华南理工大学学报(自然科学版) ›› 2014, Vol. 42 ›› Issue (1): 117-122.doi: 10.3969/j.issn.1000-565X.2014.01.020

• 计算机科学与技术 • 上一篇    下一篇

基于分数阶积分谷底边界检测的路面裂缝提取

王卫星1,2 吴林春1   

  1. 1.福州大学 物理与信息工程学院,福建 福州 350002; 2.瑞典皇家理工学院,瑞典 斯德哥尔摩
  • 收稿日期:2013-07-19 修回日期:2013-11-28 出版日期:2014-01-25 发布日期:2013-12-01
  • 通信作者: 王卫星(1959-),男,教授,博士生导师,主要从事图像处理与分析及模式识别研究. E-mail:wxwwx@fzu.edu.cn
  • 作者简介:王卫星(1959-),男,教授,博士生导师,主要从事图像处理与分析及模式识别研究.
  • 基金资助:

    国家自然科学基金资助项目(61170147)

Extraction of Pavement Cracks Based on Valley Edge Detection of Fractional Integral

Wang Wei- xing1,2 Wu Lin- chun1   

  1. 1.College of Physics and Information Engineering,Fuzhou University,Fuzhou 350002,Fujian,China;2.Royal Institute of Technology,Stockholm,Sweden
  • Received:2013-07-19 Revised:2013-11-28 Online:2014-01-25 Published:2013-12-01
  • Contact: 王卫星(1959-),男,教授,博士生导师,主要从事图像处理与分析及模式识别研究. E-mail:wxwwx@fzu.edu.cn
  • About author:王卫星(1959-),男,教授,博士生导师,主要从事图像处理与分析及模式识别研究.
  • Supported by:

    国家自然科学基金资助项目(61170147)

摘要: 针对路面裂缝图像噪声大、边界弱、裂缝细小导致分割难的问题,提出了一种基于谷底边界的路面裂缝提取方法.该方法首先对原始图像进行邻域平滑处理,在消除噪声的同时扩展了裂缝的相对宽度; 接着对图像进行基于分数阶积分的谷底边界检测; 然后采用形态学方法对图像进行处理,使裂缝趋于光滑后进行短线噪声去除,并结合最大熵阈值断线连接法自动连接裂缝断口,从而得到最终的裂缝检测结果.实验结果表明,该方法能快速检测出细小的路面裂缝,具有抗噪性能好、定位准确及检测精度高的特点.

关键词: 路面裂缝, 裂缝检测, 分数阶积分, 谷底边界, 图像分割

Abstract:

As pavement crack images are difficult to segment due to the existence of high noise,weak boundary andsmall cracks,an extraction method of pavement cracks based on the valley edge detection of fractional integral isproposed.In this method,first,neighboring smoothing of the original image is performed to eliminate the noise andexpand the relative width of the cracks.Then,the main cracks are extracted via the valley edge detection of frac-tional integral,and the resulting image is further processed via the morphological approach with short- line noiseelimination. Afterwards,final cracks are extracted by using the gap linking method on maximum entropy thresholdto cause cracks to merge automatically. Experimental results show that the proposed method instantly helps to detectsmall pavement cracks with high accuracy and strong noise robustness.

Key words: pavement crack, crack detection, fractional integral, valley edge, image segmentation