基于语义分割模型的三维沥青路面车辙异常分析方法

王艾迪, 郎洪, 丁朔, 等

doi:10.12141/j.issn.1000-565X.210778

华南理工大学学报(自然科学版) >

2023 , Vol. 51 >Issue 1: 134 - 144

DOI: https://doi.org/10.12141/j.issn.1000-565X.210778

交通运输工程

基于语义分割模型的三维沥青路面车辙异常分析方法

展开

^1.同济大学道路与交通工程教育部重点实验室, 上海 201804
^2.山西高速公路工程检测有限公司, 山西太原 030008

王艾迪（1997-），女，博士生，主要从事智能交通系统、交通安全研究。E-mail:aidiwang@tongji.edu.cn

收稿日期: 2021-12-06

网络出版日期: 2022-08-30

基金资助

国家自然科学基金资助项目(71871165)

收起

Rutting Abnormality Analysis Method for 3D Asphalt Pavement Surfaces Based on Semantic Segmentation Model

Expand

^1.Key Laboratory of Road and Traffic Engineering of the Ministry of Education, Tongji University, Shanghai 201804, China
^2.Shanxi Expressway Engineering Inspection Co. , Ltd. , Taiyuan 030008, Shanxi, China

王艾迪（1997-），女，博士生，主要从事智能交通系统、交通安全研究。E-mail:aidiwang@tongji.edu.cn

Received date: 2021-12-06

Online published: 2022-08-30

Supported by

the National Natural Science Foundation of China(71871165)

Fold

摘要

车辙深度是路面状况评价和道路养护的一个重要指标。现有车辙深度测量方法未考虑复杂路况下坑槽、松散、裂缝和桥梁接缝等对车辙计算的影响，其有效性和适用性受到了限制，测量结果的真实性也有待进一步验证。有鉴于此，文中提出了一种基于语义分割模型的沥青路面车辙异常检测与校正方法。采用三维线激光技术采集道路横断面高程数据，利用包络线算法提取车辙深度。对于最大车辙深度超过10 mm的横断面，搭建基于深度学习的语义分割框架，提出改进的DeepLabV3+网络对病害类型进行自动辨识和像素定位，并结合最大车辙深度高程点，设计基于拉格朗日插值的校正规则来对异常车辙进行校正。研究结果表明，改进的DeepLabV3+模型能较为准确地识别和定位造成车辙检测异常的路面病害，其对5种路面特征和病害的综合检测准确率达81.63%，在均交并比（MIoU）和大部分交并比（IoU）上的表现均优于U-Net、PSPNet、DeepLabV3+模型。现场验证结果表明，文中方法不仅能够自动分析车辙异常的原因，还能通过对异常车辙的校正排除其他病害的影响，从而较大程度地还原实际车辙深度水平。文中研究成果可为路面预防性养护提供科学数据支撑。

关键词： 三维线激光技术; 车辙异常检测; 语义分割模型; 车辙深度; 异常值校正

本文引用格式

王艾迪, 郎洪, 丁朔, 等 . 基于语义分割模型的三维沥青路面车辙异常分析方法[J]. 华南理工大学学报(自然科学版), 2023 , 51(1) : 134 -144 . DOI: 10.12141/j.issn.1000-565X.210778

Abstract

Rutting depth is an important indicator for the evaluation of pavement conditions and road maintenance. The existing rutting depth measurement method fails to consider the influence of potholes, raveling, cracks and bridge joints under complex road conditions, and its effectiveness and applicability are limited, and the authenticity of the measurement results remains to be further verified. In view of this, an abnormality detection and correction method based on semantic segmentation model is proposed. The road cross section elevation data is collected by three-dimensional line laser technology, and the rutting depth is extracted by the envelope algorithm. For cross-section of the maximum rut to more than 10 mm, this paper builds a semantic semantic division framework based on deep learning, proposes an improved DeepLabV3+ network to automatically identify and pixel positioning of the disease type, and designs a correction rule based on Lagrangian interpolation to correct the abnormal rut by combining the maximum rut depth elevation points. The results show that the improved DeepLabV3+ model can more accurately identify and locate pavement distress causing rutting abnormality, and its comprehensive detection accuracy of five pavement characteristics and distress reaches 81.63%. Its performance in Mean Intersection over Union (MIoU) and Intersection over Union (IoU) is better than that of U-Net, PSPNet, and DeepLabV3+ models. The field validation results show that the method in the paper can not only automatically analyze the causes of rutting abnormality, but also exclude the influence of other distress by correcting the abnormal rutting, so as to restore the actual rutting depth level to a greater extent. The research results in this paper can provide scientific data support for pavement preventive maintenance.

