The Imaging System And Method Design For Heavy Rail Surface Based On Machine Vision

In this dissertation, aiming at the complex geometrical characteristic and the lowreflection and high radiation of the heavy rail surface, the imaging method of the heavyrail surface defects was researched on the base of the theory and technology of machinevision. The imaging system of heavy rail surface defects was achieved with theoptimized design of imaging angle and the development of special lighting system. Thesystem further enhance the imaging effect of heavy rail surface defects and provide thebasis for the development of heavy rail surface defects on-line detection system. Themain works of the research are as follows:(1) Starting with the production processes of heavy rail, the geometric features andsurface defects of heavy rail surface were analyzed in detail, and the reasons andregularity of defects were summarized. The light transmittance, reflectance and thermalradiation characteristics of thermal heavy rail surface were analyzed in detail combinedwith physical optics theory and radiation theory. The overall design of heavy rail surfacedefects imaging system was proposed on the base of the researches and machine visiontheory system.(2) The best segmentation scheme of the FOV (field of view) was chose forgeometrical characteristic of heavy rail surface. The image acquisition system wasdesigned combined with the selection of camera and lens. The imaging angles ofcameras were computed with the optimization design on the base of the segmentation ofcameras’ view field, and the best angles of cameras were selected through the imagingquality evaluation of the heavy rail surface.(3) To improve the feature information of heavy rail surface, the effects of lightsource parameters and illumination mode were analyzed and the best imageenhancement technologies were chose and applied on heavy rail surface images whichwere took under different illumination mode. The best illumination mode for differentdefects was chose by the effect compare of image segmentation and edge detection. The special lighting system was developed on the base of the best illumination mode and thecharacteristic of the heavy rail surface.(4) According the different feature of cold heavy rail and thermal heavy rail, theexperimental platforms of surface defects imaging and detection were constructed forcold heavy rail and thermal heavy rail. The experiments completed in the lab and theproduction site provided a lot of data for the building of the system framework, thecomponent selection of machine vision system, the establishment of illumination modeland the development of image processing software. It provides the experimental basisfor the development of heavy rail surface defects on-line detection system.