光学学报, 2017, 37 (8): 0810004, 网络出版: 2018-09-07   

航拍图像的路面裂缝识别 下载: 1306次

Pavement Crack Recognition Based on Aerial Image
作者单位
1 北京理工大学光电学院 光电成像技术与系统教育部重点实验室, 北京 100081
2 北京理工大学宇航学院, 北京 100081
摘要
针对航拍沥青路面图像识别的噪声和干扰问题,提出一种应用于航拍图像的路面裂缝识别算法。根据路面区域与路旁景观区域灰度级数分布不同,采用多方向拟合的区域生长方法联合HSV颜色空间阈值进行路面区域分割,提取包含完整裂缝信息的单通道路面;再通过改进的形态学滤波剔除面积较大的干扰区域,利用结合显著性分析的边缘检测算法识别路面的裂缝片段,实现复杂裂缝与路面纹理噪声的区分;自动筛选存在裂缝的图像,针对裂缝可疑区域,结合人眼辅助观察标记并计算其长度。结果表明,该算法可有效剔除图像中的噪声和干扰,较好地识别沥青路面的裂缝,裂缝宽度的识别精度能达到9.7 mm,分类识别准确率大于80.0%,长度测量准确率大于75.0%。
Abstract
Aim

ing at the problems of interference and noise in image recognition of aerial asphalt pavement, a pavement crack recognition algorithm applied to aerial image is put forward. According to the difference of gray level distribution of the surface area and the roadside landscape area, a method of regional growth based on multi-directional fitting and threshold segmentation in HSV color space for road region segmentation is proposed. The single channel pavement which contains integral crack information is extracted, the large area of interference is eliminated by the improved morphological filtering, and an edge detection algorithm based on saliency analysis to recognise the crack fragment of pavement is proposed, realizing the distinction between complex cracks and pavement texture noise. The images with crack are screened automatically and the crack length is marked and calculated combined with human eye assistance observation. The experimental results show that the proposed method can effectively remove the interference and noise in the image, and well identify asphalt pavement cracks. The precision of crack width is 9.7 mm. The classification accuracy is over 80.0%. The accuracy of length measurement is over 75.0%.

王博, 王霞, 陈飞, 贺云涛, 李文光, 刘莉. 航拍图像的路面裂缝识别[J]. 光学学报, 2017, 37(8): 0810004. Bo Wang, Xia Wang, Fei Chen, Yuntao He, Wenguang Li, Li Liu. Pavement Crack Recognition Based on Aerial Image[J]. Acta Optica Sinica, 2017, 37(8): 0810004.

本文已被 9 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!