Key words： 3D line laser technology; rutting abnormality detection; semantic segmentation model; rutting depth; abnormal value correction

参考文献

1	交通运输部．2020年交通运输行业发展公报［EB/OL］．（2021-05-19）［2021-11-01］．．
2	黄晓明，张晓冰，邓学钧．沥青路面车辙形成规律环道试验研究［J］．东南大学学报（自然科学版），2000，30（5）：96-101．
2	HUANG Xiaoming， ZHANG Xiaobing， DENG Xuejun ．Asphalt pavement rutting prediction of high-grade highway［J］．Journal of Southeast University （Natural Science Edition），2000，30（5）：96-101．
3	WANG H ．Development of laser system to measure pavement rutting［D］．Tampa：South Florida University，2005．
4	戴建华．基于养护决策分析需求的路面技术状况检测［J］．中国公路，2020（15）：35-40．
4	DAI Jianhua ．Pavement technology condition detection based on maintenance decision analysis［J］．China Highway，2020（15）：35-40．
5	孟娜．基于激光扫描点云的数据处理技术研究［D］．济南：山东大学，2009．
6	ZHANG L， ZHANG Y J， CHEN B ．Improving the extracting precision of stripe center for structured light measurement［J］．Optik，2020，207：163816．
7	马建，赵祥模，贺拴海，等．路面检测技术综述［J］．交通运输工程学报，2017，17（5）：121-137．
7	MA Jian， ZHAO Xiangmo， HE Shuanhai，et al ．Review of pavement detection technology［J］．Journal of Traffic and Transportation Engineering，2017，17（5）：121-137．
8	李莉，孙立军，谭生光，等．用于路面车辙检测的线结构光图像处理流程［J］．同济大学学报（自然科学版），2013，41（5）：710-715．
8	LI Li， SUN Lijun， TAN Shengguang，et al ．Line-structured light image processing procedure for pavement rut detection［J］．Journal of Tongji University （Natural Science），2013，41（5）：710-715．
9	张德津，李清泉，何莉，等．一种新的激光车辙深度测量方法研究［J］. 光学学报，2013，33（1）：115-121．
9	ZHANG Dejin， LI Qingquan， HE Li，et al ．A new method for laser rut depth measurement［J］．Chinese Optics Letters，2013，33（1）：115-121．
10	FENG L. A Methodology for characterizing pavement rutting condition using emerging 3D line laser imaging technology［D］．Atlanta：Georgia Institute of Technology，2012．
11	KAGE T， MATSUSHIMA K ．Method of rut detection using lasers and in-vehicle stereo camera［C］∥Proceedings of IEEE 2015 International Conference on Intelligent Informatics and Biomedical Sciences．New York：IEEE，2015：48-53．
12	李中轶，罗文婷，李林，等．基于路面3D激光点云数据的车辙自动测量与横向定位［J］．传感技术学报，2019，32 （4）：637-642．
12	LI Zhongyi， LUO Wenting， LI Lin，et al ．Automatic rutting measurement and lateral positioning based on 3D laser point cloud data of road surface［J］．Journal of Sensing Technology，2019，32 （04）：637-642．
13	罗楠欣．基于路面高精三维图像的车辙识别与评价［D］．成都：西南交通大学，2015．
14	HUANG Y R， COPENHAVER T， HEMPEL P ．Texas department of transportation 3D transverse profiling system for high-speed rut measurement［J］．Journal of Infrastructure Systems，2013，19（2）：221-230．
15	LANG H， LU J， LOU Y X，et al ．Pavement cracking detection and classification based on 3D image using multiscale clustering model［J］．Journal of Computing in Civil Engineering，2020，34（5）：04020034．
16	公路路面技术状况自动化检测规程：［S］．
17	HUANG Y C C， HEMPEL P ．Texas department of transportation 3D profiling system for high-speed rut measurement［J］．Journal of Infrastructure Systems，2013，19：221-230．
18	SIMPSON A L ．Characterization of transverse profile［J］. Journal of the Transportation Research Board，1999，1655（1）：185-191．
19	公路技术状况评定标准：［S］．
20	CHEN L C， ZHU Y， PAPANDREOU G，et al ．Encoder-Decoder with Atrous separable convolution for semantic image segmentation［C］∥Proceedings of the European Conference on Computer Vision （ECCV）．［S.l.］：［s.n.］，2018：801-818．
21	ZHANG A， WANG K C P， AI C ．3D shadow modeling for detection of descended patterns on 3D pavement surface［J］．Journal of Computing in Civil Engineering，2017，31（4）：04017019/1-13．
22	LIN T Y， GOTAL P， GIRSHICK R ．Focal loss for dense object detection［J］．IEEE Transactions on Pattern Analysis & Machine Intelligence，2017，PP（99）：2999-3007．

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献