Human body action recognition method fusing attention mechanism and space-time diagram convolutional neural network under security scene

Abstract

The invention provides a human body action recognition method fusing an attention mechanism and a space-time diagram convolutional neural network under a security scene, and the method comprises the steps: firstly carrying out the random division of an obtained human body action analysis data set under the security scene, and dividing the human body action analysis data set into a training set anda verification set; secondly, performing data enhancement processing on video data of the training set and the verification set; carrying out key frame screening on the obtained and enhanced data setby utilizing an attention mechanism; transcoding and labeling the screened key frame video by using a human body posture estimation model framework to prepare for training a human body motion detection and recognition model; and finally, constructing a space-time skeleton map convolutional neural network model, training by using the training set, carrying out network parameter weight optimizationby using random gradient descent, and predicting the accuracy of the neural network model by using the verification set. The method not only can enlarge the original action data volume, but also canenhance the robustness of the model, thereby improving the final action recognition accuracy.

Description

Technical field [0001] The invention relates to the field of pattern recognition and computer vision, in particular to a human action recognition method that combines an attention mechanism and a spatiotemporal graph convolutional neural network in a security scene. Background technique [0002] Vision has always been the most important and intuitive way for humans to obtain information from the outside world. According to relevant statistics, 80% of information obtained by humans is through vision. With the continuous increase in the quality of image sensors such as cameras and the continuous decline in prices, image sensors have been deployed and applied on a large scale, resulting in massive amounts of information every day. Relying solely on the eyes to obtain the required information can no longer meet people's requirements for new information and knowledge. In addition, with the increase in computer computing speed, the further enhancement of computing power, and the conti...

AI Technical Summary

Problems solved by technology

[0008] In view of the above problems, the present invention provides a human action recognition method that integrates the attention mechanism and the spatio-temporal graph convolutional neural network in the security scene, which solves the low frequency of abnormal actions in the security scene and the difficulties in data collection and labeling; the traditional skeleton construction Modular methods usually rely on handcrafted parts or traversal rules, resulting in limited expressiveness and difficulty in generalization; traditional motion description methods such as 3DHOG, motion vectors, and dense trajectories have problems such as low efficiency and low accuracy

Images