Stereo-LiDAR Fusion by Semi-Global Matching With Discrete Disparity-Matching Cost and Semidensification

被引:0
作者
Yao, Yasuhiro [1 ]
Ishikawa, Ryoichi [1 ]
Oishi, Takeshi [1 ]
机构
[1] Univ Tokyo, Inst Ind Sci, Tokyo 1538505, Japan
关键词
Laser radar; Costs; Real-time systems; Cameras; Learning systems; Accuracy; Depth measurement; Training; Sensor fusion; Robot vision systems; Computer vision for automation; depth completion; range sensing; sensor fusion; stereo matching; DEPTH COMPLETION; PROPAGATION;
D O I
10.1109/LRA.2025.3552236
中图分类号
TP24 [机器人技术];
学科分类号
080202 ; 1405 ;
摘要
We present a real-time, non-learning depth estimation method that fuses Light Detection and Ranging (LiDAR) data with stereo camera input. Our approach comprises three key techniques: Semi-Global Matching (SGM) stereo with Discrete Disparity-matching Cost (DDC), semidensification of LiDAR disparity, and a consistency check that combines stereo images and LiDAR data. Each of these components is designed for parallelization on a GPU to realize real-time performance. When it was evaluated on the KITTI dataset, the proposed method achieved an error rate of 2.79%, outperforming the previous state-of-the-art real-time stereo-LiDAR fusion method, which had an error rate of 3.05%. Furthermore, we tested the proposed method in various scenarios, including different LiDAR point densities, varying weather conditions, and indoor environments, to demonstrate its high adaptability. We believe that the real-time and non-learning nature of our method makes it highly practical for applications in robotics and automation.
引用
收藏
页码:4548 / 4555
页数:8
相关论文
共 26 条
[1]  
Badino H., 2011, 2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT), P405, DOI 10.1109/3DIMPVT.2011.58
[2]   Fast approximate energy minimization via graph cuts [J].
Boykov, Y ;
Veksler, O ;
Zabih, R .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2001, 23 (11) :1222-1239
[3]   Noise-Aware Unsupervised Deep Lidar-Stereo Fusion [J].
Cheng, Xuelian ;
Zhong, Yiran ;
Dai, Yuchao ;
Ji, Pan ;
Li, Hongdong .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :6332-6341
[4]   Volumetric Propagation Network: Stereo-LiDAR Fusion for Long-Range Depth Estimation [J].
Choe, Jaesung ;
Joo, Kyungdon ;
Imtiaz, Tooba ;
Kweon, In So .
IEEE ROBOTICS AND AUTOMATION LETTERS, 2021, 6 (03) :4672-4679
[5]   Efficient belief propagation for early vision [J].
Felzenszwalb, Pedro F. ;
Huttenlocher, Daniel P. .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2006, 70 (01) :41-54
[6]   LiDAR-SGM: Semi-Global Matching on LiDAR Point Clouds and their Cost-based Fusion into Stereo Matching [J].
Forkel, Bianca ;
Wuensche, Hans-Joachim .
2023 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, ICRA, 2023, :2841-2847
[7]  
Geiger A, 2012, PROC CVPR IEEE, P3354, DOI 10.1109/CVPR.2012.6248074
[8]  
Guo XD, 2024, Arxiv, DOI arXiv:2312.00343
[9]   Embedded real-time stereo estimation via Semi-Global Matching on the GPU [J].
Hernandez-Juarez, D. ;
Chacon, A. ;
Espinosa, A. ;
Vazquez, D. ;
Moure, J. C. ;
Lopez, A. M. .
INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE 2016 (ICCS 2016), 2016, 80 :143-153
[10]  
Hirschmüller H, 2008, IEEE T PATTERN ANAL, V30, P328, DOI [10.1109/TPAMI.2007.1166, 10.1109/TPAMl.2007.1166]