Multi-level and Multi-modal Target Detection Based on Feature Fusion

被引：0
|
作者：
Cheng T. [1 ]
Sun L. [1 ]
Hou D. [1 ]
Shi Q. [1 ]
Zhang J. [2 ]
Chen J. [3 ]
Huang H. [1 ]
机构：
[1] School of Automobile and Traffic Engineering, Hefei University of Technology, Hefei
[2] College of Electronic Engineering, National University of Defense Technology, Hefei
[3] NIO Automotive Technology (Anhui) Company Limited, Hefei
来源：
Qiche Gongcheng/Automotive Engineering | 2021年 / 43卷 / 11期
关键词：
Autonomous driving; Environmental perception; Hierarchical feature fusion; Multimodal fusion; Small target detection;
D O I：
10.19562/j.chinasae.qcgc.2021.11.005
中图分类号：
学科分类号：
摘要：
For the problems of low robustness of the environment perception and identification difficulty of small targets of autonomous driving in complex environment, a multi-level and multi-modal fusion method based on feature fusion is proposed in this paper. Firstly, the image and point cloud modal information are mapped to the same dimension, and the hierarchical features of different size targets are extracted. On this basis, the multi-modal multi-level feature fusion is carried out. Then, six comparative experiments are designed to verify the effectiveness of each module. Finally, the Waymo data set and NIO real car data are used for training and testing. The test results show that the detection MAP value of the network is improved by 23.1% compared with that of YOLO V3. © 2021, Society of Automotive Engineers of China. All right reserved.
引用
收藏
页码：1602 / 1610
页数：8
相关论文
共 16 条
  • [1] WANG B F, QI Z Q, MA G C, Et al., Vehicle detection based on information fusion of radar and machine vision, Automotive Engineering, 37, 6, pp. 674-678, (2015)
  • [2] ZHANG Y Y, ZHANG S, ZHANG Y, Et al., Multi-modality fusion perception and computing in autonomous driving, Journal of Computer Research and Development, 9, pp. 1781-1799, (2020)
  • [3] ZHANG X Y, ZOU Z H, LI Z W, Et al., Deep multi-modal fusion in object detection for autonomous driving, Caai Transactions on Intelligent Systems, 15, 4, pp. 758-771, (2020)
  • [4] GUO L, LI K Q, WANG J Q, Et al., A feature-based vehicle detection method, Automotive Engineering, 28, 11, pp. 1031-1035, (2006)
  • [5] CHANG X, CHEN X D, ZHANG J C, Et al., An object detection and tracking algorithm based on LiDAR and camera information fusion, Opto-Electronic Engineering, 46, 7, pp. 91-101, (2019)
  • [6] SUN N, QIN H M, ZHANG L, Et al., Vehicle target recognition based on multi-sensor information fusion, Automotive Engineering, 39, 11, pp. 1310-1315, (2017)
  • [7] WU Y, XUE P L, YIN G D, Et al., Low-identification dual target recognition based on feature fusion, China Mechanical Engineering, 32, 10, pp. 1205-1212, (2021)
  • [8] KIM T, GHOSH J., Robust detection of non-motorized road users using deep learning on optical and LIDAR data, 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC), (2016)
  • [9] JIN Y L, GE F Y., Pedestrian detection in full-time automatic driving based on fpn fusion architecture, Industrial Control Computer, 33, 6, pp. 59-60, (2020)
  • [10] LIN T Y, DOLLAR P, GIRSHICK R, Et al., Feature pyramid networks for object detection, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2017)
12