3D Object Detection Based on Feature Distribution Convergence Guided by LiDar Point Cloud and Semantic Association

被引：0

作者：

Zheng J. ^{[1
,2
]}

Jiang B.-T. ^{[1
]}

Peng W. ^{[1
]}

Wang S. ^{[1
]}

机构：

[1] School of Computer Science and Engineering, Beihang University, Beijing

[2] State Key Laboratory of Virtual Reality Technology and Systems, Beijing

来源：

Tien Tzu Hsueh Pao/Acta Electronica Sinica | 2024年 / 52卷 / 05期

基金：

中国国家自然科学基金;

关键词：

3D object detection; attention perception; distribution convergence; Pseudo-LiDar; semantic association;

D O I：

10.12263/DZXB.20221141

中图分类号：

学科分类号：

摘要：

In view of the accuracy of existing 3D object detection algorithms based on Pseudo-LiDar is far lower than that based on real LiDAR (Light Detection and ranging), this paper studies the reconstruction of Pseudo-LiDar and proposes a 3D object detection algorithm suitable for Pseudo-LiDar. Considering that the Pseudo-LiDAR obtained by image depth is dense and gradually sparse along the increase of depth, a depth related Pseudo-LiDAR sparsification method is proposed to reduce the subsequent calculation amount while retaining more useful Pseudo-LiDAR in the middle and long distance, so as to realize the reconstruction of Pseudo-LiDAR. Furthermore, a 3D object detection algorithm based on object feature distri⁃ bution convergence under the guidance of LiDar point cloud and semantic association is proposed. During network train⁃ ing, a laser point cloud branch is introduced to guide the generation of Pseudo-LiDAR object features, so that the generated Pseudo-LiDar object feature distribution converges to the feature distribution of laser point cloud object, thereby correcting the detection error caused by the difference between the two data sources. Aiming at the insufficient semantic association between Pseudo-LiDar in the 3D candidate bounding-box obtained by RPN (Region Proposal Network) network, an atten⁃ tion perception module is designed to embed the semantic association between points through the attention mechanism in the feature representation of Pseudo-LiDar, so as to improve the accuracy of 3D object detection. The experimental results on KITTI 3D object detection dataset show when the existing 3D object detection network adopts the reconstructed Pseudo-LiDar, the detection accuracy is improved by 2.61%. Furthermore, the proposed 3D object detection network with the fea⁃ ture distribution convergence and semantic association improves the accuracy by 0.57%. Compared with other excellent methods, it also improves the detection accuracy. © 2024 Chinese Institute of Electronics. All rights reserved.

引用

页码：1700 / 1715

页数：15

共 37 条

[1]

CHEN X Z, KUNDU K, ZHU Y K, Et al., 3D object pro⁃ posals using stereo imagery for accurate object class detec⁃ tion, IEEE Transactions on Pattern Analysis and Ma⁃ chine Intelligence, 40, 5, pp. 1259-1272, (2018)

[2]

QIN Z Y, WANG J L, LU Y., Triangulation learning net⁃ work: From monocular to stereo 3D object detection, 2019 IEEE/CVF Conference on Computer Vision and Pat⁃ tern Recognition (CVPR), pp. 7607-7615, (2019)

[3]

LI P L, CHEN X Z, SHEN S J., Stereo R-CNN based 3D object detection for autonomous driving, 2019 IEEE/ CVF Conference on Computer Vision and Pattern Recogni⁃ tion (CVPR), pp. 7636-7644, (2019)

[4]

SUN J M, CHEN L H, XIE Y M, Et al., Disp R-CNN: Ste⁃ reo 3D object detection via shape prior guided instance dis⁃ parity estimation, 2020 IEEE/CVF Conference on Com⁃ puter Vision and Pattern Recognition (CVPR), pp. 10545-10554, (2020)

[5]

XU Z B, ZHANG W, YE X Q, Et al., ZoomNet: Part-aware adaptive zooming neural network for 3D object detection, Proceedings of the AAAI Conference on Artificial In⁃ telligence, 34, 7, pp. 12557-12564, (2020)

[6]

CHEN Y L, LIU S, SHEN X Y, Et al., DSGN: Deep stereo geometry network for 3D object detection, 2020 IEEE/ CVF Conference on Computer Vision and Pattern Recogni⁃ tion (CVPR), pp. 12533-12542, (2020)

[7]

WANG Y, YANG B, HU R, Et al., PLUMENet: Efficient 3D object detection from stereo images

[8]

YAN C, SALMAN E., Mono3D: Open source cell library for monolithic 3-D integrated circuits, IEEE Transac⁃ tions on Circuits and Systems I: Regular Papers, 65, 3, pp. 1075-1085, (2018)

[9]

LIMAYE A, MATHEW M, NAGORI S, Et al., SS3D: Sin⁃ gle shot 3D object detector

[10]

CHABOT F, CHAOUCH M, RABARISOA J, Et al., Deep manta: A coarse-to-fine many task network for joint 2D and 3D vehicle analysis from monocular image, Pro⁃ ceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2040-2049, (2017)

← 1 2 3 4 →