首页 > 论文 > 中国激光 > 47卷 > 9期(pp:910002--1)

基于影像与激光数据的小交标检测与地理定位

Detection and Geo-localization of Small Traffic Signs Based on Images and Laser Data

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

交通标志等道路设施的空间位置信息是城市三维建模的基本要素之一,也是道路设施养护管理的必要内容。为此,提出一种基于移动测量数据的小型交通标志自动提取方案,基于改进的卷积神经网络SlimNet模型对全景影像上的小交标进行检测,提出一种基于深度图的目标三维空间地理定位方法,并采用以中心点为准的距离判断法提取目标的对角线。选取三类小型交通标志的实测数据对所提方法进行验证分析。实验结果表明,SlimNet模型的平均正确率相比经典的VGG16(Visual Geometry Group 16)模型有4.2个百分点的提升。采用提出的地理定位和矢量化方案,三类目标在实验区的召回率和精确率均达到86%以上,证明整体方案的有效可行性。该方法为城市多类目标的精确三维空间地理定位提供新思路。

Abstract

Information on the spatial location of road facilities such as traffic signs is one of the basic element of urban three-dimensional (3D) modeling, and it is also an essential part of road facility maintenance and management. To this end, an automatic extraction scheme for small traffic signs based on mobile measurement data is proposed herein. Based on the improved convolutional neural network SlimNet model, small cross-marks on panoramic images are detected, and a 3D target geolocation based on depth maps is proposed. A distance assessment method based on the center point is used to extract the diagonal of the target. Measured data of the three types of small traffic signs are selected to verify and analyze the proposed method. Experiment results show that the average accuracy of the SlimNet model is 4.2 percentage higher than that of the classic VGG16 (Visual Geometry Group 16) model. Using the proposed geographic positioning and vectorization scheme, the recall rate and accuracy rate of the three types of targets in the experimental area reached over 86%, proving the effective feasibility of the overall scheme. Furthermore, the proposed method provides a new idea for an accurate 3D spatial geolocalization of urban multi-class targets.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:O436

DOI:10.3788/CJL202047.0910002

所属栏目:遥感与传感器

基金项目:国家自然科学基金、中国博士后科学基金面上项目、国防科工局项目;

收稿日期:2020-03-25

修改稿日期:2020-04-30

网络出版日期:2020-09-01

作者单位    点击查看

刘力荣:首都师范大学资源环境与旅游学院, 北京 100048自然资源部国土卫星遥感应用中心, 北京 100048
唐新明:自然资源部国土卫星遥感应用中心, 北京 100048
赵文吉:首都师范大学资源环境与旅游学院, 北京 100048
高小明:自然资源部国土卫星遥感应用中心, 北京 100048
谢俊峰:自然资源部国土卫星遥感应用中心, 北京 100048

联系人作者:刘力荣(liulirong1125@163.com)

备注:国家自然科学基金、中国博士后科学基金面上项目、国防科工局项目;

【1】Yang B S, Fang L N, Li Q Q, et al. Automated extraction of road markings from mobile lidar point clouds [J]. Photogrammetric Engineering and Remote Sensing. 2012, 78(4): 331-338.

【2】Wang Z, Zhang L Q, Fang T, et al. A multiscale and hierarchical feature extraction method for terrestrial laser scanning point cloud classification [J]. IEEE Transactions on Geoscience and Remote Sensing. 2015, 53(5): 2409-2425.

【3】Burt A, Disney M, Calders K. Extracting individual trees from lidar point clouds using treeseg [J]. Methods in Ecology and Evolution. 2019, 10(3): 438-445.

【4】Yang M M, Wan Y C, Liu X L, et al. Rapid automatic location and extraction for manhole covers based on ground mobile mapping system [J]. Chinese Journal of Lasers. 2018, 45(8): 0804001.
杨蒙蒙, 万幼川, 刘先林, 等. 基于地面移动测量系统的井盖快速自动定位与提取方法的研究 [J]. 中国激光. 2018, 45(8): 0804001.

【5】Huang G, Liu X L. Automatic extraction and classification of road markings based on deep learning [J]. Chinese Journal of Lasers. 2019, 46(8): 0804002.
黄刚, 刘先林. 基于深度学习的道路标线自动提取与分类方法 [J]. 中国激光. 2019, 46(8): 0804002.

