•  
  •  
 

Abstract

Automatic detection of rural road pavement damage is a critical prerequisite for scientific maintenance. To address issues such as high false detection rates, missed detection, and the inability to quantify damage when using smartphones for pavement damage detection, this paper proposes a novel detection method. The proposed method involves using a smartphone to capture pavement images. A region of interest is first selected in the image, followed by weighted least-squares filtering, Canny edge detection, and Hough transform line detection to identify the pavement, minimizing environmental interference and reducing false detection rates. Perspective transformation is then applied to the pavement region to generate orthophotos, decreasing missed detection rates. Finally, the Mask-RCNN model is utilized to identify damage. Experimental results show that compared to the SSD detection model, the proposed method reduces the average false detection and missed detection rates for cracks, potholes, and repairs by 15.4% and 19.6%, respectively. In addition, the method can measure the length and width of cracks and the area of potholes and repairs, effectively meeting the practical requirements for rural road pavement damage detection.

Publication Date

5-11-2023

DOI

10.14048/j.issn.1671-2579.2023.02.009

First Page

51

Last Page

57

Submission Date

March 2025

Reference

[1]交通运输部公路科学研究院.公路技术状况评定标准:JTG 5210 —2018[S].北京:人民交通出版社股份有限公司,2018. Research Institute of Highway Ministry of Transport.Highway performance assessment standards[S]. Beijing: China Communications Press Co.,Ltd., 2018. [2] 张德津, 李清泉. 公路路面快速检测技术发展综述[J]. 测绘地理信息, 2015, 40(1): 1-8. ZHANG Dejin, LI Qingquan. A review of pavement high speed detection technology[J]. Journal of Geomatics, 2015, 40(1): 1-8. [3] 魏海斌, 武少威, 张启帆, 等. 基于图像处理的沥青路面裂缝识别算法研究[J]. 中外公路, 2020, 40(4): 73-78. WEI Haibin, WU Shaowei, ZHANG Qifan, et al. Research on crack recognition algorithm of asphalt pavement based on image processing[J]. Journal of China & Foreign Highway, 2020, 40(4): 73-78. [4] 王世芳, 车艳丽, 李楠, 等. 一种基于多尺度脊边缘的沥青路面裂缝检测算法[J]. 中国公路学报, 2017, 30(4): 32-41. WANG Shifang, CHE Yanli, LI Nan, et al. Asphalt pavement crack detection algorithm based on multi-scale ridges[J]. China Journal of Highway and Transport, 2017, 30(4): 32-41. [5] 李晋惠. 用图像处理的方法检测公路路面裂缝类病害[J]. 长安大学学报(自然科学版), 2004, 24(3): 24-29. LI Jinhui. Pavement crack diseases detecting by image processing algorithm[J]. Journal of Chang’an University (Natural Science Edition), 2004, 24(3): 24-29. [6] 李伟, 孙朝云, 呼延菊, 等. 基于路面3D数据的裂缝类型判断方法[J]. 中国公路学报, 2015, 28(11): 21-28. LI Wei, SUN (ChaoZhao)(Yun), HUYAN Ju, et al. Pavement crack type judgment method based on three-dimensional pavement data[J]. China Journal of Highway and Transport, 2015, 28(11): 21-28. [7] 李清泉, 邹勤, 张德津. 利用高精度三维测量技术进行路面破损检测[J]. 武汉大学学报(信息科学版), 2017, 42(11): 1549-1564. LI Qingquan, ZOU Qin, ZHANG Dejin. Road pavement defect detection using high precision 3D surveying technology[J]. Geomatics and Information Science of Wuhan University, 2017, 42(11): 1549-1564. [8] MERTZ C, VARADHARAJAN S, JOSE S, et al. City¬wide road distress monitoring with smartphone [C]//World Congress on Intelligent Transport Systems and ITS America Annual Meeting ,2014:115¬124. [9] MAEDA H, SEKIMOTO Y, SETO T, et al. Road damage detection and classification using deep neural networks with smartphone images[J]. Computer-Aided Civil and Infrastructure Engineering, 2018, 33(12): 1127-1141. [10] 代勤, 王延杰, 韩广良. 