一种基于深度估计的铁路扣件松紧度检测方法
By using a depth estimation-based method for detecting the tightness of railway fasteners, and combining two-dimensional and depth images with ZoeDepth and YOLOv8 models, the method solves the problems of low efficiency of manual inspection and high cost of three-dimensional scanning, and achieves low-cost and rapid automated detection of fastener tightness.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CENT SOUTH UNIV
- Filing Date
- 2024-06-21
- Publication Date
- 2026-07-17
AI Technical Summary
In existing technologies, the detection of the tightness of railway fasteners relies on manual inspection, which is inefficient, costly, and has a high rate of missed detection. Furthermore, image-based machine vision methods cannot identify tightness, and 3D scanning sensor equipment is expensive and requires a large amount of computing resources.
A method for detecting the tightness of railway fasteners based on depth estimation is adopted. By acquiring two-dimensional and depth images of the track structure, and combining the ZoeDepth model and the YOLOv8 model, an absolute depth distribution and track two-dimensional image annotation model are constructed to achieve automated detection of fastener tightness.
It enables low-cost, fast, and accurate detection of railway fastener tightness, reduces hardware costs and computing resource requirements, and is suitable for automated inspection of track inspection trolleys.
Smart Images
Figure CN118711015B_ABST