Top > JACIII > An Improved Multi Target Ship Recognition Model Based on Deep ...

single-jc.php

JACIII Vol.28 No.1 pp. 216-223
doi: 10.20965/jaciii.2024.p0216
(2024)

Research Paper:

Views over last 60 days: 205

An Improved Multi Target Ship Recognition Model Based on Deep Convolutional Neural Network

Shu-Hua Li*,†, Feng-Long Yan**, and Ying-Qiu Li**

*Department of Computer Science and Technology, Guangdong University of Science and Technology
Dongguan, Guangdong 523083, China

†Corresponding author

**School of Computer and Software, Dalian Neusoft University of Information
No.8 Software Park Road, Dalian, Liaoning 116023, China

Received:
May 29, 2023
Accepted:
October 2, 2023
Published:
January 20, 2024
Creative Commons License
Keywords:
feature pyramid network, synthetic aperture radar images, ship recognition, optimization of anchor boxes
Abstract

Deep learning is the major technique used to identify objects in images captured by the synthetic aperture radar (SAR). While SAR images can be used to identify ships in general, detecting multiple ships or small vessels in these images in complex contexts remains an outstanding challenge. This study proposes a model of detection based on the improved PP-YOLO deep convolutional neural network that can identify multiple ships as well as small vessels in complex scenarios from SAR images. The histogram equalization algorithm is first used to preprocess the SAR images, and then the initial anchor box is optimized by using the shape similarity distance-based K-means clustering algorithm. Following this, the accuracy of the training network is improved based on the feature pyramid network and an attention mechanism. The experimental results show that the average accuracy (average precision) of the model was 94.25% at 41.63 frames per second on the GF-3 and the Sentinel-1 SAR datasets, superior to those of YOLOv3 (Darknet), YOLOv7, FPN (VGG), SSD, Faster R-CNN, and PP-YOLO (RestNet50-vd). The model also satisfies the demands of real-time detection.

