GeeNet：用于自动驾驶汽车地面高程估计的稳健快速点云补全

刘沥文; 杨卫东; 费奔

doi:10.1631/FITEE.2300388

Your Location：

Home >

Browse articles >

GeeNet：用于自动驾驶汽车地面高程估计的稳健快速点云补全

常规文章 | Updated：2024-07-28

- GeeNet：用于自动驾驶汽车地面高程估计的稳健快速点云补全
- GeeNet: robust and fast point cloud completion for ground elevation estimation towards autonomous vehicles
- 信息与电子工程前沿（英文） 2024年25卷第7期页码：938-950
- Affiliations：
  
  1.Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University, Shanghai 200433, China
  2.Zhuhai Fudan Innovation Institute, Zhuhai 519000, China
- Author bio：
  
  E-mail: 21210240022@m.fudan.edu.cn
  ‡Corresponding author
- Funds：
  
  National Natural Science Foundation of China(U2033209)
- DOI：10.1631/FITEE.2300388
  中图分类号： TP391
- 收稿：2023-05-31，
  
  录用：2023-07-24，
  
  纸质出版：2024-07-0
- Accepted：
Scan QR Code
刘沥文, 杨卫东, 费奔. GeeNet：用于自动驾驶汽车地面高程估计的稳健快速点云补全[J]. 信息与电子工程前沿（英文）, 2024,25(7):938-950.

Liwen LIU, Weidong YANG, Ben FEI. GeeNet: robust and fast point cloud completion for ground elevation estimation towards autonomous vehicles[J]. Frontiers of Information Technology & Electronic Engineering, 2024, 25(7): 938-950.
刘沥文, 杨卫东, 费奔. GeeNet：用于自动驾驶汽车地面高程估计的稳健快速点云补全[J]. 信息与电子工程前沿（英文）, 2024,25(7):938-950. DOI： 10.1631/FITEE.2300388.

Liwen LIU, Weidong YANG, Ben FEI. GeeNet: robust and fast point cloud completion for ground elevation estimation towards autonomous vehicles[J]. Frontiers of Information Technology & Electronic Engineering, 2024, 25(7): 938-950. DOI： 10.1631/FITEE.2300388.

摘要

地面高程估计对于无人驾驶汽车和智能机器人的许多应用至关重要，包括三维物体检测、导航空间检测、用于定位的点云匹配和用于建图的配准。然而，现有大多数工作将地面视为没有高度信息的平面，导致这些应用中出现不准确的操作。本文提出一种端到端的轻量级方法GeeNet，可几乎实时地补全地面，同时在基于网格的表示中估计地面高程。GeeNet利用二维/三维卷积的混合来保留轻量级架构，以回归网格每个单元格的地面高程信息。GeeNet首次实现了语义场景补全的地面高程估计。使用SemanticKITTI和SemanticPOSS数据集对GeeNet进行验证，展示了其在地面高程估计和点云语义场景补全方面的定性和定量性能。此外，其跨数据集泛化能力也得到实验证明。相比文献方法，GeeNet取得更好性能，并以0.88 ms运行时实现地面高程估计和地面补全。

Abstract

Ground elevation estimation is vital for numerous applications in autonomous vehicles and intelligent robotics including three-dimensional object detection

navigable space detection

point cloud matching for localization

and registration for mapping. However

most works regard the ground as a plane without height information

which causes inaccurate manipulation in these applications. In this work

we propose GeeNet

a novel end-to-end

lightweight method that completes the ground in nearly real time and simultaneously estimates the ground elevation in a grid-based representation. GeeNet leverages the mixing of two- and three-dimensional convolutions to preserve a lightweight architecture to regress ground elevation information for each cell of the grid. For the first time

GeeNet has fulfilled ground elevation estimation from semantic scene completion. We use the SemanticKITTI and SemanticPOSS datasets to validate the proposed GeeNet

demonstrating the qualitative and quantitative performances of GeeNet on ground elevation estimation and semantic scene completion of the point cloud. Moreover

the cross-dataset generalization capability of GeeNet is experimentally proven. GeeNet achieves state-of-the-art performance in terms of point cloud completion and ground elevation estimation

with a runtime of 0.88 ms.

