IAE-KM3D a 3D Object Detection Method Based on an Improved KM3D Network
Source abstract
Abstract
Deep learning-based 3D target detection methods need to solve the problem of insufficient 3D target detection accuracy. In this paper, the KM3D network is selected as the benchmark network after the experimental comparison of current mainstream algorithms, and the IAE-KM3D network algorithm based on the KM3D network is proposed. First, the Resnet V2 network is introduced, and the residual module is redesigned to improve the training capability of the new residual module with higher generalization. IBN NET is then introduced to carefully integrate instance normalization and batch normalization as building blocks to improve the model’s detection accuracy in hue- and brightness-changing scenarios without increasing time loss. Then, a parameter-free attention mechanism, Simam, is introduced to improve the detection accuracy of the model. After that, the elliptical Gaussian kernel is introduced to improve the algorithm’s ability to detect 3D targets. Finally, a new key point loss function is proposed to improve the algorithm’s ability to train. Experiments using the KITTI dataset conclude that the IAE-KM3D network model significantly improves detection accuracy and outperforms the KM3D algorithm regarding detection performance compared to the original KM3D network. The improvements for AP2D, AP3D, and APBEV are 5%, 12.5%, and 8.3%, respectively, and only a tiny amount of time loss and network parameters are added. Compared with other mainstream target detection algorithms, Monn3D, 3DOP, GS3D, and FQNet, the improved IAE-KM3D network in this paper significantly improves AP3D and APBEV, with fewer network parameters and shorter time consumption.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Industrial Vision Systems and Defect Detection · Visual Attention and Saliency Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Mechanical and Equipment Engineering, Hebei University of Engineering, Handan 056038, China
Jizhong Energy Fengfeng Group Company Limited Mechanical and Electrical Department, Handan 056038, China
Institute of Automation, Chinese Academy of Sciences Beijing, Beijing 100000, China
Funding
Natural Science Foundation of Hebei Province
References (34)
Show source-provided references
1. Kumar, G., and Bhatia, P.K. (2014, January 8–9). A detailed review of feature extraction in image processing systems. Proceedings of the 2014 Fourth International Conference on Advanced Computing & Communication Technologies, Rohtak, India.10.1109/ACCT.2014.74 ↗
2. Introduction to machine learning, neural networks, and deep learning
3. Deep Learning for Object Detection: A Survey10.32604/csse.2021.017016 ↗
4. A survey of autonomous driving: Common practices and emerging technologies10.1109/ACCESS.2020.2983149 ↗
5. Vehicle detection: A review10.1088/1742-6596/1634/1/012107 ↗
6. Zhou, Y., and Tuzel, O. (2018, January 18–23). Voxelnet: End-to-end learning for point cloud based 3d object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00472 ↗
7. Yang, B., Luo, W., and Urtasun, R. (2018, January 18–23). Pixor: Real-time 3d object detection from point clouds. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00798 ↗
8. Bi, S., Yuan, C., Liu, C., Cheng, J., Wang, W., and Cai, Y. (2021). A survey of low-cost 3D laser scanning technology. Appl. Sci., 11.10.3390/app11093938 ↗
9. Khan, F., Salahuddin, S., and Javidnia, H. (2020). Deep learning-based monocular depth estimation methods—A state-of-the-art review. Sensors, 20.10.3390/s20082272 ↗
10. Kim, S.H., and Hwang, Y. (2021). A survey on deep learning based methods and datasets for monocular 3D object detection. Electronics, 10.10.3390/electronics10040517 ↗
11. Finding critical scenarios for automated driving systems: A systematic mapping study10.1109/TSE.2022.3170122 ↗
12. Chen, X., Kundu, K., Zhang, Z., Ma, H., Fidler, S., and Urtasun, R. (2016, January 27–30). Monocular 3d object detection for autonomous driving. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.236 ↗
13. 3d object proposals using stereo imagery for accurate object class detection10.1109/TPAMI.2017.2706685 ↗
14. Chabot, F., Chaouch, M., Rabarisoa, J., Teuliere, C., and Chateau, T. (2017, January 21–26). Deep manta: A coarse-to-fine many-task network for joint 2d and 3d vehicle analysis from monocular image. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.198 ↗
15. Mono3d++: Monocular 3d vehicle detection with two-scale 3d hypotheses and task priors
16. Wang, Y., Chao, W.L., Garg, D., Hariharan, B., Campbell, M., and Weinberger, K.Q. (2019, January 15–20). Pseudo-lidar from visual depth estimation: Bridging the gap in 3d object detection for autonomous driving. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00864 ↗
17. Ku, J., Pon, A.D., and Waslander, S.L. (2019, January 15–20). Monocular 3d object detection leveraging accurate proposals and shape reconstruction. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.01214 ↗
18. Ma, X., Wang, Z., Li, H., Zhang, P., Ouyang, W., and Fan, X. (November, January 27). Accurate monocular 3d object detection via color-embedded 3d reconstruction for autonomous driving. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.
19. Qi, C.R., Su, H., Mo, K., and Guibas, L.J. (2017, January 21–26). Pointnet: Deep learning on point sets for 3d classification and segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.
20. Task-aware monocular depth estimation for 3D object detection
21. Mousavian, A., Anguelov, D., Flynn, J., and Kosecka, J. (2017, January 21–26). 3d bounding box estimation using deep learning and geometry. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.597 ↗
22. Naiden, A., Paunescu, V., Kim, G., Jeon, B., and Leordeanu, M. (2019, January 22–25). Shift r-cnn: Deep monocular 3d object detection with closed-form geometric constraints. Proceedings of the 2019 IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan.10.1109/ICIP.2019.8803397 ↗
23. Liu, L., Lu, J., Xu, C., Tian, Q., and Zhou, J. (2019, January 15–20). Deep fitting degree scoring network for monocular 3d object detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00115 ↗
24. Barabanau, I., Artemov, A., Burnaev, E., and Murashkin, V. (2019). Monocular 3d object detection via geometric reasoning on keypoints. arXiv.10.5220/0009102506520659 ↗
25. Monogrnet: A geometric reasoning network for monocular 3d object localization
26. Li, B., Ouyang, W., Sheng, L., Zeng, X., and Wang, X. (2019, January 15–20). Gs3d: An efficient 3d object detection framework for autonomous driving. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00111 ↗
27. Brazil, G., and Liu, X. (November, January 27). M3d-rpn: Monocular 3d region proposal network for object detection. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.
28. Liu, Z., Wu, Z., and Tóth, R. (2020, January 14–19). Smoke: Single-stage monocular 3d object detection via keypoint estimation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Seattle, WA, USA.10.1109/CVPRW50498.2020.00506 ↗
29. Monocular 3d detection with geometric constraint embedding and semi-supervised training10.1109/LRA.2021.3061343 ↗
30. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 11–14). Identity mappings in deep residual networks. Proceedings of the Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands.10.1007/978-3-319-46493-0_38 ↗
31. Pan, X., Luo, P., Shi, J., and Tang, X. (2018, January 8–14). Two at once: Enhancing learning and generalization capacities via ibn-net. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01225-0_29 ↗
32. Yang, L., Zhang, R.Y., Li, L., and Xie, X. (2021, January 18–24). Simam: A simple, parameter-free attention module for convolutional neural networks. Proceedings of the International Conference on Machine Learning, PMLR, Vienna, Austria.
33. Training-time-friendly network for real-time object detection
34. Geiger, A., Lenz, P., and Urtasun, R. (2012, January 16–21). Are we ready for autonomous driving? The kitti vision benchmark suite. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA.10.1109/CVPR.2012.6248074 ↗