Fastener looseness prevention identification detection method, system storage medium and computer device

Abstract

The invention discloses a fastener looseness prevention identification detection method, a system storage medium and a computer device. The method comprises the following steps: obtaining to-be-detected three-dimensional point cloud data of a detected fastener; extracting feature points in the to-be-detected three-dimensional point cloud data and pre-stored sample three-dimensional point cloud data respectively, and registering all the feature points in the to-be-detected three-dimensional point cloud data with all the feature points in the sample three-dimensional point cloud data; segmentingthe registered to-be-detected three-dimensional point cloud data and the sample three-dimensional point cloud data, and reserving an effective data area containing an anti-loose identifier; comparingthe feature points in the two segmented effective data areas, and judging whether the anti-loose identifier deflects according to whether the feature points in the two effective data areas are different or not. The position of the fastener which is frequently or easily loosened can be effectively found, effective data can be provided for the improvement of the part or the structure of the fastener, and the fastener has very high practicability.

Description

technical field [0001] The invention relates to the field of imaging detection and processing, in particular to a detection method, a system storage medium and computer equipment for anti-loosening marks of fasteners. Background technique [0002] At present, the commonly used connection and fastening method for subway vehicles is threaded connection, which relies on the threaded pair to carry the load. The biggest advantage of this fastening method is that it is more convenient and practical to disassemble. However, the existing vibration problem will inevitably lead to the deterioration of the operating condition of the equipment, and even cause damage to the components, which will seriously endanger the driving safety. Therefore, the most important link and prerequisite for vehicle overhaul and maintenance is good fastening. In view of this situation, it is particularly important to choose a reliable and feasible fastening method. At this time, it is necessary to take co...

AI Technical Summary

Problems solved by technology

The problem with this method is that there are hundreds of thousands of images for one train, and the captured images are almost all fasteners covered by stains and dust

Since there are very few anomaly detection images, the training for anomalies is insufficient, making it difficult to accurately detect anomalies

[0003] Disadvantages of the traditional anti-loose identification method: 1. It is time-consuming and labor-intensive to rely on human eyes, and in general, the detection environment is relatively harsh, which will affect people's health

At the same time, if there are a lot of tasks, there will be a lot of waste of human resources

2. If the anti-loose label is covered by stains, dust, etc., human eyes cannot complete the recognition work, and the existing 2D image technology based on color recognition cannot be accurately recognized and judged due to stains and other reasons

Images