skip to main content
10.1145/3469951.3469957acmotherconferencesArticle/Chapter ViewAbstractPublication PagesipmvConference Proceedingsconference-collections
Article

Towards Improving Car Point-Cloud Tracking Via Detection Updates

Published: 21 August 2021 Publication History

Abstract

Most autonomous driving applications leverage RGB images representing the surrounding environment that contain useful appearance features but with a cost in terms of geometric features. On the other side, 3D point clouds generated by LIDAR sensors can provide more geometric 3D information with high accuracy and robustness but with a loss on appearance features. Regardless of the adopted technology, object tracking in autonomous driving scenarios suffers from the so-called error drift in detecting objects over time/frames. This work investigates the car tracking problem in an urban scenario, leveraging 3D point clouds. In particular, we have set our goal to mitigate the typical error drift that characterizes the classic tracking algorithm and, to this aim, proposed a system able to reduce the drift error by detection. An extensive experimental evaluation on the KITTI dataset shows the improvement in our solution's performance compared to state-of-the-art approaches.

References

[1]
S. Giancola, J. Zarzar e B. Ghanem, «Leveraging Shape Completion for 3D Siamese Tracking,» CoRR, vol. abs/1903.01784, 2019
[2]
D. Wang, C. Huang, Y. Wang, Y. Deng e H. Li, «A 3D Multiobject Tracking Algorithm of Point Cloud Based on Deep Learning,» Mathematical Problems in Engineering, vol. 2020, 2020.
[3]
S. Wang, Y. Sun, C. Liu e M. Liu, «PointTrackNet: An End-to-End Network For 3-D Object Detection and Tracking From Point Clouds,» IEEE Robotics and Automation Letters, vol. 5, p. 3206–3212, 2020.
[4]
X. Weng, J. Wang, D. Held e K. Kitani, «3d multi-object tracking: A baseline and new evaluation metrics,» arXiv preprint arXiv:1907.03961, 2020.
[5]
S. Shi, C. Guo, L. Jiang, Z. Wang, J. Shi, X. Wang e H. Li, «PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection,» CoRR, vol. abs/1912.13192, 2019.
[6]
A. Geiger, P. Lenz, C. Stiller e R. Urtasun, «Vision meets robotics: The kitti dataset,» The International Journal of Robotics Research, vol. 32, p. 1231–1237, 2013.
[7]
J. Zarzar, S. Giancola e B. Ghanem, «Efficient Tracking Proposals using 2D-3D Siamese Networks on LIDAR,» CoRR, vol. abs/1903.10168, 2019.
[8]
Y. Guo, H. Wang, Q. Hu, H. Liu, L. Liu e M. Bennamoun, «Deep Learning for 3D Point Clouds: A Survey,» IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 1-1, 2020.
[9]
X. Chen, H. Ma, J. Wan, B. Li e T. Xia, «Multi-View 3D Object Detection Network for Autonomous Driving,» CoRR, vol. abs/1611.07759, 2016.
[10]
C. R. Qi, W. Liu, C. Wu, H. Su e L. J. Guibas, «Frustum PointNets for 3D Object Detection from RGB-D Data,» CoRR, vol. abs/1711.08488, 2017.
[11]
C. R. Qi, H. Su, K. Mo e L. J. Guibas, «PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation,» CoRR, vol. abs/1612.00593, 2016.
[12]
C. R. Qi, O. Litany, K. He e L. J. Guibas, «Deep Hough Voting for 3D Object Detection in Point Clouds,» CoRR, vol. abs/1904.09664, 2019.
[13]
W. Luo, B. Yang e R. Urtasun, «Fast and furious: Real time end-to-end 3d detection, tracking and motion forecasting with a single convolutional net,» in Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, 2018.
[14]
M. Simon, K. Amende, A. Kraus, J. Honer, T. Samann, H. Kaulbersch, S. Milz e H. Michael Gross, «Complexer-YOLO: Real-time 3D object detection and tracking on semantic point clouds,» in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2019.
[15]
M. Simon, S. Milz, K. Amende e H.-M. Gross, «Complex-yolo: Real-time 3d object detection on point clouds,» arXiv preprint arXiv:1803.06199, 2018.
[16]
J. Sang, Z. Wu, P. Guo, H. Hu, H. Xiang, Q. Zhang e B. Cai, «An improved YOLOv2 for vehicle detection,» Sensors, vol. 18, p. 4272, 2018.
[17]
H. Qi, C. Feng, Z. Cao, F. Zhao e Y. Xiao, «P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds,» in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.
[18]
H.-k. Chiu, A. Prioletti, J. Li e J. Bohg, «Probabilistic 3d multi-object tracking for autonomous driving,» arXiv preprint arXiv:2001.05673, 2020.
[19]
Z. Fang, S. Zhou, Y. Cui e S. Scherer, «3D-SiamRPN: An End-to-end Learning Method for Real-time 3D Single Object Tracking using Raw Point Cloud,» IEEE Sensors Journal, 2020.
[20]
Y. Wu, J. Lim e M.-H. Yang, «Online object tracking: A benchmark,» in Proceedings of the IEEE conference on computer vision and pattern recognition, 2013.
[21]
C. R. Qi, L. Yi, H. Su e L. J. Guibas, «Pointnet++: Deep hierarchical feature learning on point sets in a metric space,» Advances in neural information processing systems, vol. 30, p. 5099–5108, 2017.

Index Terms

  1. Towards Improving Car Point-Cloud Tracking Via Detection Updates
      Index terms have been assigned to the content through auto-classification.

      Recommendations

      Comments

      Information & Contributors

      Information

      Published In

      cover image ACM Other conferences
      IPMV '21: Proceedings of the 2021 3rd International Conference on Image Processing and Machine Vision
      May 2021
      87 pages
      ISBN:9781450390040
      DOI:10.1145/3469951
      Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      Published: 21 August 2021

      Permissions

      Request permissions for this article.

      Check for updates

      Author Tags

      1. Autonomous Driving
      2. Object Detection
      3. Object tracking
      4. Point Cloud

      Qualifiers

      • Article
      • Research
      • Refereed limited

      Conference

      IPMV 2021

      Contributors

      Other Metrics

      Bibliometrics & Citations

      Bibliometrics

      Article Metrics

      • 0
        Total Citations
      • 65
        Total Downloads
      • Downloads (Last 12 months)7
      • Downloads (Last 6 weeks)1
      Reflects downloads up to 16 Feb 2025

      Other Metrics

      Citations

      View Options

      Login options

      View options

      PDF

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      HTML Format

      View this article in HTML Format.

      HTML Format

      Figures

      Tables

      Media

      Share

      Share

      Share this Publication link

      Share on social media