Safety helmet wearing detection method, device and equipment and storage medium

Abstract

The invention discloses a safety helmet wearing detection method, device and equipment and a computer readable storage medium, and the method comprises the steps: inputting a to-be-detected image into a target safety helmet detection neural network model, and extracting a human body target feature map through a target detection SSD network; inputting the human body target feature map into a key area attention mechanism network to determine a head key area; segmenting and extracting a head region feature map from the human body target feature map by using a key region feature map segmentation network according to the position of the head key region; and inputting the head region feature map into a safety helmet detection dynamic model, judging the confidence output by the branch network, and outputting a detection result of which the confidence is greater than or equal to a threshold value as a safety helmet wearing detection result. According to the method, the device, the equipment and the computer readable storage provided by the invention, the precision and the efficiency of the detection result of the wearing condition of the safety helmet are improved, and the phenomena of missing detection and false detection caused by a complex background of a substation scene are effectively avoided.

Description

technical field [0001] The present invention relates to the technical field of deep learning and artificial intelligence, in particular to a safety helmet wearing detection method, device, equipment and computer-readable storage medium. Background technique [0002] Substation is an important facility in the national grid. Wearing safety helmets is an important measure to ensure the safety of workers. Therefore, it is of great significance to provide a method that can monitor the wearing of safety helmets by workers in real time. The existing safety helmet wearing detection algorithm has the following problems: a. The data set about the worker's safety helmet is relatively scarce, and the proportion of valid data is relatively low; The proportion is low, the feature information is not clear, and there will inevitably be missed detection problems; c. The environment of the substation is relatively complex, and it is prone to false detections caused by complex images. The abo...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a safety helmet wearing detection method, device, equipment and computer-readable storage medium to solve the problems of low recognition accuracy and efficiency, and the existence of missed and false detections in existing safety helmet wearing detection methods

Images