3D Object Detection Based on Strong Semantic Key Point Sampling

被引：0

作者：

Che, Yunlong ^{[1
]}

Yuan, Liang ^{[1
]}

Sun, Lihui ^{[2
]}

机构：

[1] College of Information Science and Technology, Beijing University of Chemical Technology, Beijing

[2] Non-Commissioned Officer Academy, Space Engineering University, Beijing

来源：

Computer Engineering and Applications | 2024年 / 60卷 / 09期

关键词：

3D object detection; deep learning; feature fusion; light detection and ranging (LiDAR);

D O I：

10.3778/j.issn.1002-8331.2212-0239

中图分类号：

学科分类号：

摘要：

Feature extraction of key information in the target detection algorithm is an important factor affecting the accuracy of the algorithm. Aiming at the problems of key point sampling difficulty and insufficient feature extraction in the current 3D target detection algorithm, used for reference of PV-RCNN 3D target detection network, a 3D target detection algorithm SSPS-RCNN (strong semantic point sampling RCNN) based on strong semantic key point sampling is proposed. In the key point sampling stage, the algorithm used the fusion method of semantic weighted point sampling and proposal area point filtering to obtain more characteristic representative key points and increase the proportion of foreground points in the sampling points. Without adding the network structure, the point by semantic information is reweighted to further refine the feature contribution of the key points to improve the algorithm accuracy. Experiments show that this algorithm can reduce the problem of missing detection and wrong detection than the existing mainstream algorithms, and show good stability and robustness. Experimental results on KITTI dataset show that the proposed algorithm has good stability and robustness compared with the existing mainstream algorithms, which can reduce the problem of missing detection and wrong detection and improve the overall detection accuracy. © 2024 Journal of Computer Engineering and Applications Beijing Co., Ltd.; Science Press. All rights reserved.

引用

页码：254 / 260

页数：6

共 28 条

[1]

GHASEMIEH A, KASHEF R., 3D object detection for autonomous driving: methods, models, sensors, data, and challenges, Transportation Engineering, 8, (2022)

[2]

QIAN R, LAI X, LI X., 3D object detection for autonomous driving: a survey, Pattern Recognition, 130, (2022)

[3]

XIAO Y Q, YANG H M., Research on application of object detection algorithm in traffic scene, Computer Engineering and Applications, 57, 6, pp. 30-41, (2021)

[4]

LI Y J, LI X P, ZHANG W G., Survey on vision-based 3D object detection methods, Computer Engineering and Applications, 56, 1, pp. 11-24, (2020)

[5]

ZHOU Y, TUZEL O., Voxelnet: end-to-end learning for point cloud based 3D object detection, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4490-4499, (2018)

[6]

YAN Y, MAO Y, LI B., Second: sparsely embedded convolutional detection, Sensors, 18, 10, (2018)

[7]

QI C R, SU H, MO K, Et al., PointNet: deep learning on point sets for 3D classification and segmentation, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652-660, (2017)

[8]

QI C R, YI L, SU H, Et al., PointNet++: deep hierarchical feature learning on point sets in a metric space, Proceedings of the 31st International Conference on Neural Information Processing Systems, (2017)

[9]

SHI S, WANG X, LI H., PointRCNN: 3D object proposal generation and detection from point cloud, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 770-779, (2019)

[10]

SHI S, GUO C, JIANG L, Et al., PV-RCNN: point-voxel feature set abstraction for 3D object detection, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10529-10538, (2020)

← 1 2 3 →