Human body action recognition method based on separable three-dimensional residual attention network

Abstract

The invention relates to a human body action recognition method based on a separable three-dimensional residual attention network, and belongs to the field of computer vision. The method comprises the following steps: S1, replacing a standard three-dimensional convolution in a 3D ResNet with a separable three-dimensional convolution, and constructing a Sep-3D ResNet; S2, designing a channel attention module and a space attention module, and stacking the modules in sequence to construct a dual attention mechanism; S3, carrying out double attention weighting on the middle-layer convolution features at different moments, a double attention module is expanded in the time dimension, then the double attention module is embedded into a Sep-3D RAB of the Sep-3D ResNet, and a Sep-3D RAN is built; and S4, carrying out joint end-to-end training on the Sep-3D RAN by utilizing a multi-stage training strategy. The method can improve the distinguishing capability of classification and discrimination features, achieves the efficient extraction of high-quality space-time visual features, and can enhance the classification precision and recognition efficiency of the model.

Description

technical field [0001] The invention belongs to the field of computer vision, and relates to a human action recognition method based on a separable three-dimensional residual attention network. Background technique [0002] There is a huge amount of information hidden in the video. The huge number of users in the online video market and the rapidly growing market size have brought great challenges to the management, storage and identification of online video. Therefore, the online video business has been paid more and more attention by all parties. In the human-centered computer vision research field, the human action recognition task has become an important research direction in computer vision tasks due to its wide application in many fields such as human-computer interaction, smart home, autonomous driving, and virtual reality. The main task of human action recognition is to spontaneously identify human actions in image sequences or videos. By processing and analyzing ima...

AI Technical Summary

Problems solved by technology

[0006] In view of this, the purpose of the present invention is to provide a human action recognition method based on a separable three-dimensional residual attention network, which adopts a reasonable kernel structure decomposition operation to alleviate the difficult phenomenon of deep three-dimensional convolution model optimization, and combines the attention mechanism to Improve the flexibility of key feature screening, so as to produce higher quality spatio-temporal visual features to improve the recognition performance of the model

Images