计算机工程与应用 ›› 2015, Vol. 51 ›› Issue (19): 169-172.

• 图形图像处理 • 上一篇    下一篇

轨道视觉检测系统中行程编码的应用研究

闵永智1,康  飞1,党建武1,邓  岳2   

  1. 1.兰州交通大学 自动化与电气工程学院,兰州 730070
    2.中国北车集团 大连机车车辆有限公司,辽宁 大连 116000
  • 出版日期:2015-09-30 发布日期:2015-10-13

Study on application of run length encoding in track visual inspection system

MIN Yongzhi1, KANG Fei1, DANG Jianwu1, DENG Yue2   

  1. 1.School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China
    2.Dalian Locomotive and Rolling Stock CO., LTD. CNR Group, Dalian, Liaoning 116000, China
  • Online:2015-09-30 Published:2015-10-13

摘要: 利用行程编码针对背景冗余计算的优化特性与交、并简便运算特点对二值图像形态学膨胀算法进行优化,并提出基于行程编码优化的形态学膨胀算法。利用算法对轨道轮廓二值图像进行形态学膨胀处理;依据优化前后的图像处理结果和速度进行对比分析。该算法能去除边缘毛刺与断线现象;轨道轮廓单帧图像经过优化处理后的速度提高5倍,轨道视觉检测系统的检测精度可提高到20点/m。

关键词: 行程编码, 形态学膨胀, 图像处理, 视觉检测, 轨道

Abstract: This paper optimizes the binary image morphological dilation algorithm by run length encoding with the optimization features in background redundant and intersection and union simple operation, and proposes the run length encoding-
morphological dilation optimized algorithm. It processes the track contour binary image in morphological dilation by the optimized algorithm. The compared analysis is based on the image processing result and the speed before and after optimization. The edge burr and disconnection phenomenon can be removed by the optimized algorithm. The processing result of the track contour single frame image increases 5 times, and the detection accuracy of the track visual inspection system can be improved to 20 points per meter.

Key words: run length encoding, morphological dilation, image processing, visual inspection, track