融合全景影像和车载点云的交通标志信息提取
Traffic Sign Information Extraction Based on Panoramic Images and MLS Point Clouds
DOI: 10.12677/GST.2021.92005, PDF,    科研立项经费支持
作者: 虞 敏, 李雨昊, 蒋腾平, 王 渊：武汉大学测绘遥感信息工程国家重点实验室，湖北 武汉；董 震：武汉大学测绘遥感信息工程国家重点实验室，湖北 武汉；武汉大学时空数据智能获取技术与应用教育部工程研究中心，湖北 武汉；城市空间信息工程北京市重点实验室，北京；杨必胜：武汉大学时空数据智能获取技术与应用教育部工程研究中心，湖北 武汉
关键词: 车载激光点云；全景影像；交通标志；提取；Vehicle-Mounted Laser Point Clouds； Panoramic Images； Traffic Sign； Extraction
摘要: 交通标志是城市道路交通设施的重要组成部分，对行人行车安全起着重要作用。本文融合激光点云和全景影像提出一种基于图像纹理、颜色、语义信息辅助的交通标志提取方法。本文方法在多个城市场景进行了定性与定量分析，实验结果表明本文方法能适应城市不同场景，点云标志平均提取正确率达97.9%，提取结果可以为城市交通标志规划验收、监测维护以及自动驾驶等领域提供科学辅助方案。
Abstract: Traffic sign is a significant part of road traffic facilities in city scene and plays an important role in pedestrian and traffic safety. In this paper, by fusing laser point clouds and panoramic images, we propose a method to extract traffic signs in point clouds by using texture, color and semantics of images. The method in this paper has been analyzed qualitatively and quantitatively in several urban scenes. The experimental results show that the method in this paper can adapt to different urban scenes, and the average extraction accuracy of signs reaches 97.9%. The extraction results can provide a scientific auxiliary scheme for city traffic sign planning acceptance, monitoring and maintenance, as well as the fields of automatic driving.
文章引用：虞敏, 李雨昊, 蒋腾平, 王渊, 董震, 杨必胜. 融合全景影像和车载点云的交通标志信息提取[J]. 测绘科学技术, 2021, 9(2): 41-51. https://doi.org/10.12677/GST.2021.92005

参考文献

[1] 沙莎, 肖学钢. 一种多通道融合的交通标志检测方法[J]. 计算机工程, 2009, 35(6): 202-204.
[2] Ellahyani, A., El Ansari, M. and El Jaafari, I. (2016) Traffic Sign Detection and Recognition Based on Random Forests. Applied Soft Computing, 46, 805-815. [Google Scholar] [CrossRef] 
[3] Zaklouta, F., Stanciulescu, B. and Hamdoun, O. (2011) Traffic Sign Classification Using K-d Trees and Random Forests. Proceedings of the International Joint Conference on Neural Networks, San Jose, 31 July-5 August 2011, 2151- 2155. [Google Scholar] [CrossRef] 
[4] Maldonado-Bascón, S., Lafuente-Arroyo, S., Gil-Jimenez, P., Gómez-Moreno, H. and López-Ferreras, F. (2007) Road- Sign Detection and Recognition Based on Support Vector Machines. IEEE Transactions on Intelligent Transportation Systems, 8, 264-278. [Google Scholar] [CrossRef] 
[5] Xie, B.Q. and Weng, X.X. (2019) Real-Time Embedded Traffic Sign Recognition Using Efficient Convolutional Neural Network. IEEE Access, 7, 53330-53346. [Google Scholar] [CrossRef] 
[6] Zhang, C., Yue, X., Wang, R., Li, N. and Ding, Y. (2020) Study on Traffic Sign Recognition by Optimized LeNet-5 Algorithm. International Journal of Pattern Recognition and Artificial Intelligence, 34, Article ID: 2055003. [Google Scholar] [CrossRef] 
[7] Chen, G. and Deng, Y. (2019) Multi-Scale CapsNet: A Novel Traffic Sign Recognition Method. Frontiers in Signal Processing, 3, 93. [Google Scholar] [CrossRef] 
[8] Zhang, J., Xie, Z., Sun, J., Zou, X. and Wang, J. (2020) A Cascaded R-CNN with Multiscale Attention and Imbalanced Samples for Traffic Sign Detection. IEEE Access, 8, 29742-29754. [Google Scholar] [CrossRef] 
[9] Zhang, J.M., et al. (2019) Lightweight Deep Network for Traffic Sign Classification. Annals of Telecommunications, 75, 1-11.
[10] Gudigar, A., Chokkadi, S. and Raghavendra, U. (2016) A Review on Automatic Detection and Recognition of Traffic Sign. Multimedia Tools and Applications, 75, 333-364. [Google Scholar] [CrossRef] 
[11] Nandi, D., Saif, A.F.M., Paul, P., Zubair, K.M. and Shubho, S.A. (2018) Traffic Sign Detection Based on Colour Segmentation of Obscure Image Candidates: A Compre-hensive Study. International Journal of Modern Education and Computer Science, 10, 35-46. [Google Scholar] [CrossRef] 
[12] Soilan, M., Riveiro, B., Martinez-Sanchez, J., et al. (2016) Traffic Sign Detection in MLS Acquired Point Clouds for Geometric and Image-Based Semantic Inventory. Isprs Journal of Photogrammetry & Remote Sensing, 114, 92-101. [Google Scholar] [CrossRef] 
[13] Balali, V., Jahangiri, A. and Machiani, S.G. (2017) Mul-ti-Class US Traffic Signs 3D Recognition and Localization via Image-Based Point Cloud Model Using Color Candidate Extraction and Texture-Based Recognition. Advanced Engineering Informatics, 32, 263-274. [Google Scholar] [CrossRef] 
[14] 杨凯, 刘如飞, 崔立军, 等. 全景影像中道路交通标志的自动识别[J]. 遥感信息, 2020, 35(4): 56-61.
[15] 翁升霞, 陈一平, 等. 基于移动激光点云的交通标志牌特征提取[J]. 厦门大学学报(自然科学版), 2016, 55(4): 580-585.
[16] 吴爽. 基于激光扫描点云的交通标志牌可见性评估研究[D]: [硕士学位论文]. 厦门: 厦门大学, 2017.
[17] 刘力荣, 唐新明, 赵文吉, 等. 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): 318-326.
[18] Joseph, R. and Ali, F. (2018) YOLOv3: An Incremental Im-provement. http://arxiv.org/abs/1804.02767
[19] 中华人民共和国公安部, 中华人民共和国住房和城乡建设部. GB/T 51038-2015, 城市道路交通标志和标线设置规范[S]. 北京: 中国计划出版社, 2015.

为你推荐