基于跨模块注意力的3D目标检测方法研究

doi:10.16182/j.issn1004731x.joss.23-FZ0843E

摘要/Abstract

摘要：

针对三维目标检测任务中利用点云数据在提取和传输目标特征过程中发生的特征丢失问题，提出一种跨模块注意力目标检测 方法。该方法结合通道注意力模块和空间注意力模块来增强关键特征信息。通过特征转换，将注意力模块不同阶段的特征连接起来，以减轻提取和传输过程中特征的损失。针对目标检测网络中不同尺度目标检测性能不足的问题，提出了一种跨尺度特征提取和融合方法。该方法通过采用多尺度特征提取和融合技术增强了网络获取多级特征的能力。实验结果表明：所提方法在保持33 Hz实时推理速度的同时获得了先进的性能。

关键词: 3D目标检测, 体素网络, 注意力模块, 多尺度特征

Abstract:

To address the issue of feature loss that occurs during the extraction and transmission of target features in 3D object detection tasks using point cloud data， this study proposes an object detection method based on cross-module attention. This method incorporates a channel attention module and a spatial attention module to enhance the crucial feature information. Through feature transformation， the features from different stages of the attention module are connected to mitigate the loss of features during the extraction and transmission process. To tackle the problem of inadequate detection performance in target detection networks for objects of different scales， a cross-scale feature extraction and fusion method is introduced. This method enhances the network’s ability to acquire multilevel features by employing multi-scale feature extraction and fusion techniques. Experimental results demonstrate that the proposed method achieves state-of-the-art performance while maintaining a real-time inference speed of 33 Hz.

Key words: 3D object detection, voxel-based network, attention module, multi-scale feature

中图分类号:

TP391

许仁杰,张小明,王晨等 . 基于跨模块注意力的3D目标检测方法研究[J]. 系统仿真学报, 2023, 35(12): 2680-2691.

Xu Renjie,Zhang Xiaoming,Wang Chen,et al . Research on 3D Object Detection Method with Cross-module Attention[J]. Journal of System Simulation, 2023, 35(12): 2680-2691.

图/表 10

参考文献 22

1	Lang A H, Vora S, Caesar H, et al. PointPillars: Fast Encoders for Object Detection from Point Clouds[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ, USA: IEEE, 2019: 12689-12697.
2	Yan Yan, Mao Yuxing, Li Bo. SECOND: Sparsely Embedded Convolutional Detection[J]. Sensors, 2018, 18(10): 3337.
3	Zhou Yin, Tuzel O. VoxelNet: End-to-end Learning for Point Cloud Based 3D Object Detection[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2018: 4490-4499.
4	He Chenhang, Zeng Hui, Huang Jianqiang, et al. Structure Aware Single-stage 3D Object Detection from Point Cloud[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ, USA: IEEE, 2020: 11870-11879.
5	Simon M, Milz S, Amende K, et al. Complex-YOLO: An Euler-region-proposal for Real-time 3D Object Detection on Point Clouds[C]//Computer Vision-ECCV 2018 Workshops. Cham: Springer International Publishing, 2019: 197-209.
6	Yang Bin, Luo Wenjie, Urtasun R. PIXOR: Real-time 3D Object Detection from Point Clouds[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2018: 7652-7660.
7	Ye Maosheng, Xu Shuangjie, Cao Tongyi. HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ, USA: IEEE, 2020: 1628-1637.
8	Shi Shaoshuai, Guo Chaoxu, Jiang Li, et al. PV-RCNN: Point-voxel Feature Set Abstraction for 3D Object Detection[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ, USA: IEEE, 2020: 10526-10535.
9	Chen Xiaozhi, Ma Huimin, Wan Ji, et al. Multi-view 3D Object Detection Network for Autonomous Driving[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ, USA: IEEE, 2017: 6526-6534.
10	Engelcke M, Rao D, Wang D Z, et al. Vote3Deep: Fast Object Detection in 3D Point Clouds Using Efficient Convolutional Neural Networks[C]//2017 IEEE International Conference on Robotics and Automation (ICRA). Piscataway, NJ, USA: IEEE, 2017: 1355-1361.
11	Li Bo. 3D Fully Convolutional Network for Vehicle Detection in Point Cloud[C]//2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Piscataway, NJ, USA: IEEE, 2017: 1513-1518.
12	Qi C R, Liu Wei, Wu Chenxia, et al. Frustum PointNets for 3D Object Detection from RGB-D Data[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2018: 918-927.
13	Shi Shaoshuai, Wang Xiaogang, Li Hongsheng. PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ, USA: IEEE, 2019: 770-779.
14	Wang Zhixin, Jia Kui. Frustum ConvNet: Sliding Frustums to Aggregate Local Point-wise Features for Amodal 3D Object Detection[C]//2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Piscataway, NJ, USA: IEEE, 2019: 1742-1749.
15	Yang Zetong, Sun Yanan, Liu Shu, et al. 3DSSD: Point-based 3D Single Stage Object Detector[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ, USA: IEEE, 2020: 11037-11045.
16	Yang Zetong, Sun Yanan, Liu Shu, et al. STD: Sparse-to-dense 3D Object Detector for Point Cloud[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV). Piscataway, NJ, USA: IEEE, 2019: 1951-1960.
17	Qi C R, Su Hao, Mo Kaichun, et al. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ, USA: IEEE, 2017: 77-85.
18	Qi C R, Yi Li, Su Hao, et al. PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook, NY, USA: Curran Associates Inc., 2017: 5105-5114.
19	Kuang Hongwu, Wang Bei, An Jianping, et al. Voxel-FPN: Multi-scale Voxel Feature Aggregation for 3D Object Detection from LIDAR Point Clouds[J]. Sensors, 2020, 20(3): 704.
20	Lin T Y, Dollár Piotr, Girshick R, et al. Feature Pyramid Networks for Object Detection[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ, USA: IEEE, 2017: 936-944.
21	Geiger A, Lenz P, Urtasun R. Are We Ready for Autonomous Driving? The KITTI Vision Benchmark Suite[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2012: 3354-3361.
22	Ku J, Mozifian M, Lee J, et al. Joint 3D Proposal Generation and Object Detection from View Aggregation[C]//2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Piscataway, NJ, USA: IEEE, 2018: 1-8.

