LiDAR Object Detection Method Based on Point Cloud Mask Pre-training and Gaussian Localization Uncertainty Estimation

被引：0

作者：

Feng, Yu ^{[1
]}

Xie, Guangda ^{[1
]}

Liu, Long ^{[1
]}

Su, Yunquan ^{[1
]}

Liu, Junwei ^{[1
]}

Geng, Yandong ^{[1
]}

Miao, Lie ^{[1
]}

机构：

[1] Scientific Research Institute, Inner Mongolia First Machinery Group Co.,Ltd., Inner Mongolia, Baotou

来源：

Binggong Xuebao/Acta Armamentarii | 2025年 / 46卷 / 06期

关键词：

LiDAR; object detection; point cloud mask; uncertainty estimation;

D O I：

10.12382/bgxb.2024.0788

中图分类号：

学科分类号：

摘要：

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. © 2025 China Ordnance Industry Corporation. All rights reserved.

引用

共 24 条

[1]

GONG S X, WANG X, KONG G J, Et al., Multi-vehicle cooperative target tracking method [ J ], Acta Armamentarii, 43, 10, pp. 2429-2442, (2022)

[2]

LIU G Y., A review of 3D object recognition algorithms for LiDAR point clouds, Information Recording Materials, 23, 4, pp. 243-245, (2022)

[3]

HUO W L, JING T, REN S., A review of 3D object detection for autonomous driving [ J ], Computer Science, 50, 7, pp. 107-118, (2023)

[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, pp. 13628-13637, (2022)

[5]

ZHANG R R, GUO Z Y, FANG R Y, Et al., Point-M2AE:multiscale masked autoencoders for hierarchical point cloud pre-training [J], Advances in Neural Information Processing Systems, 35, pp. 27061-27074, (2022)

[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, pp. 11621-11631, (2020)

[7]

WANG M, ZHU B., Application of uncertainty modeling in 2D and D target detection, Systems Engineering and Electronics, 45, 8, pp. 2370-2376, (2023)

[8]

XU X W, WANG Y F, ZHENG Y, Et al., Back to reality:weakly-supervised 3D object detection with shape-guided label enhancement, Proceedings of the IEEE/ CVF Conference on Computer Vision and Pattern Recognition, pp. 8438-8447, (2022)

[9]

MEYER G, THAKURDESA N., Learning an uncertaintyaware object detector for autonomous driving, Proceedings of IEEE International Conference on Intelligent Robots and Systems, pp. 10521-10527, (2020)

[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, pp. 16000-16009, (2022)

← 1 2 3 →