Improved YOLOX SAR Near-Shore Area Ship Detection Method

被引：0
|
作者：
Liu L. [1 ,2 ,3 ]
Xiao J. [2 ,3 ]
Wang X. [2 ]
Zhang D. [2 ]
Yu Z. [2 ,3 ]
机构：
[1] School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu
[2] Aerospace Information Research Institute, Chinese Academy of Sciences Haidian, Beijing
[3] School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences Huairou, Beijing
来源：
Dianzi Keji Daxue Xuebao/Journal of the University of Electronic Science and Technology of China | 2023年 / 52卷 / 01期
关键词：
improved coordinate-attention; inshore region; rotation anchor; SAR; ship detection;
D O I：
10.12178/1001-0548.2022039
中图分类号：
学科分类号：
摘要：
To solve the problem of low accuracy and high false alarm rate of synthetic aperture radar (SAR) nearshore area vessel detection, a new SAR nearshore area vessel detection method based on improved attention mechanism and rotating frame is proposed. Firstly, the feature extraction capability of the network was enhanced by improving the coordinate attention mechanism and introducing it into the feature extraction network. Secondly, the angle classification head was added and the two-dimensional Gaussian distribution was introduced to calculate the KL divergence between the prediction distribution and the target distribution, so as to evaluate the loss value of the rotating frame and complete the angle information extraction of the target. Then, based on the anchor frameless (AF) mechanism of YOLOX algorithm, the model can be made lightweight and the positioning accuracy can be further improved by reducing the redundancy of candidate frames. Finally, the model was tested on the open dataset Offical - SSDD, and the inference verification was performed on the embedded platform (NVIDIA Jetson AGX Xavier). The calculation parameter of the algorithm model is only 1.14M, and the average detection accuracy of the algorithm model is 18.77%, higher than that of the YOLOX model in the nearshore condition, and the overall detection accuracy reaches 94.2%. The verification results show that the algorithm is suitable for dense ship target detection in any direction in complex scenes and can meet the requirements of real-time processing. © 2023 Univ. of Electronic Science and Technology of China. All rights reserved.
引用
收藏
页码：44 / 53
页数：9
相关论文
共 19 条
  • [1] SUN X, WANG Z R, SUN Y R, Et al., AIR-SARShip-1.0: High-Resolution SAR ship detection dataset, Journal of Radars, 8, 6, pp. 852-862, (2019)
  • [2] REDMON J, DIVVALA S, GIRSHICK R, Et al., You only look once: Unified, real-time object detection, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779-788, (2016)
  • [3] LIU W, ANGUELOV D, ERHAN D, Et al., SSD: Single shot MultiBox detector, European Conference on Computer Vision, pp. 21-37, (2016)
  • [4] XU Y, GU Y, PENG D L, Et al., Improved YOLOv3 model for ship detection of synthetic aperture radar images in any direction, Acta Armamentarii, 42, 8, pp. 1698-1707, (2021)
  • [5] YANG J., Research on SAR ship target detection method based on deep learning, (2021)
  • [6] REN S Q, HE K M, GIRSHICK R, Et al., Faster R-CNN: Towards real-time object detection with region proposal networks, IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 6, pp. 1137-1149, (2017)
  • [7] ZHOU X K, LIU C, ZHOU B., Multi-Scale feature fusion and feature channel relationship calibration for SAR image ship detection, Journal of Radars, 10, 4, pp. 531-543, (2021)
  • [8] GE Z, LIU S T, WANG F, Et al., YOLOX: Exceeding YOLO series in 2021
  • [9] HU J, SHEN L, ALBANIE S, Et al., Squeeze-and-Excitation Networks, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132-7141, (2018)
  • [10] WOO S, PARK J, LEE J Y, Et al., CBAM: Convolutional Block Attention Module, Proceedings of the European Conference on Computer Vision (ECCV), pp. 3-19, (2018)
12