Multi-Stage Transformer 3D Object Detection Method
DOI:
https://doi.org/10.54097/fcis.v1i2.1629Keywords:
3D object detection, Point Cloud, 3D Vision, Deep LearningAbstract
With the development of autonomous driving, 3D object detection has experience great expectations. As the light detection and ranging (LiDAR) sensor can precisely measure the distance between environments and themselves, it has become the key component of current 3D object detection methods. However, the varing density and unstructure storage of LiDAR points cloud make it hard for feature learning. To tackle this problem, this paper proposes a multi-task transformer 3D object detection method.This method include a fast transformer based 3D encoder and a multi-stage transformer decoder. Extensive experiments demonstrate that our method can supress current other 3D object detection methods with a clear margin.
Downloads
References
Y. Zhou and O. Tuzel, ‘Voxelnet: End-to-end learning for point cloud based 3d object detection’, in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 4490–4499.
Y. Yan, Y. Mao, and B. Li, ‘Second: Sparsely embedded convolutional detection’, Sensors, vol. 18, no. 10, p. 3337, 2018.
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. 12697–12705.
G. Zhang, S. Lu, and W. Zhang, ‘CAD-Net: A context-aware detection network for objects in remote sensing imagery’, IEEE Trans. Geosci. Remote Sens., vol. 57, no. 12, pp. 10015–10024, 2019.
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 Prepr. ArXiv201203015, 2020.
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. 11873–11882.
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. 11040–11048.
R. Zhang, S. Tang, L. Liu, Y. Zhang, J. Li, and S. Yan, ‘High Resolution Feature Recovering for Accelerating Urban Scene Parsing.’, in IJCAI, 2018, pp. 1156–1162.
T. Yin, X. Zhou, and P. Krahenbuhl, ‘Center-based 3d object detection and tracking’, in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 11784–11793.
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.
S. Shi, Z. Wang, X. Wang, and H. Li, ‘Part-aˆ 2 net: 3d part-aware and aggregation neural network for object detection from point cloud’, ArXiv Prepr. ArXiv190703670, vol. 2, no. 3, 2019.
S. Shi et al., ‘Pv-rcnn: Point-voxel feature set abstraction for 3d object detection’, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 10529–10538.
S. Shi et al., ‘PV-RCNN++: Point-voxel feature set abstraction with local vector representation for 3D object detection’, ArXiv Prepr. ArXiv210200463, 2021.
P. Bhattacharyya and K. Czarnecki, ‘Deformable PV-RCNN: Improving 3D object detection with learned deformations’, ArXiv Prepr. ArXiv200808766, 2020.
Z. Li, Y. Yao, Z. Quan, W. Yang, and J. Xie, ‘Sienet: spatial information enhancement network for 3d object detection from point cloud’, ArXiv Prepr. ArXiv210315396, 2021.
S. Pang, D. Morris, and H. Radha, ‘CLOCs: Camera-LiDAR object candidates fusion for 3D object detection’, in 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020, pp. 10386–10393.
A. Mahmoud, J. S. Hu, and S. L. Waslander, ‘Dense Voxel Fusion for 3D Object Detection’, ArXiv Prepr. ArXiv220300871, 2022.
X. Wu et al., ‘Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion’, ArXiv Prepr. ArXiv220309780, 2022.
J. Deng, S. Shi, P. Li, W. Zhou, Y. Zhang, and H. Li, ‘Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection’, ArXiv Prepr. ArXiv201215712, 2020.
H. Sheng et al., ‘Improving 3d object detection with channel-wise transformer’, in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 2743–2752.
J. S. Hu, T. Kuai, and S. L. Waslander, ‘Point density-aware voxels for lidar 3d object detection’, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 8469–8478.
Z. Li, F. Wang, and N. Wang, ‘Lidar r-cnn: An efficient and universal 3d object detector’, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 7546–7555.
C. Lee et al., ‘Interactive Multi-Class Tiny-Object Detection’, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 14136–14145.