关键词

Keywords

references

Behley J , Garbade M , Milioto A , et al. , 2019 . SemanticKITTI: a dataset for semantic scene understanding of LiDAR sequences . Proc IEEE/CVF Int Conf on Computer Vision , p. 9296 - 9306 . https://doi.org/10.1109/ICCV.2019.00939 https://doi.org/10.1109/ICCV.2019.00939

Boulch A , le Saux B , Audebert N , 2017 . Unstructured point cloud semantic labeling using deep segmentation networks . Proc Workshop on 3D Object Retrieval , p. 17 - 24 . https://doi.org/10.2312/3dor.20171047 https://doi.org/10.2312/3dor.20171047

Byun J , Na KI , Seo BS , et al. , 2015 . Drivable road detection with 3D point clouds based on the MRF for intelligent vehicle . In: Mejias L , Corke P , Roberts J (Eds.), Field and Service Robotics . Springer , Cham, Switzerland , p. 49 - 60 . https://doi.org/10.1007/978-3-319-07488-7_4 https://doi.org/10.1007/978-3-319-07488-7_4

Chen LC , Papandreou G , Kokkinos I , et al. , 2017 . DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs . IEEE Trans Patt Anal Mach Intell , 40 ( 4 ): 834 - 848 . https://doi.org/10.1109/TPAMI.2017.2699184 https://doi.org/10.1109/TPAMI.2017.2699184

Chen YD , Hao CY , Wu W , et al. , 2016 . Robust dense reconstruction by range merging based on confidence estimation . Sci China Inform Sci , 59 ( 9 ): 092103 . https://doi.org/10.1007/s11432-015-0957-4 https://doi.org/10.1007/s11432-015-0957-4

Cheng R , Agia C , Ren Y , et al. , 2021 . S3CNet: a sparse semantic scene completion network for LiDAR point clouds . Proc Conf on Robot Learning , p. 2148 - 2161 .

Choy C , Gwak J , Savarese S , 2019 . 4D spatio-temporal ConvNets: Minkowski convolutional neural networks . Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition , p. 3070 - 3079 . https://doi.org/10.1109/CVPR.2019.00319 https://doi.org/10.1109/CVPR.2019.00319

Garbade M , Chen YT , Sawatzky J , et al. , 2019 . Two stream 3D semantic scene completion . Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition Workshops , p. 416 - 425 . https://doi.org/10.1109/CVPRW.2019.00055 https://doi.org/10.1109/CVPRW.2019.00055

Graham B , Engelcke M , van der Maaten L , 2018 . 3D semantic segmentation with submanifold sparse convolutional networks . Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition , p. 9224 - 9232 . https://doi.org/10.1109/CVPR.2018.00961 https://doi.org/10.1109/CVPR.2018.00961

Himmelsbach M , Hundelshausen FV , Wuensche HJ , 2010 . Fast segmentation of 3D point clouds for ground vehicles . IEEE Intelligent Vehicles Symp , p. 560 - 565 . https://doi.org/10.1109/IVS.2010.5548059 https://doi.org/10.1109/IVS.2010.5548059

Landrieu L , Boussaha M , 2019 . Point cloud oversegmentation with graph-structured deep metric learning . Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition , p. 7432 - 7491 . https://doi.org/10.1109/CVPR.2019.00762 https://doi.org/10.1109/CVPR.2019.00762

Landrieu L , Simonovsky M , 2018 . Large-scale point cloud semantic segmentation with superpoint graphs . Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition , p. 4558 - 4567 . https://doi.org/10.1109/CVPR.2018.00479 https://doi.org/10.1109/CVPR.2018.00479

Lang AH , Vora S , Caesar H , et al. , 2019 . PointPillars: fast encoders for object detection from point clouds . Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition , p. 12689 - 12697 . https://doi.org/10.1109/CVPR.2019.01298 https://doi.org/10.1109/CVPR.2019.01298

Lawin FJ , Danelljan M , Tosteberg P , et al. , 2017 . Deep projective 3D semantic segmentation . Proc 17 th Int Conf on Computer Analysis of Images and Patterns , p. 95 - 107 . https://doi.org/10.1007/978-3-319-64689-3_8 https://doi.org/10.1007/978-3-319-64689-3_8

Leonard J , How J , Teller S , et al. , 2008 . A perception-driven autonomous urban vehicle . J Field Robot , 25 ( 10 ): 727 - 774 . https://doi.org/10.1002/rob.20262 https://doi.org/10.1002/rob.20262

