Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
173 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Real-Time and Robust 3D Object Detection Within Road-Side LiDARs Using Domain Adaptation (2204.00132v2)

Published 31 Mar 2022 in cs.CV

Abstract: This work aims to address the challenges in domain adaptation of 3D object detection using infrastructure LiDARs. We design a model DASE-ProPillars that can detect vehicles in infrastructure-based LiDARs in real-time. Our model uses PointPillars as the baseline model with additional modules to improve the 3D detection performance. To prove the effectiveness of our proposed modules in DASE-ProPillars, we train and evaluate the model on two datasets, the open source A9-Dataset and a semi-synthetic infrastructure dataset created within the Regensburg Next project. We do several sets of experiments for each module in the DASE-ProPillars detector that show that our model outperforms the SE-ProPillars baseline on the real A9 test set and a semi-synthetic A9 test set, while maintaining an inference speed of 45 Hz (22 ms). We apply domain adaptation from the semi-synthetic A9-Dataset to the semi-synthetic dataset from the Regensburg Next project by applying transfer learning and achieve a 3D [email protected] of 93.49% on the Car class of the target test set using 40 recall positions.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (39)
  1. C. Creß, W. Zimmer, L. Strand, M. Fortkord, S. Dai, V. Lakshminarasimhan, and A. Knoll, “A9-dataset: Multi-sensor infrastructure-based dataset for mobility research,” arXiv preprint arXiv, 2022.
  2. A. H. Lang, S. Vora, H. Caesar, L. Zhou, J. Yang, and O. Beijbom, “Pointpillars: Fast encoders for object detection from point clouds,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 12 697–12 705.
  3. W. Zheng, W. Tang, L. Jiang, and C.-W. Fu, “Se-ssd: Self-ensembling single-stage object detector from point cloud,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 14 494–14 503.
  4. Z. Liu, X. Zhao, T. Huang, R. Hu, Y. Zhou, and X. Bai, “Tanet: Robust 3d object detection from point clouds with triple attention,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 07, 2020, pp. 11 677–11 684.
  5. A. Krämmer, C. Schöller, D. Gulati, V. Lakshminarasimhan, F. Kurz, D. Rosenbaum, C. Lenz, and A. Knoll, “Providentia-a large-scale sensor system for the assistance of autonomous vehicles and its evaluation,” Journal of Field Robotics, 2022.
  6. V. Lakshminarasimhan and A. Knoll, “C-v2x resource deployment architecture based on moving network convoys,” in 2020 IEEE 91st vehicular technology conference (VTC2020-Spring).   IEEE, 2020, pp. 1–6.
  7. C. Creß and A. C. Knoll, “Intelligent transportation systems with the use of external infrastructure: A literature survey,” arXiv preprint arXiv:2112.05615, 2021.
  8. V. R. Torunsky, “Pilotprojekt mit Vorbildcharakter,” p. 1.
  9. A. Dosovitskiy, G. Ros, F. Codevilla, A. Lopez, and V. Koltun, “Carla: An open urban driving simulator,” in Conference on robot learning.   PMLR, 2017, pp. 1–16.
  10. “Asam e.v. openlabel v1.0.0 standardization project.” https://www.asam.net/project-detail/asam-openlabel-v100/.
  11. J. Wu, W. Zimmer, and A. Knoll, “Real-time lidar-based 3d object detection on the providentia++ test stretch using a single-stage architecture,” Master’s thesis, Technische Universität München, 2021, unpublished thesis.
  12. W. Zimmer, E. Ercelik, X. Zhou, X. Jair Diaz Ortiz, and A. Knoll, “A survey of robust 3d object detection methods in point clouds,” arXiv preprint arXiv:submit/4161670, 2022.
  13. S. Shi, X. Wang, and H. Li, “Pointrcnn: 3d object proposal generation and detection from point cloud,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 770–779.
  14. C. R. Qi, L. Yi, H. Su, and L. J. Guibas, “Pointnet++ deep hierarchical feature learning on point sets in a metric space,” in Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017, pp. 5105–5114.
  15. Z. Yang, Y. Sun, S. Liu, and J. Jia, “3dssd: Point-based 3d single stage object detector,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 11 040–11 048.
  16. Y. Yan, Y. Mao, and B. Li, “Second: Sparsely embedded convolutional detection,” Sensors, vol. 18, no. 10, p. 3337, 2018.
  17. B. Graham, M. Engelcke, and L. Van Der Maaten, “3d semantic segmentation with submanifold sparse convolutional networks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 9224–9232.
  18. C. He, H. Zeng, J. Huang, X.-S. Hua, and L. Zhang, “Structure aware single-stage 3d object detection from point cloud,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 11 873–11 882.
