Track component inspection method and device, computer equipment and storage medium

Abstract

The invention relates to a track component inspection method and device, computer equipment and a storage medium. The track component inspection method comprises the following steps: acquiring a track picture; the rail picture comprises a multi-view rail image shot by the unmanned aerial vehicle along the rail; a region generation network containing an attention mechanism is adopted to extract a target region of the rail picture, and a target detection result is determined; the target region comprises rail fasteners; the target detection result comprises a feature matrix of the target region; based on a preset screening rule, performing multi-target screening on the target detection result to obtain a screened picture; according to the multi-view rail image, performing feature fusion on each view feature matrix of the same target region in the screened image to obtain a fused image; carrying out anomaly detection on the fused image by adopting a meta-learning anomaly detection model, and outputting an inspection result; the inspection result comprises an abnormal probability value of the rail fastener. The flexibility, the accuracy and the real-time performance of the inspection process are effectively improved.

Description

technical field [0001] The present application relates to the technical field of inspection, and in particular to a method, device, computer equipment and storage medium for inspection of rail components. Background technique [0002] The most important thing to ensure the safety of railway traffic is to ensure that the railway track is in good condition at all times. Rail fasteners are components used to connect concrete sleepers and rails on the track, also known as intermediate connecting components. Its function is to firmly fix the rail on the sleeper, maintain a long-term and reliable connection between the sleeper and the track, and prevent the rail from moving laterally and longitudinally relative to the sleeper from the sleeper rail, thereby causing traffic threats. Therefore, whether the rail fasteners are in good condition determines the probability of an accident on the current road section. [0003] Traditional railway track inspections are limited by the level...

AI Technical Summary

Problems solved by technology

[0004] In the process of implementation, the inventors found that there are at least the following problems in the traditional technology: the current detection method has problems such as low detection efficiency and poor accuracy

Images