Gray intensity values histogram before and after equalization

Gray intensity values histogram before and after equalization

Cite this article as:
S. Li, F. Yan, and Y. Li, “An Improved Multi Target Ship Recognition Model Based on Deep Convolutional Neural Network,” J. Adv. Comput. Intell. Intell. Inform., Vol.28 No.1, pp. 216-223, 2024.
Data files:
References
  1. [1] Z. Lin, “SAR Image Object Recognition Research on Deep Learning Algorithm,” Practical Electronics, Vol.2020, No.22, pp. 65-66+27, 2020 (in Chinese). https://doi.org/10.16589/j.cnki.cn11-3571/tn.2020.22.024
  2. [2] X. Liu et al., “Research on Small Target Detection Based on Deep Learning,” Tactical Missile Technology, Vol.2019, No.1, pp. 100-107, 2019 (in Chinese). https://doi.org/10.16358/j.issn.1009-1300.2019.8.522
  3. [3] X. Li, M. Ye, and T. Li, “Review of Object Detection Based on Convolutional Neural Networks,” Application Research of Computers, Vol.34, No.10, pp. 2881-2886+2891, 2017 (in Chinese). https://doi.org/10.3969/j.issn.1001-3695.2017.10.001
  4. [4] J. Redmon and A. Farhadi, “YOLO9000: Better, Faster, Stronger,” 2017 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 6517-6525, 2017. https://doi.org/10.1109/CVPR.2017.690
  5. [5] J. Redmon et al., “You Only Look Once: Unified, Real-Time Object Detection,” 2016 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 779-788, 2016. https://doi.org/10.1109/CVPR.2016.91
  6. [6] W. Liu et al., “SSD: Single Shot MultiBox Detector,” Proc. of the 14th European Conf. on Computer Vision (ECCV 2016), pp. 21-37, 2016. https://doi.org/10.1007/978-3-319-46448-0_2
  7. [7] T.-Y. Lin et al., “Focal Loss for Dense Object Detection,” 2017 IEEE Int. Conf. on Computer Vision (ICCV), pp. 2999-3007, 2017. https://doi.org/10.1109/ICCV.2017.324
  8. [8] M. Kang et al., “A Modified Faster R-CNN Based on CFAR Algorithm for SAR Ship Detection,” 2017 Int. Workshop on Remote Sensing with Intelligent Processing (RSIP), 2017. https://doi.org/10.1109/RSIP.2017.7958815
  9. [9] T. Kong et al., “Deep Feature Pyramid Reconfiguration for Object Detection,” Proc. of the 15th European Conf. on Computer Vision (ECCV 2018), pp. 172-188, 2018. https://doi.org/10.1007/978-3-030-01228-1_11
  10. [10] Z. Xu and H. Huang, “Ship Detection in SAR Image Based on Multiple Connected Features Pyramid Network,” Laser & Optoelectronics Progress, Vol.58, No.8, pp. 287-294, 2021 (in Chinese).
  11. [11] X. Long et al., “PP-YOLO: An Effective and Efficient Implementation of Object Detector,” arXiv: 2007.12099, 2020. https://doi.org/10.48550/arXiv.2007.12099
  12. [12] M. Tan, R. Pang, and Q. V. Le, “EfficientDet: Scalable and Efficient Object Detection,” 2020 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 10778-10787, 2020. https://doi.org/10.1109/CVPR42600.2020.01079
  13. [13] G. Ghiasi, T.-Y. Lin, and Q. V. Le, “DropBlock: A Regularization Method for Convolutional Networks,” Proc. of the 32nd Int. Conf. on Neural Information Processing Systems (NIPS’18), pp. 10750-10760, 2018.
  14. [14] S. Wu, X. Li, and X. Wang, “IoU-Aware Single-Stage Object Detector for Accurate Localization,” Image and Vision Computing, Vol.97, Article No.103911, 2020. https://doi.org/10.1016/j.imavis.2020.103911
  15. [15] J. Yu et al., “UnitBox: An Advanced Object Detection Network,” Proc. of the 24th ACM Int. Conf. on Multimedia (MM’16), pp. 516-520, 2016. https://doi.org/10.1145/2964284.2967274
  16. [16] Y. Wang, G. Shi, and J. Lin, “SAR Ship Image Detection Based on Improved Faster R-CNN,” Ship Engineering, Vol.43, No.8, pp. 29-33+169, 2021 (in Chinese). https://doi.org/10.13788/jcnki.cbgc.2021.08.06
  17. [17] G. Gao, “Survey on Attention Mechanisms in Deep Learning Recommendation Models,” Computer Engineering and Applications, Vol.58, No.9, pp. 9-18, 2022 (in Chinese).
  18. [18] S. Woo et al., “CBAM: Convolutional Block Attention Module,” Proc. of the 15th European Conf. on Computer Vision (ECCV 2018), Part 7, pp. 13-19, 2018. https://doi.org/10.1007/978-3-030-01234-2_1
  19. [19] Z. Bao and X. Zhao, “Ship Detector in SAR Images Based on EfficientDet Without Pre-Training,” J. of Beijing University of Aeronautics and Astronautics, Vol.47, No.8, pp. 1664-1672, 2021 (in Chinese). https://doi.org/10.13700/j.bh.1001-5965.2020.0255
  20. [20] R. C. Gonzalez and R. E. Woods, “Digital Image Processing,” Prentice Hall, 2008.
  21. [21] X.-W. Jiang, C.-P. Wang, and Q. Fu, “Infrared Aircraft Detection Based on Improved Region Proposal Network,” Laser & Infrared, Vol.49, No.1, pp. 110-115, 2019 (in Chinese).
  22. [22] “Paddle Detection Documentation on YOLOv2/v5 Algorithm.” https://github.com/PaddlePaddle/PaddleDetection/blob/release/0.4/docs/tutorials/Custom_DataSet.md#3%E7%94%9F%E6%88%90anchor [Accessed June 27, 2022]
  23. [23] T.-Y. Lin et al., “Feature Pyramid Networks for Object Detection,” 2017 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 936-944, 2017. https://doi.org/10.1109/CVPR.2017.106
  24. [24] H. Zhou, Z. Liu, and P. Chen, “Multi-Target Ship Detection of SAR Images by Using Improved Feature Pyramid Networks Model,” Telecommunication Engineering, Vol.60, No.8, pp. 896-901, 2020 (in Chinese).
  25. [25] Y. Zhang et al., “A Neural Network and Generalized Predictive Control Framework for Urban Traffic System Optimal Perimeter Control,” J. Adv. Comput. Intell. Intell. Inform., Vol.27, No.1, pp. 74-83, 2023. https://doi.org/10.20965/jaciii.2023.p0074

Creative Commons License  This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Oct. 01, 2024