Abstract
For autonomous cars it is crucial to perceive its current environment to ensure safe driving maneuvers. Light detection and ranging sensors (LiDAR) are often used for object detection due to their accurate distance measurements. However, point clouds sensed by LiDAR provide information of the environment which are not important for object detection algorithms (e.g.: vegetation, buildings). Adding semantic segmentation information to the point cloud supports object detection algorithms and improves their performance.
Within this work we transfer well established semantic segmentation methods from the image domain to point clouds and evaluate the performance on solid state LiDAR data. We successfully show the applicability of semantic segmentation methods on this new sensor technology. Furthermore, we compare semantic segmentation approaches which operate on different input representations and discuss the benefit of additional information like intensity measurements on the algorithm’s performance. The evaluations are conducted on solid state LiDAR measurements from German highway scenarios.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Nitsch, J. et al.: 3d ground point classification for automotive scenarios. In: 2018 21 st International Conference on Intelligent Transportation Systems (ITSC), pp. 2603–2608. IEEE (2018)
Douillard, B. et al.: On the segmentation of 3d lidar point clouds. In: International Conference on Robotics and Automation (ICRA), pp. 2798–2805. IEEE (2011)
Milioto, A., Vizzo, I., Behley, J., Stachniss, C.: Rangenet++: Fast and accurate lidar semantic segmentation. Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (2019)
Qi, C., Su, R., Mo, H., Guibas, K., Pointnet, L. J.: Deep learning on point sets for 3d classification and segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652–660 (2017)
Su, H., Maji, S., Kalogerakis, E., Learned-Miller, E.: Multi-view convolutional neural networks for 3d shape recognition. Proceedings of the IEEE international conference on computer vision, pp. 945–953 (2015)
Velas, M., Spanel, M., Hradis, M., Herout, A.: Cnn for very fast ground segmentation in velodyne lidar data. In: 2018 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC), pp. 97–103. IEEE (2018)
Maturana, D., Scherer, S.: Voxnet: A 3d convolutional neural network for real-time object recognition. In: 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 922–928. IEEE (2015)
Zhou, Y., Tuzel, O.: Voxelnet: End-to-end learning for point cloud based 3d object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4490–4499 (2018)
Huang, J., You, S.: Point cloud labeling using 3d convolutional neural network. In: 2016 23rd International Conference on Pattern Recognition (ICPR), pp. 2670–2675. IEEE (2016)
Riegler, G., Osman Ulusoy, A., Geiger, A.: Octnet: Learning deep 3d representations at high resolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3577–3586 (2017)
Wang, P.-S., Liu, Y., Guo, Y.-X., Sun, C.-Y., Tong, X.: O-cnn: Octree-based convolutional neural networks for 3d shape analysis. ACM Transactions on Graph (TOG) 36, 72 (2017)
Qi, C.R., Yi, L., Su, H., Guibas, L. J.: Pointnet++: Deep hierarchical feature learning on point sets in a metric space. In: Advances in neural information processing systems, pp. 5099–5108 (2017)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3431–3440 (2015)
Badrinarayanan, V., Kendall, A., Cipolla, R.: Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE transactions on pattern analysis machine intelligence 39, 2481–2495 (2017)
Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention, pp. 234–241. Springer, Cham (2015)
Milletari, F., Navab, N., Ahmadi, S.-A.: V-net: Fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV), pp. 565–571. IEEE (2016)
Stanislas, L. et al.: Airborne particle classification in lidar point clouds using deep learning. Keio University (2019).
Stanislas, L. et al.: Airborne particle classification in lidar point clouds using deep learning. In: Field and Service Robotics (pp. 395–410). Springer, Singapore (2019, September)
Shen, C. et al.: On the influence of dice loss function in multi-class organ segmentation of abdominal ct using 3d fully convolutional networks. arXiv preprint arXiv:1801.05912 (2018).
Nishida, N., Nakayama, H.: Multimodal gesture recognition using multi-stream recurrent neural network. In: Image and Video Technology, pp. 682–694. Springer, Cham (2015)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature
About this paper
Cite this paper
Erichsen, S., Nitsch, J., Schmidt, M., Schlaefer, A. (2021). Semantic Segmentation of Solid-State LiDAR Measurements for Automotive Applications. In: Bargende, M., Reuss, HC., Wagner, A. (eds) 21. Internationales Stuttgarter Symposium. Proceedings. Springer Vieweg, Wiesbaden. https://doi.org/10.1007/978-3-658-33466-6_27
Download citation
DOI: https://doi.org/10.1007/978-3-658-33466-6_27
Published:
Publisher Name: Springer Vieweg, Wiesbaden
Print ISBN: 978-3-658-33465-9
Online ISBN: 978-3-658-33466-6
eBook Packages: Computer Science and Engineering (German Language)