Liu BS , Chen XM , Han YH , et al. , 2019 . Accelerating DNN-based 3D point cloud processing for mobile computing . Sci China Inform Sci , 62 ( 11 ): 212206 . https://doi.org/10.1007/s11432-019-9932-3 https://doi.org/10.1007/s11432-019-9932-3

Liu KQ , Wang WG , Tharmarasa R , et al. , 2019 . Ground surface filtering of 3D point clouds based on hybrid regression technique . IEEE Access , 7 : 23270 - 23284 . https://doi.org/10.1109/ACCESS.2019.2899674 https://doi.org/10.1109/ACCESS.2019.2899674

Liu S , Hu Y , Zeng YM , et al. , 2018 . See and think: disentangling semantic scene completion . Proc 32 nd Int Conf on Neural Information Processing Systems , p. 261 - 272 .

Liu Y , 2016 . Robust segmentation of raw point clouds into consistent surfaces . Sci China Technol Sci , 59 ( 8 ): 1156 - 1166 . https://doi.org/10.1007/s11431-016-6072-8 https://doi.org/10.1007/s11431-016-6072-8

Narksri P , Takeuchi E , Ninomiya Y , et al. , 2018 . A slope-robust cascaded ground segmentation in 3D point cloud for autonomous vehicles . Proc 21 st Int Conf on Intelligent Transportation Systems , p. 497 - 504 . https://doi.org/10.1109/ITSC.2018.8569534 https://doi.org/10.1109/ITSC.2018.8569534

Paigwar A , Erkent Ö , Sierra-Gonzalez D , et al. , 2020 . GndNet: fast ground plane estimation and point cloud segmentation for autonomous vehicles . IEEE/RSJ Int Conf on Intelligent Robots and Systems , p. 2150 - 2156 . https://doi.org/10.1109/IROS45743.2020.9340979 https://doi.org/10.1109/IROS45743.2020.9340979

Pan YC , Gao B , Mei JL , et al. , 2020 . SemanticPOSS: a point cloud dataset with large quantity of dynamic instances . IEEE Intelligent Vehicles Symp , p. 687 - 693 . https://doi.org/10.1109/IV47402.2020.9304596 https://doi.org/10.1109/IV47402.2020.9304596

Qi CR , Su H , Mo KC , et al. , 2017a . PointNet: deep learning on point sets for 3D classification and segmentation . Proc IEEE Conf on Computer Vision and Pattern Recognition , p. 77 - 85 . https://doi.org/10.1109/CVPR.2017.16 https://doi.org/10.1109/CVPR.2017.16

Qi CR , Yi L , Su H , et al. , 2017b . PointNet++: deep hierarchical feature learning on point sets in a metric space . Proc 31 st Int Conf on Neural Information Processing Systems , p. 5105 - 5114 .

Ren DY , Wu ZY , Li JW , et al. , 2022 . Point attention network for point cloud semantic segmentation . Sci China Inform Sci , 65 ( 9 ): 192104 . https://doi.org/10.1007/s11432-021-3387-7 https://doi.org/10.1007/s11432-021-3387-7

Riegler G , Ulusoy AO , Geiger A , 2017 . OctNet: learning deep 3D representations at high resolutions . Proc IEEE Conf on Computer Vision and Pattern Recognition , p. 6620 - 6629 . https://doi.org/10.1109/CVPR.2017.701 https://doi.org/10.1109/CVPR.2017.701

Rist CB , Emmerichs D , Enzweiler M , et al. , 2022 . Semantic scene completion using local deep implicit functions on LiDAR data . IEEE Trans Patt Anal Mach Intell , 44 ( 10 ): 7205 - 7218 . https://doi.org/10.1109/TPAMI.2021.3095302 https://doi.org/10.1109/TPAMI.2021.3095302

Roldão L , de Charette R , Verroust-Blondet A , 2020 . LMSCNet: lightweight multiscale 3D semantic completion . Int Conf on 3D Vision , p. 111 - 119 . https://doi.org/10.1109/3DV50981.2020.00021 https://doi.org/10.1109/3DV50981.2020.00021