【6】Yu Y T, Li J, Guan H Y, et al. Automated extraction of urban road facilities using mobile laser scanning data [J]. IEEE Transactions on Intelligent Transportation Systems. 2015, 16(4): 2167-2181.

【7】Jung J, Che E Z, Olsen M J, et al. Efficient and robust lane marking extraction from mobile lidar point clouds [J]. ISPRS Journal of Photogrammetry and Remote Sensing. 2019, 147: 1-18.

【8】Ritter W. Traffic sign recognition in color image sequences . [C]∥Proceedings of the Intelligent Vehicles ''''92 Symposium, June 29-July 1, 1992, Detroit, MI, USA. New York: IEEE. 1992, 12-17.

【9】Gao X W, Podladchikova L, Shaposhnikov D, et al. Recognition of traffic signs based on their colour and shape features extracted using human vision models [J]. Journal of Visual Communication and Image Representation. 2006, 17(4): 675-685.

【10】Yang Y, Luo H L, Xu H R, et al. Towards real-time traffic sign detection and classification [J]. IEEE Transactions on Intelligent Transportation Systems. 2016, 17(7): 2022-2031.

【11】Hoferlin B, Zimmermann K. Towards reliable traffic sign recognition . [C]∥2009 IEEE Intelligent Vehicles Symposium, June 3-5, 2009, Xi''''an, China. New York: IEEE. 2009, 324-329.

【12】Fleyeh H. Road and traffic sign detection and recognition . [C]∥Proceedings of the 16th Mini-EURO Conference, September 13-16, 2005, Poznan, Poland. Uppsala: DiVA. 2005, 644-653.

【13】Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation . [C]∥2014 IEEE Conference on Computer Vision and Pattern Recognition, June 23-28, 2014, Columbus, OH, USA. New York: IEEE. 2014, 580-587.

【14】Ma Y J, Li X Y, Song X F. Trafficsign recognition based on improved deep convolution neural network [J]. Laser & Optoelectronics Progress. 2018, 55(12): 121009.
马永杰, 李雪燕, 宋晓凤. 基于改进深度卷积神经网络的交通标志识别 [J]. 激光与光电子学进展. 2018, 55(12): 121009.

【15】Ren S Q, He K M, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2017, 39(6): 1137-1149.

【16】Liu W, Anguelov D, Erhan D, et al. SSD: single shot MultiBox detector [M]. ∥Leibe B, Matas J, Sebe N, et al. Computer vision-ECCV 2016. Lecture notes in computer science. Cham: Springer. 2016, 9905: 21-37.

【17】Redmon J, Farhadi A. YOLO9000: better. -12-25)[2020-03-24] . https:∥arxiv. 2016, org/abs/1612: 08242.

【18】Redmon J. -04-08)[2020-03-24] . https:∥arxiv. 2018, org/abs/1804: 02767.

【19】Yang Z, Liu Y L, Liu L R, et al. Detecting small objects in urban settings using SlimNet model [J]. IEEE Transactions on Geoscience and Remote Sensing. 2019, 57(11): 8445-8457.

【20】Zhu Z, Liang D, Zhang S H, et al. Traffic-sign detection and classification in the wild . [C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30, 2016, Las Vegas, NV, USA. New York: IEEE. 2016, 2110-2118.

【21】Github. LabelImg[2020-03-24]. https:∥github.com/tzutalin/labelImg.[2020-03-24]. 0.

【22】Everingham M, van Gool L, Williams C K I, et al. The pascal visual object classes (VOC) challenge [J]. International Journal of Computer Vision. 2010, 88(2): 303-338.

【23】Lin T Y, Maire M, Belongie S, et al. Microsoft COCO: common objects in context [M]. ∥Fleet D, Pajdla T, Schiele B, et al. Computer vision - ECCV 2014. Lecture notes in computer science. Cham: Springer. 2014, 8693: 740-755.

引用该论文

Liu Lirong,Tang Xinming,Zhao Wenji,Gao Xiaoming,Xie Junfeng. Detection and Geo-localization of Small Traffic Signs Based on Images and Laser Data[J]. Chinese Journal of Lasers, 2020, 47(9): 0910002

刘力荣,唐新明,赵文吉,高小明,谢俊峰. 基于影像与激光数据的小交标检测与地理定位[J]. 中国激光, 2020, 47(9): 0910002

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF