YOLO-RD: A lightweight object detection network for range doppler radar images

2019 International Conference on Advanced Electronic Materials, Computers and Materials Engineering

无线电电子学;计算机科学;材料科学

Zhou, Long^1^2 ; Wei, Suyuan^1 ; Cui, Zhongma^2 ; Ding, Wei^2^3

Rocket Force University of Engineering, Xi'an

710025, China^1

Beijing Institute of Remote Sensing Equipment, Beijing

100854, China^2

University of Electronic Science and Technology of China, Chengdu

611731, China^3

关键词: Computing power;    Detection accuracy;    Detection networks;    Large-scale objects;    Limited memory;    Multi-scale features;    Network training;    Range doppler;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/563/4/042027/pdf
DOI  :  10.1088/1757-899X/563/4/042027

来源: IOP

【 摘 要 】

Under the condition of limited memory and computing power of radar aircraft equipment, large-scale object detection network based deep learning can not be deployed. Based on the darknet framework, Our paper proposes a lightweight object detection network for range doppler(RD) radar images: YOLO-RD, and builds a lightweight RD dataset: Mini-RD, for efficient network training. Firstly, YOLO-RD extracts features from the input image through a series of small convolutional. Secondly, the dense block connection module is used to design the backbone extraction network. Finally, the prediction layer is combined with multi-scale features for prediction. Experiments show that YOLO-RD has achieved good results on the mini-RD dataset with a smaller memory budget, with a detection accuracy of 97.54%.