Coal mine personnel behavior detection method and device, and storage medium

Abstract

The embodiment of the invention provides a coal mine personnel behavior detection method and device, and a storage medium. The method comprises the following steps: obtaining a to-be-processed image, preprocessing the to-be-processed image, obtaining an input mark sequence corresponding to the to-be-processed image, determining an attention output matrix based on an attention algorithm according to the input mark sequence, generating a feature map according to the attention output matrix, and carrying out bounding box regression processing on the feature map to obtain a behavior classification result of the coal mine personnel in each bounding box. According to the embodiment of the invention, global image processing is carried out on the to-be-processed image, and compared with only extraction of human body node information, more detail information features are included, so that the output behavior classification result of the coal mine personnel is more accurate, and the accuracy of the behavior classification result is improved by adopting the bounding box regression algorithm. The behaviors of multiple persons in the image can be detected at the same time, the behavior classification results corresponding to the persons in the bounding boxes are obtained, and the comprehensiveness of the detection results is guaranteed.

Description

technical field [0001] The embodiments of the present application relate to the technical field of image processing, and in particular to a coal mine personnel behavior detection method, device and storage medium. Background technique [0002] With the improvement of video data processing capability and the development of computer vision technology, the performance requirements of coal mine intelligent video surveillance system are getting higher and higher. Through the coal mine intelligent video monitoring system, real-time monitoring of the coal mine production site can be carried out, and unsafe working factors can be found as early as possible to ensure the safety of the coal mine production environment. [0003] In the existing technology, the coal mine intelligent video surveillance system can use the key point detection method based on deep learning to extract the human body node information of the coal mine personnel, and realize the detection of the coal mine perso...

AI Technical Summary

Problems solved by technology

[0004] However, in the process of implementing this application, the inventors found that there are at least the following problems in the prior art: in the existing behavior detection scheme, the behavior detection of coal mine personnel is only based on the extracted human node information, and the data base is relatively weak. In the case of complex and diverse behavior types, the accuracy of behavior detection results is low

Images