Method for recognizing human body behaviors by utilizing posture mask

Abstract

The invention provides a method for performing human body behavior recognition by using an attitude mask, and belongs to the technical field of behavior recognition. The method comprises: extracting athermodynamic diagram from the frame image of the RGB video by using a preposed two-dimensional attitude estimation network; and performing multi-point Gaussian diffusion on the thermodynamic diagramto obtain an attitude mask, taking an image sample obtained by fusing the attitude mask and the original image as input of a space-time neural network, and training the space-time neural network by using the training set marked with the human body behavior category label to obtain a model for human body behavior recognition. According to the method, the spatial features of the human body skeletonkey point position area obtained through attitude estimation are extracted through the attitude mask, the robustness to the change of the image background is high, the number of recognition network parameters is small, the training cost is low, and the recognition accuracy of human body behaviors is high.

Description

technical field [0001] The invention belongs to the technical field of behavior recognition, in particular to a method for human body behavior recognition by using a gesture mask. Background technique [0002] Human behavior recognition has broad application prospects in the fields of intelligent monitoring, human-computer interaction, and video analysis, and has become a research hotspot in recent years. With the rapid development of convolutional neural network (CNN), methods based on deep learning have gradually become the mainstream methods in the field of action recognition. [0003] Among the existing network models, two-stream methods, 3D-CNN and recurrent neural network structures have achieved remarkable success on multiple public datasets. However, these methods mainly focus on the feature extraction of RGB images and optical flow, ignoring the rich features provided by the joint points of human bones, which makes the model parameters of the method large, the feat...

AI Technical Summary

Problems solved by technology

However, these methods directly use human body pose images as input, without distinguishing them according to different skeletal joint points, which leads to the network model indiscriminately extracting the spatial features of each part of the human body, while ignoring the human body structure. semantic features

Images