基于点云掩码预训练与高斯定位不确定性估计的激光雷达目标检测方法

doi:10.12382/bgxb.2024.0788

摘要/Abstract

摘要：

激光雷达获取的三维点云数据是自动驾驶的关键数据源,但其标注难度大、数据量有限且标签不确定性高,限制了基于深度学习的三维目标检测模型的训练效果。针对以上问题,提出点云掩码策略构建预训练数据集,结合迁移学习提升模型检测精度;提出基于高斯分布的定位不确定性估计建模方法,使目标检测模型在预测边界框坐标的同时预测每个坐标的定位不确定性。实验结果表明,在不明显增加算法复杂度的前提下,新方法有效减少了误检现象,显著提高了目标检测的准确性。

关键词: 激光雷达, 目标检测, 点云掩码, 不确定性估计

Abstract:

The 3D point cloud data acquired by LiDAR is crucial for autonomous driving.However,the annotation of point cloud data is difficult;the available data is limited;and there is usually a high uncertainty in its labels,which constrain the training effects of deep learning-based 3D object detection models.To address these issues,this paper proposes a point cloud masking strategy to construct a pre-training dataset,which is combined with transfer learning to improve detection accuracy.Additionally,a Gaussian distribution-based localization uncertainty estimation modeling method is proposed,enabling the object detection model to predict the localization uncertainty of each coordinate while predicting the bounding box coordinates.Experimental results demonstrate that the proposed method effectively reduces the false detections and significantly improves the accuracy of object detection without significantly increasing algorithmic complexity.

Key words: LiDAR, object detection, point cloud mask, uncertainty estimation

中图分类号:

TP181

冯宇, 谢光达, 刘龙, 苏云泉, 刘珺玮, 耿艳东, 苗蕾. 基于点云掩码预训练与高斯定位不确定性估计的激光雷达目标检测方法[J]. 兵工学报, 2025, 46(6): 240788-.

FENG Yu, XIE Guangda, LIU Long, SU Yunquan, LIU Junwei, GENG Yandong, MIAO Lie. LiDAR Object Detection Method Based on Point Cloud Mask Pre-training and Gaussian Localization Uncertainty Estimation[J]. Acta Armamentarii, 2025, 46(6): 240788-.

