Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
126 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

PointCompress3D: A Point Cloud Compression Framework for Roadside LiDARs in Intelligent Transportation Systems (2405.01750v2)

Published 2 May 2024 in eess.IV and cs.CV

Abstract: In the context of Intelligent Transportation Systems (ITS), efficient data compression is crucial for managing large-scale point cloud data acquired by roadside LiDAR sensors. The demand for efficient storage, streaming, and real-time object detection capabilities for point cloud data is substantial. This work introduces PointCompress3D, a novel point cloud compression framework tailored specifically for roadside LiDARs. Our framework addresses the challenges of compressing high-resolution point clouds while maintaining accuracy and compatibility with roadside LiDAR sensors. We adapt, extend, integrate, and evaluate three cutting-edge compression methods using our real-world-based TUMTraf dataset family. We achieve a frame rate of 10 FPS while keeping compression sizes below 105 Kb, a reduction of 50 times, and maintaining object detection performance on par with the original data. In extensive experiments and ablation studies, we finally achieved a PSNR d2 of 94.46 and a BPP of 6.54 on our dataset. Future work includes the deployment on the live system. The code is available on our project website: https://pointcompress3d.github.io.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (40)
  1. S. Schwarz, M. Preda, V. Baroncini, M. Budagavi, P. Cesar, P. A. Chou, R. A. Cohen, M. Krivokuća, S. Lasserre, Z. Li, et al., “Emerging mpeg standards for point cloud compression,” IEEE Journal Emerging and Selected Topics in Circuits and Systems, vol. 9, pp. 133–148, 2018.
  2. M. Cui, J. Long, M. Feng, B. Li, and H. Kai, “Octformer: Efficient octree-based transformer for point cloud compression with local enhancement,” in Proc. of AAAI Conf. on Artificial Intellig., vol. 37, no. 1, 2023, pp. 470–478.
  3. S. Biswas, J. Liu, K. Wong, S. Wang, and R. Urtasun, “Muscle: Multi sweep compression of lidar using deep entropy models,” Adv. in Neural Information Processing Systems, vol. 33, pp. 22 170–22 181, 2020.
  4. F. Galligan, M. Hemmer, O. Stava, F. Zhang, and J. Brettle, “Google/draco: a library for compressing and decompressing 3d geometric meshes and point clouds,” https://github.com/google/draco, 2018.
  5. Y. He, X. Ren, D. Tang, Y. Zhang, X. Xue, and Y. Fu, “Density-preserving deep point cloud compression,” in Proc. of IEEE/CVF Conf. on Computer Vision and Pattern Recognition, 2022, pp. 2333–2342.
  6. L. Huang, S. Wang, K. Wong, J. Liu, and R. Urtasun, “Octsqueeze: Octree-structured entropy model for lidar compression,” in Proc. of IEEE/CVF conf. on computer vision and pattern recognition, 2020.
  7. Z. Que, G. Lu, and D. Xu, “Voxelcontext-net: An octree based framework for point cloud compression,” in Proc. of IEEE/CVF Conf. on Computer Vision and Pattern Recognition, 2021, pp. 6042–6051.
  8. L. Wiesmann, A. Milioto, X. Chen, C. Stachniss, and J. Behley, “Deep compression for dense point cloud maps,” IEEE Robotics and Automation Letters, vol. 6, no. 2, pp. 2060–2067, 2021.
  9. C. Fu, G. Li, R. Song, W. Gao, and S. Liu, “Octattention: Octree-based large-scale contexts model for point cloud compression,” in Proc. of AAAI conf. on artificial intellig., vol. 36, no. 1, 2022, pp. 625–633.
