A Construction Helmet Wearing Monitoring Method Based on Computer Vision Human Pose Estimation

Abstract

The invention discloses a construction safety helmet wearing monitoring method based on computer vision human body posture estimation, comprising the following steps: S100 detecting and outputting the body skeleton postures of all individuals in the image according to the real-time multi-person posture estimation algorithm model OpenPose; S200 according to the depth Learning object detection algorithm model YOLOv3 detects workers and helmets in the image, and uses two types of rectangular borders to mark and output them respectively; S300 integrates two algorithm models, according to the intersection ratio of the two types of rectangular borders and the ratio of the rectangular borders of the helmet Compare the length of the diagonal line with the length from the center point of the character's face to the center point of the helmet to determine whether the worker in the picture is wearing a helmet. The invention can accurately judge whether the safety helmet is worn correctly. The method has a clear logic flow and a fast detection speed, and is of great significance for ensuring the effective wearing of the safety helmet at the construction site in real time and maintaining the life safety of construction personnel.

Description

technical field [0001] The invention belongs to the field of safe and civilized construction management of civil engineering and intelligent video monitoring, and in particular relates to a construction safety helmet wearing monitoring method based on computer vision human body posture estimation. Background technique [0002] Civil engineering construction requires a large number of people to participate, and the site environment is complex, which is a high-risk manufacturing process. Safety helmets can significantly buffer physical impacts, reduce head injuries, and effectively protect the safety of construction workers. However, during construction operations, construction workers often fail to wear safety helmets in accordance with production specifications, causing potential safety hazards. Therefore, it is of great significance to ensure the effective wearing of helmets on the construction site in real time to maintain the life safety of construction workers. The man...

AI Technical Summary

Problems solved by technology

[0004] The problem to be solved by the present invention is that the detection accuracy of the current video-based construction personnel safety helmet wearing detection method is low, the detection principle is relatively simple, and it is easy to fail under the actual complex construction site and human behavior. Therefore, a method based on Construction helmet wearing monitoring method based on computer vision human pose estimation

Images