Method	t/s	Car			Pedestrian			Cyclists
Method	t/s	Easy	Moderate	Hard	Easy	Moderate	Hard	Easy	Moderate	Hard
F-PointNet ^[12]	0.17	88.70	84.00	75.33	58.09	50.22	47.20	75.38	61.96	54.68
AVOD ^[22]	0.08	86.80	85.44	77.73	42.51	35.24	33.97	63.66	47.74	46.55
MV3D ^[9]	0.24	85.82	77.00	68.94	N/A	N/A	N/A	N/A	N/A	N/A
SECOND ^[2]	0.05	88.07	79.37	77.95	55.10	46.27	44.76	73.67	56.04	48.78
VoxelNet ^[3]	0.23	89.35	79.26	77.39	46.13	40.74	38.11	66.70	54.76	50.55
ours	0.03	89.99	87.39	85.79	61.07	55.26	51.09	84.87	70.55	66.74

Method	t/s	Car			Pedestrian			Cyclists
Method	t/s	Easy	Moderate	Hard	Easy	Moderate	Hard	Easy	Moderate	Hard
F-PointNet ^[12]	0.17	81.20	70.39	62.19	51.21	44.89	40.23	71.96	56.77	50.39
AVOD ^[22]	0.08	73.59	65.78	58.38	38.28	31.51	26.98	60.11	44.90	38.80
MV3D ^[9]	0.24	66.77	52.73	51.31	N/A	N/A	N/A	N/A	N/A	N/A
SECOND ^[2]	0.05	83.13	73.66	66.20	51.07	42.56	37.29	70.51	53.85	46.90
VoxelNet ^[3]	0.23	77.47	65.11	57.73	39.48	33.69	31.51	61.22	48.36	44.37
ours	0.03	87.19	77.45	75.67	54.94	49.61	45.56	80.34	64.83	62.05

A1	A2	A3	A4	MSF	CMA	Easy	Moderate	Hard
						89.96	87.07	79.66
	√	√				89.82	87.10	84.45
	√	√	√			89.15	86.71	84.90
				√		89.75	87.23	82.54
	√	√	√		√	89.51	86.99	84.27
		√	√	√	√	89.70	87.17	85.60
	√	√	√	√	√	89.99	87.39	85.79
√	√	√	√	√	√	89.73	87.25	85.49

A1	A2	A3	A4	MSF	CMA	Easy	Moderate	Hard
						82.51	66.15	61.28
	√	√				79.25	68.32	64.53
	√	√	√			82.82	70.36	66.22
	√	√	√		√	80.77	67.07	62.00
				√		83.12	68.51	63.34
		√	√	√	√	83.44	68.07	63.58
	√	√	√	√	√	84.87	70.55	66.75
√	√	√	√	√	√	82.16	68.62	64.04

[1]	于豪, 蒋锦霞, 赖晓翰, 梅峰, 王庆. 基于自适应感受野的电力设备表面缺陷检测方法[J]. 系统仿真学报, 2023, 35(7): 1572-1580.
[2]	付玉, 张垚, 赵萌, 王绵沼, 郑江鹏, 贾晨, 陈胜勇. 基于仿真数据迁移学习的固定翼无人机检测[J]. 系统仿真学报, 2023, 35(5): 998-1007.