面向自动驾驶场景的多目标点云检测算法

doi:10.19562/j.chinasae.qcgc.2024.07.008

Abstract

Abstract:

The three-dimensional object detection algorithm based on point cloud is one of the key technologies in the autonomous driving system. Currently， the voxel-based anchor-free detection algorithm is a research hotspot in academia， but most researches focus on designing complex refinement stage， at the expense of huge algorithm latency， to bring limited performance improvement. Although the single-stage anchor-free point cloud detection algorithm has a more streamlined detection process， its detection performance cannot satisfy the needs of autonomous driving scenarios. In this regard， based on the anchor-free detection algorithm CenterPoint， a single-stage anchor-free point cloud object detection algorithm for autonomous driving scenarios is proposed in this paper. Specifically， the encoding and decoding sparse module is introduced in this paper， which greatly promotes the information interaction of the spatial non-connected areas of the three-dimensional feature extractor， ensuring that the three-dimensional feature extractor can extract features that satisfy various target detection. In addition， considering that it is challenging to adapt the existing two-dimensional feature fusion backbone to the center-based head， in this paper self-calibrated convolution and large kernel attention modules are introduced in to effectively extract point cloud features of the target area， which are then gathered into the center point area， thereby improving the algorithm's recall and accuracy of the target. The proposed algorithm in this article is trained and experimentally verified on the large-scale public dataset of nuScenes. Compared with the benchmark algorithm， mAP and NDS are increased by 5.97% and 3.62% respectively. At the same time， the actual road experiments with the proposed algorithm are conducted on a self-built vehicle platform， further proving the effectiveness of the proposed algorithm.

Key words: autonomous driving, deep learning, point cloud detection, anchor-free

Le Tao,Hai Wang,Yingfeng Cai,Long Chen. Multi-object Detection Algorithm Based on Point Cloud for Autonomous Driving Scenarios[J].Automotive Engineering, 2024, 46(7): 1208-1218.

