Video motion identification method based on sparse time slicing network

Abstract

The invention discloses a video motion identification method based on a sparse time slicing network. The method includes steps: extracting information from each training video, and performing first training and optimization on the time slicing network; adding a sparse to the network after the first optimization, and performing second training and optimization; performing cutting and dimension adjustment on the network after the second optimization; performing third training and optimization on the network after dimension adjustment until the identification precision or the sparsity reaches theexpectation; and extracting information from a to-be-identified video, inputting the extracted information to the network after the third optimization, and performing output and fusion on the time slicing network to obtain a motion identification result. According to the method, the information of the longer video can be obtained through the time slicing network, and a double-flow convolutional network structure can fully utilize the video information and greatly improve the motion identification precision; and a structured sparse method can enable the weight of a convolution layer to be sparse in groups, a model is further simplified by network cutting, and the storage space is reduced.

Description

technical field [0001] The invention belongs to the field of image processing, and more specifically relates to a video action recognition method based on a sparse time segment network. Background technique [0002] Video action recognition is to process the data of the input video, and then design an algorithm to analyze the human behavior in the video and recognize the human action. In 2014, Simonyan et al. proposed a video action recognition method based on a two-stream convolutional network model. The model consists of two neural networks. The first is a spatial neural network, and the input data is a traditional single RGB image. The second It is a temporal neural network, and the input data is the optical flow map corresponding to the RGB image of the first network. The optical flow map is calculated from two RGB images at adjacent moments. By calculating the changes in pixels between the two images, an optical flow map containing change information can be obtained, s...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the defects of the prior art, the purpose of the present invention is to solve the technical problems of large storage space, low recognition accuracy and slow recognition speed in the prior art

Images