Rummelhard L , Nègre A , Laugier C , 2015 . Conditional Monte Carlo dense occupancy tracker . IEEE 18 th Int Conf on Intelligent Transportation Systems , p. 2485 - 2490 . https://doi.org/10.1109/ITSC.2015.400 https://doi.org/10.1109/ITSC.2015.400

Rummelhard L , Paigwar A , Nègre A , et al. , 2017 . Ground estimation and point cloud segmentation using spatiotemporal conditional random field . IEEE Intelligent Vehicles Symp , p. 1105 - 1110 . https://doi.org/10.1109/IVS.2017.7995861 https://doi.org/10.1109/IVS.2017.7995861

Song SR , Yu F , Zeng A , et al. , 2017 . Semantic scene completion from a single depth image . Proc IEEE Conf on Computer Vision and Pattern Recognition , p. 190 - 198 . https://doi.org/10.1109/CVPR.2017.28 https://doi.org/10.1109/CVPR.2017.28

Tatarchenko M , Park J , Koltun V , et al. , 2018 . Tangent convolutions for dense prediction in 3D . Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition , p. 3887 - 3896 . https://doi.org/10.1109/CVPR.2018.00409 https://doi.org/10.1109/CVPR.2018.00409

Thomas H , Qi CR , Deschaud JE , et al. , 2019 . KPConv: flexible and deformable convolution for point clouds . Proc IEEE/CVF Int Conf on Computer Vision , p. 6410 - 6419 . https://doi.org/10.1109/ICCV.2019.00651 https://doi.org/10.1109/ICCV.2019.00651

Thrun S , Montemerlo M , Dahlkamp H , et al. , 2006 . Stanley: the robot that won the DARPA grand challenge . J Field Robot , 23 ( 9 ): 661 - 692 . https://doi.org/10.1002/rob.20147 https://doi.org/10.1002/rob.20147

Wang L , Huang YC , Hou YL , et al. , 2019 . Graph attention convolution for point cloud semantic segmentation . Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition , p. 10288 - 10297 . https://doi.org/10.1109/CVPR.2019.01054 https://doi.org/10.1109/CVPR.2019.01054

Wang PS , Liu Y , Guo YX , et al. , 2017 . O-CNN: octree-based convolutional neural networks for 3D shape analysis . ACM Trans Graph , 36 ( 4 ): 72 . https://doi.org/10.1145/3072959.3073608 https://doi.org/10.1145/3072959.3073608

Wu BC , Wan A , Yue XY , et al. , 2018 . SqueezeSeg: convolutional neural nets with recurrent CRF for real-time road-object segmentation from 3D LiDAR point cloud . IEEE Int Conf on Robotics and Automation , p. 1887 - 1893 . https://doi.org/10.1109/ICRA.2018.8462926 https://doi.org/10.1109/ICRA.2018.8462926

Wu BC , Zhou XY , Zhao SC , et al. , 2019 . SqueezeSegV2: improved model structure and unsupervised domain adaptation for road-object segmentation from a LiDAR point cloud . Int Conf on Robotics and Automation , p. 4376 - 4382 . https://doi.org/10.1109/ICRA.2019.8793495 https://doi.org/10.1109/ICRA.2019.8793495

Wu WX , Qi ZA , Li FX , 2019 . PointConv: deep convolutional networks on 3D point clouds . Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition , p. 9613 - 9622 . https://doi.org/10.1109/CVPR.2019.00985 https://doi.org/10.1109/CVPR.2019.00985

Yan X , Gao JT , Li J , et al. , 2021 . Sparse single sweep LiDAR point cloud segmentation via learning contextual shape priors from scene completion . Proc AAAI Conf on Artificial Intelligence , p. 3101 - 3109 . https://doi.org/10.48550/arXiv.2012.03762 https://doi.org/10.48550/arXiv.2012.03762

Zhou Y , Tuzel O , 2018 . VoxelNet: end-to-end learning for point cloud based 3D object detection . Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition , p. 4490 - 4499 . https://doi.org/10.1109/CVPR.2018.00472 https://doi.org/10.1109/CVPR.2018.00472

浏览量

432

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

Pre-training with asynchronous supervised learning for reinforcement learning based autonomous driving

On 3D face reconstruction via cascaded regression in shape space

Accurate real-time stereo correspondence using intra- and inter-scanline optimization

A hybrid genetic algorithm to optimize device allocation in industrial Ethernet networks with real-time constraints