Figures/Tables 12

References 35

1	王海，李洋，蔡英凤，等. 基于激光雷达的3D实时车辆跟踪［J］. 汽车工程， 2021， 43（7）： 1013-1021.
	WANG Hai， LI Yang， CAI Yingfeng， et al. 3D real⁃time vehicle tracking based on lidar［J］. Automotive Engineering， 2021， 43（7）： 1013-1021.
2	娄新雨，王海，蔡英凤，等. 采用64线激光雷达的实时道路障碍物检测与分类算法的研究［J］. 汽车工程， 2019， 41（7）： 779-784.
	LOU Xinyu， WANG Hai， CAI Yingfeng， et al. A research on an algorithm for real-time detection and classification of road obstacle by using 64-line lidar［J］. Automotive Engineering， 2019， 41（7）： 779-784.
3	QI C R， SU H， MO K， et al. PointNet： deep learning on point sets for 3D classification and segmentation［C］. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition， 2017： 652-660.
4	QI C R， YI L， SU H， et al. PointNet++： deep hierarchical feature learning on point sets in a metric space［J］. Advances in Neural Information Processing Systems， 2017， 30.
5	SHI S， WANG X， LI H. PointrCNN： 3D object proposal generation and detection from point cloud［C］. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition， 2019： 770-779.
6	ZHANG Y， HU Q， XU G， et al. Not all points are equal： learning highly efficient point-based detectors for 3D lidar point clouds［C］. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition， 2022： 18953-18962.
7	龚章鹏，王国业，于是. 基于体素网络的道路场景多类目标识别算法［J］. 汽车工程， 2021， 43（4）： 469-477.
	GONG Zhangpeng， WANG Guoye， YU Shi. The algorithm of multi⁃category object recognition in road scene based on voxel network［J］. Automotive Engineering， 2021， 43（4）： 469-477.
8	SHI S， GUO C， JIANG L， et al. PV-RCNN： point-voxel feature set abstraction for 3D object detection［C］. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition， 2020： 10529-10538.
9	SHI S， JIANG L， DENG J， et al. PV-RCNN++： point-voxel feature set abstraction with local vector representation for 3D object detection［J］. International Journal of Computer Vision， 2023， 131（2）： 531-551.
10	REN S， HE K， GIRSHICK R， et al. Faster R-CNN： towards real-time object detection with region proposal networks［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2016， 39（6）： 1137-1149.
11	YIN T， ZHOU X， KRAHENBUHL P. Center-based 3D object detection and tracking［C］. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition， 2021： 11784-11793.
12	GE R， DING Z， HU Y， et al. AFDet： anchor free one stage 3D object detection［M］. arXiv， 2020.
13	DUAN K， BAI S， XIE L， et al. CenterNet： keypoint triplets for object detection［C］. Proceedings of the IEEE/CVF International Conference on Computer Vision， 2019： 6569-6578.
14	YAN Y， MAO Y， LI B. Second： sparsely embedded convolutional detection［J］. Sensors， 2018， 18（10）： 3337.
15	夏祥腾，王大方，曹江，等. 基于稀疏卷积神经网络的车载激光雷达点云语义分割方法［J］. 汽车工程， 2022， 44（1）： 26-35.
	XIA Xiangteng， WANG Dafang， CAO Jiang， et al. Semantic segmentation method of on-board lidar point cloud based on sparse convolutional neural network［J］. Automotive Engineering， 2022， 44（1）： 26-35.
16	GRAHAM B， VAN DER MAATEN L. Submanifold sparse convolutional networks［M］. arXiv， 2017.
17	CHEN Y， LIU J， ZHANG X， et al. LargekerNel 3D： scaling up kernels in 3D sparse CNNS［C］. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition， 2023： 13488-13498.
18	MAO J， XUE Y， NIU M， et al. Voxel transformer for 3D object detection［C］. Proceedings of the IEEE/CVF International Conference on Computer Vision， 2021： 3164-3173.
19	ZHANG G， JUNNAN C， GAO G， et al. HedNet： a hierarchical encoder-decoder network for 3D object detection in point clouds［J］. Advances in Neural Information Processing Systems， 2024， 36.
20	LIU J J， HOU Q， CHENG M M， et al. Improving convolutional networks with self-calibrated convolutions［C］. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition， 2020： 10096-10105.
21	CAESAR H， BANKITI V， LANG A H， et al. nuScenes： a multimodal dataset for autonomous driving［C］. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition， 2020： 11621-11631.
22	WANG H， SHI C， SHI S， et al. DSVT： dynamic sparse voxel transformer with rotated sets［C］. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition， 2023： 13520-13529.
23	赵东宇，赵树恩. 基于级联 YOLOv7 的自动驾驶三维目标检测［J］. 汽车工程， 2023， 45（7）： 1112-1122.
	ZHAO Dongyu， ZHAO Shuen. Autonomous driving 3D object detection based on cascade YOLOv7［J］. Automotive Engineering， 2023， 45（7）： 1112-1122.
24	LI Y， HOU Q， ZHENG Z， et al. Large selective kernel network for remote sensing object detection［C］. Proceedings of the IEEE/CVF International Conference on Computer Vision， 2023： 16794-16805.
25	LIN T Y， GOYAL P， GIRSHICK R， et al. Focal loss for dense object detection［C］. Proceedings of the IEEE International Conference on Computer Vision， 2017： 2980-2988.
26	TEAM O D. OpenPCDet： an open-source toolbox for 3D object detection from point clouds （2020）［Z］. 2020.
27	LOSHCHILOV I， HUTTER F. Decoupled weight decay regularization［M］. arXiv， 2019.
28	ZHU B， JIANG Z， ZHOU X， et al. Class-balanced grouping and sampling for point cloud 3D object detection［M］. arXiv， 2019.
29	LANG A H， VORA S， CAESAR H， et al. Pointpillars： fast encoders for object detection from point clouds［C］. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition， 2019： 12697-12705.
30	CHEN Y， LIU J， ZHANG X， et al. VoxelNeXt： fully sparse VoxelNet for 3D object detection and tracking［C］. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition， 2023： 21674-21683.
31	ZHOU Z， ZHAO X， WANG Y， et al. CenterFormer： center-based transformer for 3D object detection［M］//AVIDAN S， BROSTOW G， CISSÉ M， et al. Computer Vision-ECCV 2022： Vol. 13698. Cham： Springer Nature Switzerland， 2022： 496-513.
32	SHI G， LI R， MA C. PillarNet： real-time and high-performance pillar-based 3D object detection［M］//AVIDAN S， BROSTOW G， CISSÉ M， et al. Computer Vision-ECCV 2022： Vol. 13670. Cham： Springer Nature Switzerland， 2022： 35-52.
33	ERABATI G K， ARAUJO H. Li3detr： a lidar based 3D detection transformer［C］. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision， 2023： 4250-4259.
34	LI Y， CHEN Y， QI X， et al. Unifying voxel-based representation with transformer for 3D object detection［J］. Advances in Neural Information Processing Systems， 2022， 35： 18442-18455.
35	BAI X， HU Z， ZHU X， et al. Transfusion： robust lidar-camera fusion for 3D object detection with transformers［C］. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition， 2022： 1090-1099.

