基于激光雷达的道路不平度及可行驶区域检测

为了提高室外场景中车载激光雷达道路不平度信息检测的精度, 采用随机降采样和局部特征聚合的网络结构对道路环境信息进行提取分割。在分割过程中加入随机降采样的方法, 从而提高点云信息的计算效率, 为解决道路环境信息分割过程中关键特征丢失的问题, 加入局部特征聚合器来增加每个3维点云的接受域来保留几何细节。结果表明, 所提出的算法可以准确识别道路环境信息, 对于凸包、凹坑、道路可行驶区域的识别精度分别达到71.87%, 82.71%, 93.01%, 与传统卷积神经网络相比有显著提升。该研究可高效提取道路不平度及道路可行驶区域信息, 从而提高了车辆的主动安全性与平顺性。

Abstract

In order to improve the accuracy of road unevenness detection by vehicle-mounted lidar in outdoor scenes, the road environment information was extracted and segmented by the network structure of random down-sampling and local feature aggregation. Random sampling method was added in the segmentation process to improve the computing efficiency of high point cloud information. To solve the problem of the loss of key features in the segmentation process of road environment information, local feature aggregator was added to increase the acceptance domain of each 3-D point cloud to retain geometric details. The results show that the proposed algorithm can accurately identify the road environment information, and the recognition accuracy of convex hull, pit, and road able area reaches 71.87%, 82.71%, and 93.01% respectively, which is significantly improved compared with the traditional convolution neural network. This study can efficiently extract the information of road roughness and road able area. Thus, the active safety and ride comfort of the vehicle are improved.

参考文献

[1] KUMAR P, ANGELATS E. An automated road roughness detection from mobile laser scanning date［J］. Remote Sensing and Spatial Information Sciences, 2017, 42(1): 91-96.

[2] BALARINI J P, NESMACHNOW S. A C++ implementation of Otsu’s image segmentation method［J］. Image Processing on Line, 2016, 6(10): 155-164.

[3] KUMAR P, MCELHINNEY C P, LEWIS P, et al. Automated road markings extraction from mobile laser scanning data［J］. International Journal of Applied Earth Observation and Geoinformation, 2014, 32(1): 125-137.

[4] MICHEL A, KAPIT J, WITINSKI M F, et al. Open-path spectroscopic methane detection using a broadband monolithic distributed feedback-quantum cascade laser array［J］. Applied Optics, 2017, 56(11): 23-29.

[5] ZHU J K, LI L J, LIN X Zh. Research on the measurement field planning of LiDAR measurement system［J］.Laser Technology, 2021, 45(1): 99-104(in Chinese).

[6] WU J J, CHEN L, LI L, et al. Research on power line extraction and reconstruction in airborne LiDAR point cloud［J］. Laser Technology,2019,43(4): 64-69(in Chinese).

[7] YANG B Sh, LIU Y, DONG Zh, et al. 3D local feature BKD to extract road information from mobile laser scanning point clouds［J］. ISPRS Journal of Photogrammetry and Remote Sensing, 2017, 130(8): 329-343.

[8] YAN L, LIU H, TAN J X, et al. Scan line based road marking extraction from mobile LiDAR point clouds［J］. Sensors, 2016, 16(6): 6-21.

[9] MA L F, LI Y, LI J H, et al. Capsule-based networks for road marking extraction and classification from mobile LiDAR point clouds［J］. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(4): 1981-1995.

[10] GUAN H Y, YAN W Q, YU Y T, et al. Robust traffic-sign detection and classification using mobile LiDAR data with digital images［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, 11(5): 1715-1724.

[11] GARGOUM S, EL-BASYOUNY K, SABBAGH J, et al. Automated highway sign extraction using LiDAR data ［J］. Transportation Research Record, 2017, 2643(1): 1-8.

[12] HU Z Zh, LIU J H, H G, et al. Indoor robot localization based on wifi, LiDAR and map ［J］.Journal of Electronics and Information Technology, 2021,43(8): 2308-2316(in Chinese).

[13] MA L F, LI Y, LI J H, et al. Generation of horizontally curved driving lines in HD maps using mobile laser scanning point clouds［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019, 12(5): 1572-1586.

[14] LANDRIEU L, SIMONOVSKY M.Large-scale point cloud semantic segmentation with superpoint graphs［C］//2018 IEEE/CVF Confe-rence on Computer Vision and Pattern Recognition (CVPR). New York, USA: CVPR, 2018: 4558-4567.

[15] YAN Sh, ZHANG M J, FAN Y Ch, et al. Research progress of 3D reconstruction technology for large-scale outdoor image［J］. Chinese Journal of Image and Graphics, 2021, 26(6): 1429-1449.

[16] MA Y, ZHENG Y B, CHENG J Ch, et al. Real-time visualization method for estimating 3D highway sight distance using LiDAR data［J］. Journal of Transportation Engineering, 2019, A145(4): 1-14.

[17] YU L L, YU H Y, HE Z X, et al. Point cloud scene segmentation based on dual attention mechanism and multi-scale features［J］.Laser & Optoelectronics Progress, 2021, 58(24): 2428007(in Chin-ese).

[18] YU Z L, HU Y J. Initial road extraction from airborne LiDAR point cloud［J］. Laser & Optoelectronics Progress, 2021, 58(24): 2401003 (in Chinese).

[19] XIE B, ZHAO Y N, GAO L, et al. Small target semantic s egmen-tation enhancement method based on LiDAR point cloud ［J］. Laser Journal,2020,41(4): 18-23(in Chinese).

[20] HU Q Y, YANG B, XIE L H, et al. RandLA-net: Efficient semantic segmentation of large-scale point clouds［C］//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New York, USA: CVPR, 2020: 11108-11117.

闫德立, 高尚, 李韶华, 霍萌. 基于激光雷达的道路不平度及可行驶区域检测[J]. 激光技术, 2022, 46(5): 624. YAN Deli, GAO Shang, LI Shaohua, HUO Meng. Detection of road roughness and drivable area based on LiDAR[J]. Laser Technology, 2022, 46(5): 624.

基于激光雷达的道路不平度及可行驶区域检测

关于本站 Cookie 的使用提示

全站搜索

基于激光雷达的道路不平度及可行驶区域检测

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索