基于改进Hough变换和透视变换的透视图像矫正[J]. 液晶与显示, 2012, 27(4): 552-556. DAI Qin, WANG Yanjie, HAN Guangliang. Perspective image rectification based on improved Hough transformation and perspective transformation[J]. Chinese Journal of Liquid Crystals and Displays, 2012, 27(4): 552-556. [11] TANG J L, HUANG H N, SHI L C, et al. An improved perspective transform for image distortion correction[C]//2018 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW). May 19-21, 2018, Taichung, Taiwan, China. IEEE, 2018: 1-2. [12] 王颖, 李锋. 基于改进透视变换的结构光图像校正[J]. 计算机与数字工程, 2019, 47(5): 1240-1243, 1248. WANG Ying, LI Feng. Correction of structured light image based on improved perspective transform[J]. Computer & Digital Engineering, 2019, 47(5): 1240-1243, 1248. [13] 郭栋鸿, 谭丽, 温润. 基于MMSE的自适应灰度形态学钢轨边缘检测算法[J]. 云南大学学报(自然科学版), 2019, 41(6): 1144-1151. GUO Donghong, TAN Li, WEN Run. An adaptive gray morphological method for rail edge detection based on MMSE[J]. Journal of Yunnan University (Natural Sciences Edition), 2019, 41(6): [14] 罗朝阳, 张鹏超, 姚晋晋, 等. 一种基于形态学的边缘检测算法[J]. 计算机应用与软件, 2020, 37(2):177-181. LUO Zhaoyang, ZHANG Pengchao, YAO Jinjin, et al. An edge detection algorithm based on morphology[J]. Computer Applications and Software, 2020, 37(2):177-181. [15] RUSSAKOVSKY O, DENG J, SU H, et al. ImageNet large scale visual recognition challenge[J]. International Journal of Computer Vision, 2015, 115(3): 211-252. [16] LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: common objects in context[M]//Computer Vision – ECCV 2014. Cham: Springer International Publishing, 2014: 740-755. [17] HE K, GKIOXARI G, DOLL´AR P, et al.Mask RCNN[C]//Katsushi Ikeuchi, Gérard Medioni, Marcello Pelillo. IEEE International Conference on Computer Vision. Venice: In ICCV,2017:770‑783. [18] 李画, 李明晶, 李凯, 等. Mask RCNN模型在路面缺陷检测中的应用[J]. 科学技术创新, 2020(29): 131-132. LI Hua, LI Mingjing, LI Kai, et al. Application of mask RCNN model in pavement defect detection[J]. Scientific and Technological Innovation, 2020(29): 131-132. [19] 金勇俊, 李言俊, 张科. 一种透视变换图像金字塔匹配改进算法[J]. 计算机工程与应用, 2007, 43(24): 78-80, 165. JIN Yongjun, LI Yanjun, ZHANG Ke. Improved perspective transformation image pyramid registration method[J]. Computer Engineering and Applications, 2007, 43(24): 78-80, 165. [20] 张建伟, 雷霖. 基于透视投影的垂直视角投影算法研究[J]. 成都大学学报(自然科学版), 2017, 36(1): 47-50. ZHANG Jianwei, LEI Lin. Top-view projection algorithm research based on perspective projection[J]. Journal of Chengdu University (Natural Science Edition), 2017, 36(1): 47-50. [21] 李红云, 云利军, 高银. 基于边界限制加权最小二乘法滤波的雾天图像增强算法[J]. 中国激光, 2019, 46(3): 0309002. LI Hongyun, YUN Lijun, GAO Yin. Fog image enhancement algorithm based on boundary-limited weighted least squares filtering[J]. Chinese Journal of Lasers, 2019, 46(3): 0309002. [22] 王琦, 宋伟东, 王竞雪. 基于Hough变换的直线提取方法及改进[J]. 测绘与空间地理信息, 2019, 42(6): 214-217, 221. WANG Qi, SONG Weidong, WANG Jingxue. The line extraction method and improvement based on Hough transform[J]. Geomatics & Spatial Information Technology, 2019, 42(6): 214-217, 221.

Download

Share

COinS