Pyramid-feature-fusion-based Two-stage Vehicle Detection via 3D Point Cloud

被引：0
|
作者：
Zhang M.-F. [1 ]
Wu Y.-F. [1 ]
Wang L. [1 ]
Wang P.-W. [1 ]
机构：
[1] Beijing Key Laboratory of Urban Road Intelligent Traffic Control Technology, North China University of Technology, Beijing
来源：
Jiaotong Yunshu Xitong Gongcheng Yu Xinxi/Journal of Transportation Systems Engineering and Information Technology | 2022年 / 22卷 / 05期
基金：
中国国家自然科学基金;
关键词：
convolutional neural network; intelligent transportation; laser point cloud; pyramid feature fusion; vehicle detection;
D O I：
10.16097/j.cnki.1009-6744.2022.05.011
中图分类号：
学科分类号：
摘要：
To improve the performance of vehicle target detection in three dimension (3D) point cloud bird eyes view (BEV), this paper proposes a two- stage 3D point cloud vehicle target detection framework based on the pyramid feature fusion. First, the original 3D point cloud is encoded by dimension reduction and voxel occupancy, which results in a two-dimension (2D) feature map. Then, the up-sampling network is used to transfer high-level semantic features, and the down-sampling network is used to transfer low-level location features. A one-stage pyramid network structure is constructed to extract vehicle target features. The candidate regions with different scales are obtained through the region proposal layer. The scale of each candidate region is aligned by the region of interest pooling layer, and the multi-scale features are fused by the full connection layer to extract the vehicle target features under different receptive fields. In addition, in terms of loss function, the sine and cosine angle loss is supplemented and weighted into the total loss function to optimize the prediction of vehicle target heading angle. The experimental analysis based on Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) open dataset shows that the proposed algorithm can effectively supplement the feature extraction of 3D point cloud aerial view compared with the benchmark network, and the average detection accuracy in difficult detection tasks is improved by 5.07% to 8.59%. © 2022 Science Press. All rights reserved.
引用
收藏
页码：107 / 116
页数：9
相关论文
共 15 条
  • [1] HUANG S C, SHAO C F, LI J, Et al., Vehicle trajectory reconstruction and anomaly detection using deep learning, Journal of Transportation Systems Engineering and Information Technology, 21, 3, pp. 47-54, (2021)
  • [2] LU D B, GUO Z M, CAI B G, Et al., A vehicle detection and tracking method based on range data, Journal of Transportation Systems Engineering and Information Technology, 18, 3, pp. 55-62, (2018)
  • [3] WANG H, YU Y, CAI Y, Et al., Soft-weighted-average ensemble vehicle detection method based on single-stage and two-stage deep learning models, IEEE Transactions on Intelligent Vehicles, 6, 1, pp. 100-109, (2021)
  • [4] 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)
  • [5] LANG A H, VORA S, CAESAR H, Et al., Pointpillars: Fast encoders for object detection from point clouds, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 12697-12705, (2019)
  • [6] ZHANG H, YANG D, YURTSEVER E, Et al., Faraway-frustum: Dealing with lidar sparsity for 3D object detection using fusion, Proceedings of the IEEE Conference on International Intelligent Transportation Systems, pp. 2646-2652, (2021)
  • [7] YANG B, LUO W, URTASUN R., PIXOR: Real-time 3D object detection from point clouds, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7652-7660, (2018)
  • [8] CHEN X, MA H, WAN J, Et al., Multi-view 3D object detection network for autonomous driving, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1907-1915, (2017)
  • [9] KU J, MOZIFIAN M, LEE J, Et al., Joint 3D proposal generation and object detection from view aggregation, Proceedings of the IEEE International Conference on Intelligent Robots and Systems, pp. 1-8, (2018)
  • [10] CHEN Y, LIU S, SHEN X, Et al., Fast point R-CNN, Proceedings of the IEEE International Conference on Computer Vision, pp. 9775-9784, (2019)
12