  19. W. Zheng, W. Tang, S. Chen, L. Jiang, and C.-W. Fu, “Cia-ssd: Confident iou-aware single-stage object detector from point cloud,” arXiv preprint arXiv:2012.03015, 2020.
  20. J. Mao, M. Niu, H. Bai, X. Liang, H. Xu, and C. Xu, “Pyramid r-cnn: Towards better performance and adaptability for 3d object detection,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 2723–2732.
  21. P. Sun, H. Kretzschmar, X. Dotiwalla, A. Chouard, V. Patnaik, P. Tsui, J. Guo, Y. Zhou, Y. Chai, B. Caine et al., “Scalability in perception for autonomous driving: Waymo open dataset,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 2446–2454.
  22. J. Mao, Y. Xue, M. Niu, H. Bai, J. Feng, X. Liang, H. Xu, and C. Xu, “Voxel transformer for 3d object detection,” 2021.
  23. Q. Xu, Y. Zhong, and U. Neumann, “Behind the curtain: Learning occluded shapes for 3d object detection,” CoRR, vol. abs/2112.02205, 2021. [Online]. Available: https://arxiv.org/abs/2112.02205
  24. A. Xiao, J. Huang, D. Guan, F. Zhan, and S. Lu, “Synlidar: Learning from synthetic lidar sequential point cloud for semantic segmentation,” CoRR, vol. abs/2107.05399, 2021. [Online]. Available: https://arxiv.org/abs/2107.05399
  25. L. T. Triess, M. Dreissig, C. B. Rist, and J. M. Zöllner, “A survey on deep domain adaptation for lidar perception,” CoRR, vol. abs/2106.02377, 2021. [Online]. Available: https://arxiv.org/abs/2106.02377
  26. D. Jia, A. Hermans, and B. Leibe, “Domain and modality gaps for lidar-based person detection on mobile robots,” CoRR, vol. abs/2106.11239, 2021. [Online]. Available: https://arxiv.org/abs/2106.11239
  27. Y. Wang, X. Chen, Y. You, L. E. Li, B. Hariharan, M. E. Campbell, K. Q. Weinberger, and W. Chao, “Train in germany, test in the USA: making 3d object detectors generalize,” CoRR, vol. abs/2005.08139, 2020. [Online]. Available: https://arxiv.org/abs/2005.08139
  28. J. Yang, S. Shi, Z. Wang, H. Li, and X. Qi, “ST3D: self-training for unsupervised domain adaptation on 3d object detection,” CoRR, vol. abs/2103.05346, 2021. [Online]. Available: https://arxiv.org/abs/2103.05346
  29. K. G. Derpanis, “Overview of the ransac algorithm,” Image Rochester NY, vol. 4, no. 1, pp. 2–3, 2010.
  30. Y. Eldar, M. Lindenbaum, M. Porat, and Y. Y. Zeevi, “The farthest point strategy for progressive image sampling,” IEEE Transactions on Image Processing, vol. 6, no. 9, pp. 1305–1315, 1997.
  31. J. Hu, L. Shen, and G. Sun, “Squeeze-and-excitation networks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 7132–7141.
  32. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778.
  33. C. R. Qi, H. Su, K. Mo, and L. J. Guibas, “Pointnet: Deep learning on point sets for 3d classification and segmentation,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 652–660.
  34. S. Ioffe and C. Szegedy, “Batch normalization: Accelerating deep network training by reducing internal covariate shift,” in International conference on machine learning.   PMLR, 2015, pp. 448–456.
  35. V. Nair and G. E. Hinton, “Rectified linear units improve restricted boltzmann machines,” in Icml, 2010.
  36. L. Yi, B. Gong, and T. A. Funkhouser, “Complete & label: A domain adaptation approach to semantic segmentation of lidar point clouds,” CoRR, vol. abs/2007.08488, 2020. [Online]. Available: https://arxiv.org/abs/2007.08488
  37. M. Jaritz, T. Vu, R. de Charette, É. Wirbel, and P. Pérez, “xmuda: Cross-modal unsupervised domain adaptation for 3d semantic segmentation,” CoRR, vol. abs/1911.12676, 2019. [Online]. Available: http://arxiv.org/abs/1911.12676
  38. T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, “Focal loss for dense object detection,” in Proceedings of the IEEE international conference on computer vision, 2017, pp. 2980–2988.
  39. H. Caesar, V. Bankiti, A. H. Lang, S. Vora, V. E. Liong, Q. Xu, A. Krishnan, Y. Pan, G. Baldan, and O. Beijbom, “nuscenes: A multimodal dataset for autonomous driving,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 11 621–11 631.
Citations (9)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now