基于历史信息的路面表观损坏图像识别
CSTR:
作者:
作者单位:

1.同济大学 道路与交通工程教育部重点实验室,上海 201804;2.中交公路规划设计院有限公司,北京 100010

作者简介:

徐婷怡(1989—),女,博士生,主要研究方向为道路工程、交通基础设施管理。 E-mail:xutingyi@tongji.edu.cn

通讯作者:

陈 长(1977—),男,副教授,博士生导师,工学博士,主要研究方向为道路工程、路面检测、道路养护、

中图分类号:

TP181

基金项目:

河北省省级科技计划(20310802D)


Pavement Distress Detection Based on Historical Information
Author:
Affiliation:

1.Key Laboratory of Road and Traffic Engineering of the Ministry of Education, Tongji University, Shanghai 201804, China;2.China Communications Construction Corporation Highway Consultants Co., Ltd., Beijing 100010, China

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [19]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    在路面表观损坏图像识别方法中,为了解决现有方法准确度与速度不高的问题,利用历史检测结果这一历史信息,提出一种基于历史信息的路面表观损坏图像识别方法。首先,搭建了面向历史信息应用的算法框架,引入利用历史信息创建损坏识别的初始约束条件的机制。其次,训练VGG-16网络用于提取损坏特征。最后,利用历史信息建立初始种群以及设计特征参数,从而改进遗传算法。实验结果表明,该方法相较不运用历史信息的识别方法,能在不降低识别准确度的前提下显著提升识别速度,最快可较不运用历史信息的算法提升141.71倍速度。

    Abstract:

    In order to solve the problem that the accuracy and speed of the existing methods are not high in recognition of pavement distress image, a recognition method of pavement distress image based on historical information is proposed by using historical detection results. First, an algorithm framework for the application of historical information is built, and the mechanism of using historical information to create initial constraints for distress detection is introduced. Next, the VGG-16 network is trained to extract damage features. Finally, the initial population is established, and the feature parameters are designed by using historical information to improve the genetic algorithm. The experimental results show that this method can significantly improve the recognition speed without reducing the recognition accuracy compared with the recognition method without using historical information, and the fastest speed can be 141.71 times higher than the algorithm without historical information.

    参考文献
    [1] LI G, HE Y A. Novel image detection and classification for pavement crack under non-uniform illumination[J]. Acta Photonica Sinica, 2010, 39(8):1405. DOI: 10.3788/gzxb20103908.1405.
    [2] 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. DOI: 10.3321/j.issn:1671-8879.2004.03.007.
    [3] 夏德深, 傅德胜. 现代图像处理技术与应用[M]. 南京: 东南大学出版社, 1997.
    [4] ZHOU J, HUANG P S, CHIANG F P. Wavelet-aided pavement distress image processing[J]. Proceedings of SPIE - The International Society for Optical Engineering, 2003, 5207(2): 728. DOI: 10.1117/12.509670.
    [5] DO M N, VETTERLI M. The finite ridgelet transform for image representation [J]. IEEE Transactions on Image Processing, 2003,12(1): 16.
    [6] ZHANG Lei, YANG Fan, ZHANG Daniel, et al. Road crack detection using deep convolutional neural network[C]// IEEE International Conference on Image Processing (ICIP 2016). Piscataway: IEEE, 2016:3708-3712.
    [7] 李楠. 基于深度学习框架Caffe的路面裂缝识别研究[J]. 工程技术研究, 2017(3): 20. DOI:10.3969/j.issn.1671-3818.2017.03.009.
    [8] 车艳丽. 基于深度学习的路面裂缝分类与识别技术研究与实现[D]. 西安: 长安大学, 2018.
    [9] 袁亚超. 基于深度学习的路面裂缝检查及全面质量管理方法研究[D]. 重庆: 重庆大学, 2017.
    [10] 李伟. 基于深度卷积网络的路面裂缝分割方法[C]//2019世界交通运输大会论文集(下). 北京: 中国公路学会, 2019: 346-356.
    [11] 张宁. 基于Faster R-CNN的公路路面病害检测算法的研究[D]. 南昌: 华东交通大学, 2019.
    [12] 孙朝云,裴莉莉,李伟,等.基于改进Faster R-CNN的路面灌封裂缝检测方法[J].华南理工大学学报(自然科学版), 2020, 48(2): 84. DOI: CNKI:SUN:HNLG.0.2020-02-011.
    [13] DU Yuchuan, PAN Ning, XU Zihao, et al. Pavement distress detection and classification based on YOLO network[J]. International Journal of Pavement Engineering, 2020(1): 1. DOI: 10.1080/10298436.2020.1714047.
    [14] LI W, PIECH V, GILBERT C D. Perceptual learning and top-down influences in primary visual cortex[J]. Nature Neuroscience, 2004, 7(6):651. DOI: 10.1038/nn1255.
    [15] LAN R, ZHOU Y, LIU Z, et al. Prior knowledge-based probabilistic collaborative representation for visual recognition[J]. IEEE Transactions on Cybernetics, 2018, 50(4): 1. DOI: 10.1109/TCYB.2018.2880290.
    [16] GAO Q, WANG X, XIE G. License plate recognition based on prior knowledge[C]//Proceedings of the IEEE International Conference on Automation and Logistics. Piscataway: IEEE, 2007: 2964-2968.
    [17] WANG Y, MAO L, YU M A, et al. Automatic recognition of parathyroid nodules in ultrasound images based on fused prior pathological knowledge features[J]. IEEE Access, 2021(9): 69626. DOI:10.1109/ACCESS.2021.3075226.
    [18] DING X, LUO Y, LI Q, et al. Prior knowledge-based deep learning method for indoor object recognition and application[J]. Systems Science & Control Engineering, 2018, 6(1): 249. DOI: 10.1080/21642583.2018.1482477.
    [19] MANUEL L A, RUBEN G O, NICOLAI P. Appearance-invariant place recognition by discriminatively training a convolutional neural network[J]. Pattern Recognition Letters, 2017, 92:89. DOI: 10.1016/j.patrec.2017.04.017
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

徐婷怡,姜振天,梁远路,陈长,孙立军.基于历史信息的路面表观损坏图像识别[J].同济大学学报(自然科学版),2022,50(4):562~570

复制
分享
文章指标
  • 点击次数:189
  • 下载次数: 601
  • HTML阅读次数: 90
  • 引用次数: 0
历史
  • 收稿日期:2021-05-27
  • 在线发布日期: 2022-05-06
文章二维码