Curb Detection and Mapping via Robust Iterative Gaussian Process Regression
WANG Di1, CHEN Si2, MA Zhen-ni1, SHI Jia-jia1, ZHANG Fu-chun1
1. School of Physics and Electronic Information, Yan'an University, Yan'an, Shaanxi 716000, China; 2. China Electronics Technology Group Corporation, Beijing 100086, China
Curb Detection and Mapping via Robust Iterative Gaussian Process Regression
WANG Di1, CHEN Si2, MA Zhen-ni1, SHI Jia-jia1, ZHANG Fu-chun1
1. School of Physics and Electronic Information, Yan'an University, Yan'an, Shaanxi 716000, China; 2. China Electronics Technology Group Corporation, Beijing 100086, China
摘要Curb detection and mapping are of great importance to ensure the safety and efficiency of intelligent vehicles. However, it remains challenging because shape estimation under noise and outliers is not well addressed in real traffic scenarios. In this paper, an efficient curb detection and mapping algorithm is proposed to achieve an accurate representation of curb shape. More specifically, an iterative Gaussian process regression (iGPR) is introduced, where each candidate point is verified multiple times. Then iGPR is employed in shape estimation of both road profile and curb, which serves as the backbone unit in curb candidate detection. During this process, the input 3D point cloud is segmented into road and obstacles, and potential curb points are selected by evaluating physically interpretable curb features. Finally, the proposed iGPR is validated and tested on two large-scale, complex urban datasets under real traffic scenarios. Experimental results show that the proposed iGPR achieves better performance than several state-of-the-art algorithms.
Abstract：Curb detection and mapping are of great importance to ensure the safety and efficiency of intelligent vehicles. However, it remains challenging because shape estimation under noise and outliers is not well addressed in real traffic scenarios. In this paper, an efficient curb detection and mapping algorithm is proposed to achieve an accurate representation of curb shape. More specifically, an iterative Gaussian process regression (iGPR) is introduced, where each candidate point is verified multiple times. Then iGPR is employed in shape estimation of both road profile and curb, which serves as the backbone unit in curb candidate detection. During this process, the input 3D point cloud is segmented into road and obstacles, and potential curb points are selected by evaluating physically interpretable curb features. Finally, the proposed iGPR is validated and tested on two large-scale, complex urban datasets under real traffic scenarios. Experimental results show that the proposed iGPR achieves better performance than several state-of-the-art algorithms.
WANG Di, CHEN Si, MA Zhen-ni, SHI Jia-jia, ZHANG Fu-chun. Curb Detection and Mapping via Robust Iterative Gaussian Process Regression[J]. Journal of Highway and Transportation Research and Development, 2024, 18(2): 26-33.
WANG Di, CHEN Si, MA Zhen-ni, SHI Jia-jia, ZHANG Fu-chun. Curb Detection and Mapping via Robust Iterative Gaussian Process Regression. Journal of Highway and Transportation Research and Development, 2024, 18(2): 26-33.
[1] BAI D, CAO T, GUO J, et al. How to Build a Curb Dataset with Lidar Data for Autonomous Driving[C]//2022 International Conference on Robotics and Automation (ICRA). Philadelphia, USA:IEEE, 2022:2576-2582. [2] ROMERO L M, GUERRERO J A, ROMERO G. Road Curb Detection:a Historical Survey[J]. Sensors, 2021, 21(21):6952. [3] GUO D, YANG G, QI B, et al. Curb Detection and Compensation Method for Autonomous Driving via a 3-D-LiDAR Sensor[J]. IEEE Sensors Journal, 2022, 22(20):19500-19512. [4] JUNG Y, JEON M, KIM C, et al. Uncertainty-aware Fast Curb Detection Using Convolutional Networks in Point Clouds[C]//2021 IEEE International Conference on Robotics and Automation (ICRA). Xi'an, China:IEEE, 2021:12882-12888. [5] ZOU M, KAGEYAMA Y. Road Curb Detection Based on a Deep Learning Framework[C]//2023 IEEE 13th Annual Computing and Communication Workshop and Conference (CCWC). Las Vegas, USA:IEEE, 2023:0259-0262. [6] ZHANG Y, WANG J, WANG X, et al. Road-Segmentation-ased Curb Detection Method for Self-Driving via a 3D-lidar Sensor[J]. IEEE Transactions on Intelligent Transportation Systems, 2018, 19(12):3981-3991. [7] HATA A Y, OSORIO F S, WOLF D F. Robust Curb Detection and Vehicle Localization in Urban Environments[C]//2014 IEEE Intelligent Vehicles Symposium Proceedings. Ypsilanti, USA:IEEE, 2014:1257-1262. [8] GALLAZZI B, CUDRANO P, FROSI M, et al. Clothoidal Mapping of Road Line Markings for Autonomous Driving High-Definition Maps[C]//2022 IEEE Intelligent Vehicles Symposium (IV). Aachen, Germany:IEEE, 2022:1631-1638. [9] XIONG H, ZHU T, LIU Y, et al. Road-Model-Based Road Boundary Extraction for High Definition Map via LIDAR[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(10):18456-18465. [10] WANG D, XUE J, CUI D, et al. A Robust Submap-Based Road Shape Estimation via Iterative Gaussian Process Regression[C]//2017 IEEE Intelligent Vehicles Symposium (IV). Redondo Beach, USA:IEEE, 2017:1776-1781. [11] WANG Y, WANG Z, HAN K, et al. Gaussian Process-Based Personalized Adaptive Cruise Control[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(11):21178-21189. [12] CHEN T, DAI B, LIU D, et al. Velodyne-based Curb Detection up to 50 Meters Away[C]//2015 IEEE Intelligent Vehicles Symposium (IV). Seoul, South Korea:IEEE, 2015:241-248. [13] TAO Z, XUE J, WANG D, et al. An Adaptive Invariant EKF for Map-aided Localization Using 3D Point Cloud[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(12):24057-24070.
2024, Vol. 18 