  10. J. Pang, M. A. Lodhi, and D. Tian, “Grasp-net: Geometric residual analysis and synthesis for point cloud compression,” in Proc. of Workshop on Advances in Point Cloud Compression, Processing and Analysis, 2022, pp. 11–19.
  11. X. Zhou, C. R. Qi, Y. Zhou, and D. Anguelov, “Riddle: Lidar data compression with range image deep delta encoding,” in Proc. of IEEE/CVF Conf. on Computer Vision and Pattern Recognition, 2022, pp. 17 212–17 221.
  12. T. Beemelmanns, Y. Tao, B. Lampe, L. Reiher, R. van Kempen, T. Woopen, and L. Eckstein, “3d point cloud compression with recurrent neural network and image compression methods,” in 2022 IEEE Intelligent Vehicles Symposium (IV).   IEEE, 2022, pp. 345–351.
  13. A. Akhtar, Z. Li, and G. Van der Auwera, “Inter-frame compression for dynamic point cloud geometry coding,” IEEE Trans. on Image Processing, 2024.
  14. X. Zhou, M. Liu, B. L. Zagar, E. Yurtsever, and A. C. Knoll, “Vision language models in autonomous driving and intelligent transportation systems,” arXiv preprint arXiv:2310.14414, 2023.
  15. W. Zimmer, J. Wu, X. Zhou, and A. C. Knoll, “Real-time and robust 3d object detection with roadside lidars,” in Proc. of Int. Scientific Conf. on Mobility and Transport: Mobility Innovations for Growing Megacities.   Springer, 2023, pp. 199–219.
  16. W. Zimmer, J. Birkner, M. Brucker, H. T. Nguyen, S. Petrovski, B. Wang, and A. C. Knoll, “Infradet3d: Multi-modal 3d object detection based on roadside infrastructure camera and lidar sensors,” in 2023 IEEE Intelligent Vehicles Symposium (IV).   IEEE, 2023.
  17. W. Zimmer, M. Grabler, and A. Knoll, “Real-time and robust 3d object detection within road-side lidars using domain adaptation,” arXiv preprint arXiv:2204.00132, 2022.
  18. W. Zimmer, E. Ercelik, X. Zhou, X. J. D. Ortiz, and A. Knoll, “A survey of robust 3d object detection methods in point clouds,” arXiv preprint arXiv:2204.00106, 2022.
  19. A. H. Lang, S. Vora, H. Caesar, L. Zhou, J. Yang, and O. Beijbom, “Pointpillars: Fast encoders for object detection from point clouds,” in Proc. of IEEE/CVF conf. on computer vision and pattern recognition, 2019, pp. 12 697–12 705.
  20. Y. Li, A. W. Yu, T. Meng, B. Caine, J. Ngiam, D. Peng, J. Shen, Y. Lu, D. Zhou, Q. V. Le, et al., “Deepfusion: Lidar-camera deep fusion for multi-modal 3d object detection,” in Proc. of IEEE/CVF Conf. on Computer Vision and Pattern Recognition, 2022, pp. 17 182–17 191.
  21. G. Melotti, C. Premebida, and N. Gonçalves, “Multimodal deep-learning for object recognition combining camera and lidar data,” in 2020 IEEE Int. Conf. on Autonomous Robot Systems and Competitions (ICARSC).   IEEE, 2020, pp. 177–182.
  22. A. Ghita, B. Antoniussen, W. Zimmer, R. Greer, C. Creß, A. Møgelmose, M. M. Trivedi, and A. C. Knoll, “Activeanno3d–an active learning framework for multi-modal 3d object detection,” in 2024 IEEE Intelligent Vehicles Symposium, IV 2024, Korea, June 2-6, 2024.   IEEE, 2024, p. 8.
  23. A. Hekimoglu, P. Friedrich, W. Zimmer, M. Schmidt, A. Marcos-Ramiro, and A. Knoll, “Multi-task consistency for active learning,” in Proc. of IEEE/CVF Int. Conf. on Comp. Vision, 2023.
  24. J. Behley, M. Garbade, A. Milioto, J. Quenzel, S. Behnke, C. Stachniss, and J. Gall, “Semantickitti: A dataset for semantic scene understanding of lidar sequences,” in Proc. of IEEE/CVF int. conf. on computer vision, 2019, pp. 9297–9307.