图/表 10

参考文献 24

[1]	龚诗雄, 王旭, 孔国杰, 等. 多车协同目标跟踪方法[J]. 兵工学报, 2022, 43(10):2429-2442.
	GONG S X, WANG X, KONG G J, et al. Multi-vehicle cooperative target tracking method[J]. Acta Armamentarii, 2022, 43(10):2429-2442. (in Chinese)
[2]	刘桂宇. 面向激光雷达点云的三维目标识别算法研究综述[J]. 信息记录材料, 2022, 23(4):243-245.
	LIU G Y. A review of 3D object recognition algorithms for LiDAR point clouds[J]. Information Recording Materials, 2022, 23(4):243-245. (in Chinese)
[3]	霍威乐, 荆涛, 任爽. 面向自动驾驶的三维目标检测综述[J]. 计算机科学, 2023, 50(7):107-118. doi: 10.11896/jsjkx.220700090
	HUO W L, JING T, REN S. A review of 3D object detection for autonomous driving[J]. Computer Science, 2023, 50(7):107-118. (in Chinese) doi: 10.11896/jsjkx.220700090
[4]	VASCONCELOS C, BIRODKAR V, DUMOULIN V. Proper reuse of image classification features improves object detection[C]// Proceedings of Conference on Computer Vision and Pattern Recognition.New Orleans,LA,US:IEEE, 2022:13628-13637.
[5]	ZHANG R R, GUO Z Y, FANG R Y, et al. Point-M2AE:multi-scale masked autoencoders for hierarchical point cloud pre-training[J]. Advances in Neural Information Processing Systems, 2022, 35:27061-27074.
[6]	CAESAR H, BANKITI V, LANG A H, et al. nuscenes:a multimodal dataset for autonomous driving[C]// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Seattle,WA,US:IEEE, 2020:11621-11631.
[7]	汪萌, 诸兵. 不确定性建模在2D和3D目标检测中的应用[J]. 系统工程与电子技术, 2023, 45(8) :2370-2376. doi: 10.12305/j.issn.1001-506X.2023.08.10
	WANG M, ZHU B. Application of uncertainty modeling in 2D and D target detection[J]. Systems Engineering and Electronics, 2023, 45(8) :2370-2376. (in Chinese)
[8]	XU X W, WANG Y F, ZHENG Y, et al. Back to reality:weakly-supervised 3D object detection with shape-guided label enhancement[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.New Orleans,LA,US:IEEE, 2022:8438-8447.
[9]	MEYER G, THAKURDESA N. Learning an uncertaintyaware object detector for autonomous driving[C]// Proceedings of IEEE International Conference on Intelligent Robots and Systems.Las Vegas,NV,US:IEEE, 2020:10521-10527.
[10]	HE K M, CHEN X L, XIE S N, et al. Masked autoencoders are scalable vision learners[C]// Proceedings of Conference on Computer Vision and Pattern Recognition.New Orleans,LA,US:IEEE, 2022:16000-16009.
[11]	GEIGER A, LENZ P, STILLER C, et al. Vision meets robotics:the KITTI dataset[J]. International Journal of Robotics Research, 2013, 32(11):1231-1237.
[12]	SUN P, KRETZSCHMAR H, DOTIWALLA X, et al. Scalability in perception for autonomous driving:Waymo open dataset[C]// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Seattle,WA,US:IEEE, 2020:2446-2454.
[13]	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.Vancouver,BC,Canada:IEEE, 2023:21674-21683.
[14]	HU R, CAO F L, WANG W J. A novel complementary dual-aware network for point cloud classification[J]. Engineering Applications of Artificial Intelligence, 2024, 137:109224.
[15]	YAN Y, MAO Y X, LI B. Second:Sparsely embedded convolutional detection[J]. Sensors, 2018, 18(10):3337-3354.
[16]	谢兄, 杨金鹏. YOLO-wLU:考虑定位不确定性的目标检测算法[J]. 计算机工程与应用, 2021, 57(22):223-231. doi: 10.3778/j.issn.1002-8331.2007-0234
	XIE X, YANG J P. YOLO-wLU:an object detection algorithm considering localization uncertainty[J]. Computer Engineering and Applications, 2021, 57(22):223-231. (in Chinese)
[17]	PSAROS A F, MENG X H, ZOU Z R, et al. Uncertainty quantification in scientific machine learning:Methods,metrics,and comparisons[J]. Journal of Computational Physics, 2023, 477:111902.
[18]	WANG Z, DAHL G E, SWERSKY K, et al. Pre-trained Gaussian processes for Bayesian optimization[J]. Journal of Machine Learning Research, 2024, 25(212):1-83.
[19]	LIANG A, HUA H Y, FANG J, et al. Boosting 3D point-based object detection by reducing information loss caused by discontinuous receptive fields[J]. International Journal of Applied Earth Observation and Geoinformation, 2024, 132:104049.
[20]	KONG X H, LI X J, ZHU X X, et al. Detection model based on improved faster-RCNN in apple orchard environment[J]. Intelligent Systems with Applications, 2024, 21:200325.
[21]	KINGMA D, BA J. Adam:a method for stochastic optimization[C]// Proceedings of the 3rd International Conference on Learning Representations.San Diego,CA,US:ICLR, 2015:1-15.
[22]	MARK E, LUC V, CHRISTOPHER K, et al. The PASCAL visual object classes (VOC) challenge[J]. International Journal of Computer Vision, 2010, 88:303-338.
[23]	YIN T W, ZHOU X Y, KRAHENBUHL P. Center-based 3D object detection and tracking[C]// Proceedings of IEEE International Conference on Computer Vision.Nashville,TN,US:IEEE, 2021:11784-11793.
[24]	CHEN Y K, LI Y W, ZHANG X Y, et al. Focal sparse convolutional networks for 3D object detection[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.New Orleans,LA,US:IEEE, 2022:5428-5437.

类别	示例
汽车
骑自行车的人
行人
背景

类别	示例
汽车
骑自行车的人
行人
背景

方法	Car Apr40			Ped Apr40			Cyc-Apr40
方法	容易	中等	困难	容易	中等	困难	容易	中等	困难
SECOND	91.0	79.9	77.1	58.0	51.9	47.1	78.5	56.7	52.8
SE+Pr	91.1	80.5	78.8	59.9	55.4	50.2	79.7	59.5	55.8
提升	0.1	0.6	1.7	1.9	3.5	3.1	1.2	2.8	2.9

方法	Car Apr40			Ped Apr40			Cyc-Apr40
方法	容易	中等	困难	容易	中等	困难	容易	中等	困难
SECOND	91.0	79.9	77.1	58.0	51.9	47.1	78.5	56.7	52.8
SE+Pr	91.1	80.5	78.8	59.9	55.4	50.2	79.7	59.5	55.8
提升	0.1	0.6	1.7	1.9	3.5	3.1	1.2	2.8	2.9

方法及提升值	mAP (<15m)	mAP (15~30m)	mAP (>30m)	mAP	NDS
SECOND	69.9	53.6	25.4	52.8	63.3
SE+Ga	71.6	56.5	29.0	55.5	67.4
提升值	1.7	2.9	3.6	2.7	3.1