Comparison of Major LiDAR Data-Driven Feature Extraction Methods for Autonomous Vehicles

  • Duarte Fernandes
  • Rafael Névoa
  • António SilvaEmail author
  • Cláudia Simões
  • João Monteiro
  • Paulo Novais
  • Pedro Melo
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1160)


Object detection is one of the areas of computer vision that has matured very rapidly. Nowadays, developments in this research area have been playing special attention to the detection of objects in point clouds due to the emerging of high-resolution LiDAR sensors. However, data from a Light Detection and Ranging (LiDAR) sensor is not characterised by having consistency in relative pixel densities and introduces a third dimension, raising a set of drawbacks. The following paper presents a study on the requirements of 3D object detection for autonomous vehicles; presents an overview of the 3D object detection pipeline that generalises the operation principle of models based on point clouds; and categorises the recent works on methods to extract features and summarise their performance.


LiDAR Point clouds 3D Object Detection and Classification CNNs 



This work is supported by European Structural and Investment Funds in the FEDER component, through the Operational Competitiveness and Internationalization Programme (COMPETE 2020) [Project n\(^{\circ }\) 037902; Funding Reference: POCI-01-0247-FEDER-037902]


  1. 1.
    Chen, X., Ma, H., Wan, J., Li, B., Xia, T.: Multi-view 3d object detection network for autonomous driving. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1907–1915 (2017)Google Scholar
  2. 2.
  3. 3.
    Graham, B.: Sparse 3d convolutional neural networks (2015). CoRR abs/1505.02890,
  4. 4.
    Graham, B.: Spatially-sparse convolutional neural networks (2014). CoRR abs/1409.6070,
  5. 5.
    Graham, B., van der Maaten, L.: Submanifold sparse convolutional networks (2017). CoRR abs/1706.01307,
  6. 6.
    Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., Beijbom, O.: Pointpillars: fast encoders for object detection from point clouds (2018)Google Scholar
  7. 7.
    Prime, A.: Velodyne alpha puck (2017). Accessed 22 Nov 2019
  8. 8.
    Qi, C.R., Liu, W., Wu, C., Su, H., Guibas, L.J.: Frustum pointnets for 3d object detection from rgb-d data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 918–927 (2018)Google Scholar
  9. 9.
    Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: deep learning on point sets for 3d classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652–660 (2017)Google Scholar
  10. 10.
    Wiseman, Y.: Ancillary ultrasonic rangefinder for autonomous vehicles. Int. J. Secur. Appl. 12(5), 49–58 (2018)Google Scholar
  11. 11.
    Xu, D., Anguelov, D., Jain, A.: Pointfusion: deep sensor fusion for 3d bounding box estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 244–253 (2018)Google Scholar
  12. 12.
    Yan, Y., Mao, Y., Li, B.: Second: sparsely embedded convolutional detection. Sensors 18(10), 3337 (2018)CrossRefGoogle Scholar
  13. 13.
    Zhou, Y., Tuzel, O.: Voxelnet: End-to-end learning for point cloud based 3d object detection (2017)Google Scholar
  14. 14.
    Zhu, B., Jiang, Z., Zhou, X., Li, Z., Yu, G.: Class-balanced grouping and sampling for point cloud 3d object detection (2019)Google Scholar

Copyright information

© The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Duarte Fernandes
    • 1
  • Rafael Névoa
    • 1
  • António Silva
    • 1
    Email author
  • Cláudia Simões
    • 2
  • João Monteiro
    • 1
  • Paulo Novais
    • 1
  • Pedro Melo
    • 1
    • 3
  1. 1.Algoritmi CentreUniversity of MinhoBragaPortugal
  2. 2.BoschBragaPortugal
  3. 3.Universidade de Trás-os-Montes e Alto DouroVila RealPortugal

Personalised recommendations