra-type variations, as well as small intra-type variations caused by subtle differences in overall appearance between types. Recently, deep convolutional neural networks (DCNNs) have been used to learn many powerful features, handle large changes with hierarchical models, and localize regions automatically. Despite the advances in these methods, previous work treats the object classification task as a still image classification problem, ignoring the complementary temporal information present in videos. So far, no neural network based methods have been used to classify objects in videos. [0003] The present invention introduces the problem...

AI Technical Summary

Problems solved by technology

So far, no methods based on neural network meth

Images