  25. S. Agarwal, A. Vora, G. Pandey, W. Williams, H. Kourous, and J. McBride, “Ford multi-av seasonal dataset,” The Int. Journal of Robotics Research, vol. 39, no. 12, pp. 1367–1376, 2020.
  26. 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,” in 2022 IEEE Intelligent Vehicles Symposium (IV).   IEEE, 2022, pp. 965–970.
  27. W. Zimmer, C. Creß, H. T. Nguyen, and A. C. Knoll, “Tumtraf intersection dataset: All you need for urban 3d camera-lidar roadside perception,” in 2023 IEEE 26th Int. Conf. on Intelligent Transportation Systems (ITSC).   IEEE, 2023, pp. 1030–1037.
  28. C. Creß, W. Zimmer, N. Purschke, B. N. Doan, S. Kirchner, V. Lakshminarasimhan, L. Strand, and A. C. Knoll, “Tumtraf event: Calibration and fusion resulting in a dataset for roadside event-based and rgb cameras,” IEEE Transactions on Intelligent Vehicles, pp. 1–19, 2024.
  29. W. Zimmer, G. A. Wardana, S. Sritharan, X. Zhou, R. Song, and A. C. Knoll, “Tumtraf v2x cooperative perception dataset,” in Proc. of IEEE/CVF Conf. on Comp. Vision and Pattern Recog., 2024, p. 10.
  30. J. Pang, K. Bui, and D. Tian, “Pivot-net: Heterogeneous point-voxel-tree-based framework for point cloud compression,” arXiv preprint arXiv:2402.07243, 2024.
  31. H. Houshiar and A. Nüchter, “3d point cloud compression using conventional image compression for efficient data transmission,” in 2015 XXV int. conf. on information, communication and automation technologies (ICAT).   IEEE, 2015, pp. 1–8.
  32. M. Tatarchenko, A. Dosovitskiy, and T. Brox, “Octree generating networks: Efficient convolutional architectures for high-resolution 3d outputs,” in Proc. of IEEE int. conf. on computer vision, 2017.
  33. M. Quach, J. Pang, D. Tian, G. Valenzise, and F. Dufaux, “Survey on deep learning-based point cloud compression,” Frontiers in Signal Processing, vol. 2, p. 846972, 2022.
  34. D. T. Nguyen, M. Quach, G. Valenzise, and P. Duhamel, “Learning-based lossless compression of 3d point cloud geometry,” in ICASSP 2021-2021 IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP).   IEEE, 2021, pp. 4220–4224.
  35. G. Toderici, D. Vincent, N. Johnston, S. Jin Hwang, D. Minnen, J. Shor, and M. Covell, “Full resolution image compression with recurrent neural networks,” in Proc. of IEEE conf. on Computer Vision and Pattern Recognition, 2017, pp. 5306–5314.
  36. M. Liu, E. Yurtsever, J. Fossaert, X. Zhou, W. Zimmer, Y. Cui, B. L. Zagar, and A. C. Knoll, “A survey on autonomous driving datasets: Statistics, annotation quality, and a future outlook,” IEEE Transactions on Intelligent Vehicles, pp. 1–29, 2024.
  37. S. Lab, “DracoPy: Python bindings for Draco,” https://github.com/seung-lab/DracoPy, Accessed: 2024-05-01.
  38. A. Javaheri, C. Brites, F. Pereira, and J. Ascenso, “Improving psnr-based quality metrics performance for point cloud geometry,” in Int. Conf. on Image Processing (ICIP).   IEEE, 2020, pp. 3438–3442.
  39. W. Zimmer, A. Rangesh, and M. Trivedi, “3d bat: A semi-automatic, web-based 3d annotation toolbox for full-surround, multi-modal data streams,” in 2019 IEEE Intelligent Vehicles Symposium (IV).   IEEE, 2019, pp. 1816–1821.
  40. Tinyjpg - compress jpeg images intelligently. [Online]. Available: https://tinyjpg.com/

Summary

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

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