Human-machine collision early warning method and system on construction site

Abstract

The present disclosure relates to a human-machine collision early warning method and system at a construction site. The system includes: a data acquisition module, which collects data of the construction site through multiple binocular cameras and multiple sensors installed on mobile mechanical equipment at the construction site. Current image data, depth image data and motion data of mechanical equipment; the processing module analyzes and processes each current image data to determine the worker contour pixel coordinates in each current image data, according to the worker contour pixel coordinates, depth image data Determine the distance between the worker and the mechanical equipment and the color combination of the worker's helmet in each current image data and the corresponding motion data of the mechanical equipment; the risk identification module, according to the distance between the worker and the mechanical equipment in each current image data Combining with the color of the worker's helmet to identify the risk level corresponding to the current image data; the early warning module determines the corresponding human-machine collision warning prompt method according to the risk level.

Description

Technical field[0001]The present disclosure relates to the technical field of safety monitoring on construction sites, and in particular to a method and system for early warning of human-machine collisions on construction sites.Background technique[0002]With the development of construction technology in the construction industry, more and more mobile construction machinery, such as excavators, forklifts, cranes, etc., are used on the job site. The use of mobile construction machinery has introduced the risk of human-machine collisions on the construction site. Collision-related accidents at the construction site accounted for 22% of the total accidents. Human-machine collisions have gradually become one of the main causes of accidents on the construction site.[0003]The human-machine collision accident at the construction site is caused by the following two reasons. The first is that the machinery may be in a state of overall or partial movement due to the needs of the work task, suc...

AI Technical Summary

Problems solved by technology

[0005] 1) The combination of operating machinery and staff matches but is not common, which means low-frequency correct operation. Due to the relatively low frequency, the proficiency of workers and managers is relatively low, and early warning is required to increase the attention of staff;

[0006] 2) There is a visual blind spot, and an early warning is required to indicate the existence of the blind spot;

[0008] 4) There is a lack of workers or supervisors in the operation area. At this time, early warning is required to prompt high-risk operations

[0009] 5) There are too many supervisors, and supervisors sometimes gather in risky areas, bringing unnecessary risks. At this time, it is necessary to warn and drive away unnecessary supervisors

Artificial intelligence technology can provide support for identifying high-risk conditions on the construction site, but artificial intelligence technology relies on the powerful computing power of hardware equipment, and collision accidents require that the accident risk identification should not exceed 1s

Images