Multi-view stereoscopic vision detection device and method for bridge base nut-screw looseness or fracture

Abstract

The invention discloses a multi-view stereoscopic vision detection device and method for bridge base nut-screw looseness or fracture. According to the method, multiple micro-cameras are installed in bionic installation racks to form a stereoscopic vision detection system, and each nut-screw group in a circumference can be detected; three-dimensional parameters of nut-screw assembling are obtainedthrough camera coordinate correlation, image preprocessing, image matching, three-dimensional point cloud reconstruction, denoising, etc.; and through algorithm and geometric parameter calculation, the three-dimensional parameters are compared with standard assembling nut-screw data, comparison parameters are obtained, quantitative data of nut-screw looseness or fracture is obtained, and maintenance parameters are provided for technicians. Through the detection device and method, detection precision is high, real-time detection is realized, and cost is low.

Description

technical field [0001] The invention relates to the technical field of detection, in particular to a multi-eye stereo vision detection device and method for loose or broken nuts and screws of a bridge base. Background technique [0002] The base of the bridge steel frame is connected with the nut and the screw. Due to the damage of vibration, impact, rain, snow and acid rain, the nut and the screw will be loose or broken, which requires manual judgment with eyes. Some dead angles may not be detectable manually. At the same time, due to subjective factors and visual fatigue, there will be detection errors or missed detections. It can be seen that the manual inspection of the nuts and screws of the bridge base has problems such as unsafe heights, high labor costs, and low efficiency. At present, there is a method of manually taking photos with a camera to detect whether the nuts and screws of the bridge base are loose or broken, and judge whether they are loose by manually lo...

AI Technical Summary

Problems solved by technology

[0002] The base of the bridge steel frame is connected with the nut and the screw. Due to the damage of vibration, impact, rain, snow and acid rain, the nut and the screw will be loose or broken, which requires manual judgment with eyes. Some dead angles may not be detectable manually. At the same time, due to subjective factors and visual fatigue, there will be detection errors or missed detections.

It can be seen that there are problems such as high altitude unsafety, high labor cost and low efficiency in manual inspection of bridge base nuts and screws

At present, there is a method of manually taking photos with a camera to detect whether the nuts and screws of the bridge base are loose or broken, and judge whether they are loose by manually looking at the photos. However, if the hand shakes, the obtained image is blurred and cannot be accurately judged. Dead spots that the camera cannot detect

Moreover, manual or manual camera detection cannot be monitored in real time, and a single image obtained by a single camera cannot obtain accurate quantitative loosening values ​​through 3D reconstruction, and cannot provide technicians with specific maintenance parameters.

Images