算法	Car	Truck	Bus	Trailer	CV	Ped	Motor	Bicycle	TC	Barrier	mAP	NDS
Baseline	0.849	0.574	0.708	0.381	0.169	0.851	0.59	0.420	0.698	0.683	0.592 2	0.664 8
改进算法	0.863 1	0.598 8	0.738 5	0.450 7	0.241 4	0.866 9	0.736 4	0.607	0.750 2	0.666	0.651 9	0.701 0
提升	+1.41%	+2.48%	+3.05%	+6.97%	+7.24%	+1.59%	+8.8%	+18.7%	+5.22%	-1.7%	+5.97%	+3.62%

算法	mATE↓	mASE↓	mAOE↓	mAVE↓	mAAE↓	mAP↑	NDS↑
PointPillar-MultiHead	0.338 7	0.260 0	0.320 7	0.287 4	0.201 5	0.446 3	0.582 3
CBGS	0.311 5	0.255 1	0.266 4	0.262 6	0.204 6	0.505 9	0.622 9
CenterPoint	0.288 0	0.254 3	0.372 7	0.215 5	0.182 4	0.592 2	0.664 8
VoxelNext	0.301 1	0.252 3	0.405 7	0.216 9	0.185 6	0.605 3	0.666 5
CenterFormer	0.275 0	0.252 0	0.275 0	0.243 0	0.208 0	0.554 0	0.652 0
PillarNet（res18）	0.277 2	0.252 0	0.289 3	0.246 7	0.191 1	0.599 0	0.673 9
Li3DeTr						0.614 0	0.676 0
UVTR-L	0.334 0	0.257 0	0.300 0	0.204 0	0.182 0	0.609	0.677 0
Transfusion-L	0.279 7	0.253 7	0.293 2	0.273 2	0.185 4	0.645 7	0.694 3
改进算法	0.276 9	0.252 7	0.338 4	0.196 0	0.186 0	0.651 9	0.701 0

Baseline	DynamicVoxel	SED-3D-Backbone	LK-2D-Backbone	IoU-Branch	Direction-Cls	mAP	NDS	FPS/Hz
√						0.592 2	0.664 8	13.5
√	√					0.601 1	0.668 4	13.1
√	√	√				0.639 9	0.684 3	12.3
√	√	√	√			0.647 4	0.695 6	11.6
√	√	√	√	√		0.649 5	0.699 6	11.4
√	√	√	√	√	√	0.651 9	0.701 0	11.4

