Detection and alarm method for staying of personnel below crane

Abstract

The invention belongs to the technical field of image recognition application, and particularly discloses a method for detecting and warning retention of personnel below a crane, which comprises the following steps: acquiring a to-be-detected crane scene picture by using a camera, and calibrating the camera and the picture to obtain a projection transformation module between a picture plane and the ground; preprocessing the picture to obtain a preprocessed picture; inputting the preprocessed picture into a pre-trained deep neural network model, and outputting the position of the personnel, the position of the crane and a projection point of the center of the crane on the ground; the projection points are input into the projection transformation module, and the dangerous area range below the crane is obtained; and judging whether the personnel position is in a dangerous area and giving an alarm. The system has the beneficial effects that the safety problem in an engineering construction site or a large mechanical equipment factory is solved, all-weather and real-time detection of personnel retention in a dangerous area below the crane is achieved, accurate, stable and timely monitoring and early warning operation processing can be completed, and safe production operation is achieved.

Description

Technical field [0001] The present invention belongs to the field of image recognition applications, in particular to the field of target key detection in the field of image recognition, and specifically involves a landing of the personnel in a crane. Background technique [0002] In the construction site of the project or in a factory with large machinery, cranes, cranes, etc. are common mechanical equipment. [0003] Since the needs of large-scale objects are often caused, in the safety management system, the dangerous area is dangerous, while the dangerous area personnel are retained or walking is a huge safety hazard in the operation process, and the real-time supervision or inspection of this safety hazard is required. [0004] In the past, the method of artificial inspections, on the one hand, the efficiency of the inspection is low, and it is impossible to meet the needs of modern enterprise production and development; on the other hand, security hidden dangers threatened ...

AI Technical Summary

Problems solved by technology

[0004] The manual inspection method in the past, on the one hand, the inspection efficiency is low and cannot meet the needs of the production and development of modern enterprises; on the other hand, hidden safety hazards pose a threat to the personal safety of inspectors

Images