Vessel Detection in Satellite Images using Deep Learning
Received: 16 August 2024 | Revised: 17 September 2024 | Accepted:4 October 2024 | Online: 2 December 2024
Corresponding author: Snehal Bhosale
Abstract
Maritime surveillance and monitoring have emerged as crucial components, serving various purposes such as security, environmental protection, and economic activities. This paper focuses on utilizing Synthetic Aperture Radar (SAR) satellite imagery to detect and track vessels in maritime regions. SAR technology provides notable advantages in imaging capabilities, enabling effective vessel detection under diverse weather conditions and during both day and night. Deep learning (DL) models are trained employing annotated SAR images, including multiple vessel patterns, sizes, and orientations. The enhancement of model generalization and robustness is accomplished by applying transfer learning techniques and data augmentation strategies, ensuring reliable detection performance across different environmental conditions and vessel types. By leveraging SAR imagery, this paper aims to contribute to enhanced maritime situational awareness, enabling timely identification of small vessels, including those involved in illegal fishing, smuggling, or other illicit activities. The results of this research hold promise for bolstering maritime security, aiding search and rescue operations, and facilitating effective regulation of maritime traffic.
Keywords:
YOLO, deep learning, satellite images, vessel detectionDownloads
References
L. Jiao et al., "A Survey of Deep Learning-Based Object Detection," IEEE Access, vol. 7, pp. 128837–128868, 2019.
J. Pei, Y. Huang, W. Huo, Y. Zhang, J. Yang, and T.-S. Yeo, "SAR Automatic Target Recognition Based on Multiview Deep Learning Framework," IEEE Transactions on Geoscience and Remote Sensing, vol. 56, no. 4, pp. 2196–2210, Apr. 2018.
X. Chen, S. Xiang, C.-L. Liu, and C.-H. Pan, "Vehicle Detection in Satellite Images by Hybrid Deep Convolutional Neural Networks," IEEE Geoscience and Remote Sensing Letters, vol. 11, no. 10, pp. 1797–1801, Jul. 2014.
K. Tong, Y. Wu, and F. Zhou, "Recent advances in small object detection based on deep learning: A review," Image and Vision Computing, vol. 97, May 2020, Art. no. 103910.
T. Zhang and X. Zhang, "High-Speed Ship Detection in SAR Images Based on a Grid Convolutional Neural Network," Remote Sensing, vol. 11, no. 10, Jan. 2019, Art. no. 1206.
J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection," in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, Jun. 2016, pp. 779–788.
J. Redmon and A. Farhadi, "YOLO9000: Better, Faster, Stronger," in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, Jul. 2017, pp. 6517–6525.
W. Gai, Y. Liu, J. Zhang, and G. Jing, "An improved Tiny YOLOv3 for real-time object detection," Systems Science & Control Engineering, vol. 9, no. 1, pp. 314–321, Jan. 2021.
T. Saidani, "Deep Learning Approach: YOLOv5-based Custom Object Detection," Engineering, Technology & Applied Science Research, vol. 13, no. 6, pp. 12158–12163, Dec. 2023.
D. Thuan, "Evolution of Yolo alorithm and Yolov5: The state-of-the-art object detection algorithm," B.S. Thesis, Oulu University of Applied Sciences, Oulu, Finland, 2021.
S. S. Padmanabula, R. C. Puvvada, V. Sistla, and V. K. K. Kolli, "Object Detection Using Stacked YOLOv3," Ingénierie des Systèmes d’Information, vol. 25, no. 5, pp. 691–697, Aug. 2020.
J. Redmon and A. Farhadi, "YOLOv3: An Incremental Improvement," ArXiv, Apr. 2018.
J. Yu and W. Zhang, "Face Mask Wearing Detection Algorithm Based on Improved YOLO-v4," Sensors, vol. 21, no. 9, Jan. 2021, Art. no. 3263.
A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, "YOLOv4: Optimal Speed and Accuracy of Object Detection," ArXiv, Apr. 2020.
J. Woo, J.-H. Baek, S.-H. Jo, S. Y. Kim, and J.-H. Jeong, "A Study on Object Detection Performance of YOLOv4 for Autonomous Driving of Tram," Sensors, vol. 22, no. 22, Jan. 2022, Art. no. 9026.
Z. Jiang, L. Zhao, S. Li, and Y. Jia, "Real-time object detection method based on improved YOLOv4-tiny," ArXiv, Dec. 2020.
A. Kathuria, "What’s new in YOLO v3?," Towards Data Science, Apr. 2018.
J. Solawetz and J. Nelson, "PP-YOLO Surpasses YOLOv4 - State of the Art Object Detection Techniques," Roboflow, Aug. 03, 2020.
S. Saponara, A. Elhanashi, and Q. Zheng, "Developing a real-time social distancing detection system based on YOLOv4-tiny and bird-eye view for COVID-19," Journal of Real-Time Image Processing, vol. 19, no. 3, pp. 551–563, Jun. 2022.
T. Zhang et al., "LS-SSDD-v1.0: A Deep Learning Dataset Dedicated to Small Ship Detection from Large-Scale Sentinel-1 SAR Images," Remote Sensing, vol. 12, no. 18, Jan. 2020, Art. no. 2997.
T. Zhang, X. Zhang, J. Shi, and S. Wei, "HyperLi-Net: A hyper-light deep learning network for high-accurate and high-speed ship detection from synthetic aperture radar imagery," ISPRS Journal of Photogrammetry and Remote Sensing, vol. 167, pp. 123–153, Sep. 2020.
T. Zhang and X. Zhang, "ShipDeNet-20: An Only 20 Convolution Layers and <1-MB Lightweight SAR Ship Detector," IEEE Geoscience and Remote Sensing Letters, vol. 18, no. 7, pp. 1234–1238, Jul. 2021, https://doi.org/10.1109/LGRS.2020.2993899.
N. Mo and L. Yan, "Improved Faster RCNN Based on Feature Amplification and Oversampling Data Augmentation for Oriented Vehicle Detection in Aerial Images," Remote Sensing, vol. 12, no. 16, Jan. 2020, Art. no. 2558.
I. Singh and G. Munjal, "Modified YOLOv5 for small target detection in aerial images," Multimedia Tools and Applications, vol. 83, no. 18, pp. 53221–53242, May 2024.
Downloads
How to Cite
License
Copyright (c) 2024 Darshana Sankhe, Snehal Bhosale
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