[1]	Hai Wang,Yuxuan Ding,Tong Luo,Meng Qiu,Yingfeng Cai,Long Chen. A Multi-class Multi-target Tracking Algorithm Combining Motion Speed and Appearance Features in Driving Scenarios [J]. Automotive Engineering, 2024, 46(6): 956-964.
[2]	Jing Huang,Xiangzhen Liu,Xiaoyang Deng,Ran Chen. Research on Intelligent Vehicle Trajectory Planning Based on Multimodal Trajectory Prediction [J]. Automotive Engineering, 2024, 46(6): 965-974.
[3]	Fuxing Yao,Chao Sun,Yungang Lan,Bing Lu,Bo Wang,Haiyang Yu. A Lane Change Decision Method for Intelligent Connected Vehicles Based on Mixture of Expert Model [J]. Automotive Engineering, 2024, 46(5): 882-892.
[4]	Mengfan Li,Zhongxiang Feng,Weihua Zhang,Jingyu Li. Study on Driver's Visual Transfer Characteristics During the Takeover Process of Human-Computer Co-driving Mode [J]. Automotive Engineering, 2024, 46(5): 795-804.
[5]	Ting Chikit,Yafei Wang,Yichen Zhang,Mingyu Wu,Yile Wang. Energy-Saving Planning Method for Autonomous Driving Mining Trucks Based on Composite Dynamic Sampling [J]. Automotive Engineering, 2024, 46(4): 588-595.
[6]	Hongyi Liang,Jikai Chen,Wanli Liu,Fengchong Lan,Bingda Mo,Jiqing Chen. Prediction of the Remaining Useful Life of Real Vehicle Lithium Batteries by Fusion of K-means Clustering and Sequence Decomposition [J]. Automotive Engineering, 2024, 46(4): 634-642.
[7]	Yiwei Zhou,Mo Xia,Bing Zhu. Multimodal Vehicle Trajectory Prediction Methods Considering Multiple Traffic Participants in Urban Road Scenarios [J]. Automotive Engineering, 2024, 46(3): 396-406.
[8]	Xiaocong Zhao,Shiyu Fang,Zirui Li,Jian Sun. Extraction and Application of Key Utility Term for Social Driving Interaction [J]. Automotive Engineering, 2024, 46(2): 230-240.
[9]	Ze Gao, Zunkang Chu, Jiasheng Shi, Fu Lin, Weixiong Rao, Haiyan Yu. Research on Fast Prediction Method of Stress Field of Automotive Parts Based on Graph Network [J]. Automotive Engineering, 2024, 46(1): 170-178.
[10]	Yanli Ma, Qin Qin, Fangqi Dong, Yining Lou. Takeover Risk Assessment Model Based on Risk Field Theory Under Different Cognitive Secondary Tasks [J]. Automotive Engineering, 2024, 46(1): 9-17.
[11]	Weiguo Liu,Zhiyu Xiang,Weiping Liu,Daoxin Qi,Zixu Wang. Research on Vehicle Control Algorithm Based on Distributed Reinforcement Learning [J]. Automotive Engineering, 2023, 45(9): 1637-1645.
[12]	Weiguo Liu,Zhiyu Xiang,Rui Liu,Guodong Li,Zixu Wang. Research on End-to-End Vehicle Motion Planning Method Based on Deep Learning [J]. Automotive Engineering, 2023, 45(8): 1343-1352.
[13]	Ming Wang,Xiaolin Tang,Kai Yang,Guofa Li,Xiaosong Hu. A Motion Planning Method for Autonomous Vehicles Considering Prediction Risk [J]. Automotive Engineering, 2023, 45(8): 1362-1372.
[14]	Dongyu Zhao, Shuen Zhao. Autonomous Driving 3D Object Detection Based on Cascade YOLOv7 [J]. Automotive Engineering, 2023, 45(7): 1112-1122.
[15]	Jiahao Zhao,Zhiquan Qi,Zhifeng Qi,Hao Wang,Lei He. Calculation of Heading Angle of Parallel Large Vehicle Based on Tire Feature Points [J]. Automotive Engineering, 2023, 45(6): 1031-1039.

Multi-object Detection Algorithm Based on Point Cloud for Autonomous Driving Scenarios

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 12

References 35

Related Articles 15

Metrics

Comments

Recommended 0