摘要
基于钢轨在监测图像中的特征,结合Radon变换思想,推导出用于钢轨识别检测的Bresenham直线算法,提出钢轨直线检测实现方法。在此基础上,得到一种基于图像处理的钢轨识别检测方法,现场试验验证了该检测方法的计算效果。研究结果表明:由该方法计算得出的2条直线准确地落在监测图像中的2条钢轨上,并得出在图像坐标系下的2条钢轨直线方程,说明该方法可准确识别检测出监测图像中的钢轨,为准确监测沙雪等异物入侵事件提供了必要支撑。
Based on the railway rail feature in the monitoring image, combined with the Radon transform idea, the Bresenham line detection algorithm was derived for the railway rail recognition detection, and the railway rail line detection implementation method was proposed. A recognition method for the railway rail based on the image processing was obtained. The field test verified the numeration effectiveness of the method. The results show that the two straight lines calculated by the railway rail recognition detection method accurately fall on the two railway rails in the monitor image, and the two railway rails equations are obtained in the image coordinates, which shows that the method can accurately identify and detect the railway rail in the monitoring image, and can provide the necessary support for accurately monitoring the sand, snow and other foreign matter invasion.
出处
《中南大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2014年第7期2496-2502,共7页
Journal of Central South University:Science and Technology
基金
湖南省科技计划重点项目(2013SK2006)
中国铁路总公司科技研究开发计划项目(2013T002-A-1-1)
