Coastal Vessel Target Detection Model Based on Improved YOLOv7

Abstract

To address low detection accuracy in near-coastal vessel target detection under complex conditions, a novel near-coastal vessel detection model based on an improved YOLOv7 architecture is proposed in this paper. The attention mechanism Coordinate Attention is used to improve channel attention weight and enhance a network’s ability to extract small target features. In the enhanced feature extraction network, the lightweight convolution algorithm Grouped Spatial Convolution is used to replace MPConv to reduce model calculation costs. EIoU Loss is used to replace the regression frame loss function in YOLOv7 to reduce the probability of missed and false detection. The performance of the improved model was verified using an enhanced dataset obtained through rainy and foggy weather simulation. Experiments were conducted on the datasets before and after the enhancement. The improved model achieved a mean average precision (mAP) of 97.45% on the original dataset, and the number of parameters was reduced by 2%. On the enhanced dataset, the mAP of the improved model reached 88.08%. Compared with seven target detection models, such as Faster R-CNN, YOLOv3, YOLOv4, YOLOv5, YOLOv7, YOLOv8-n, and YOLOv8-s, the improved model can effectively reduce the missed and false detection rates and improve target detection accuracy. The improved model not only accurately detects vessels in complex weather environments but also outperforms other methods on original and enhanced SeaShip datasets. This finding shows that the improved model can achieve near-coastal vessel target detection in multiple environments, laying the foundation for vessel path planning and automatic obstacle avoidance.

Keywords

Vessel target detection / YOLOv7 / Attention mechanism / Lightweight convolution / Data enhancement

References

[1] Del-Rey-Maestre N, Mata-Moya D, Jarabo-Amores MP, Gomez-del-Hoyo PJ, Barcena-Humanes JL. Artificial intelligence techniques for small boats detection in radar clutter. Real data validation. Engineering Applications of Artificial Intelligence, 2018, 67: 296-308.

[2] Elvidge CD, Zhizhin M, Baugh K, Hsu FC. Automatic boat identification system for VIIRS low light imaging data. Remote Sensing, 2015, 7(3): 3020-3036.

[3] Girshick R. Fast R-CNN. 2015 IEEE International Conference on Computer Vision (ICCV), 20151440-1448.

[4] Guo Y, Yu H, Ma L, Zeng L, Luo X. THFE: A triple-hierarchy feature enhancement method for tiny boat detection. Engineering Applications of Artificial Intelligence, 2023, 123: 106271.

[5] He K, Pan Z, Zhao W, Wang J, Wan D. Overview of research progress on numerical simulation methods for turbulent flows around underwater vehicles. Journal of Marine Science and Application, 2024, 23(1): 1-22.

[6] Hou Q, Zhou D, Feng J. Coordinate attention for efficient mobile network design. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 202113713-13722

[7] Huang Z, Jiang X, Wu F, Fu Y, Zhang Y, Fu T, Pei J. An improved method for ship target detection based on YOLOv4. Applied Sciences, 2023, 13(3): 1302.

[8] Kanjir U, Greidanus H, Oštir K. Vessel detection and classification from spaceborne optical images: A literature survey. Remote Sensing of Environment, 2018, 207: 1-26.

[9] Kong Z, Cui Y, Xiong W, Xiong Z, Xu P. Ship target recognition based on context-enhanced trajectory. ISPRS International Journal of Geo-Information, 2022, 11(12): 584.

[10] Li B, Xie X, Wei X, Tang W. Ship detection and classification from optical remote sensing images: A survey. Chinese Journal of Aeronautics, 2021, 34(3): 145-163.

[11] Li H, Deng L, Yang C, Liu J, Gu Z. Enhanced YOLO v3 tiny network for real-time ship detection from visual image. IEEE Access, 2021, 9: 16692-16706.

[12] Li H, Li J, Wei H, Liu Z, Zhan Z, Ren Q. Slim-neck by GSConv a lightweight-design for real-time detector architectures. Journal of Real-Time Image Processing, 2024, 21(3): 62.

[13] Liu RW, Yuan W, Chen X, Lu Y. An enhanced CNN-enabled learning method for promoting ship detection in maritime surveillance system. Ocean Engineering, 2021, 235: 109435.

[14] Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC. SSD: Single shot multibox detector. Computer Vision-ECCV 2016: 14th European Conference, 201621-37.

[15] Qi L, Li B, Chen L, Wang W, Dong L, Jia X, Huang J, Ge C, Xue G, Wang D. Ship target detection algorithm based on improved faster R-CNN. Electronics, 2019, 8(9): 959.

[16] Ramsay W, Fridell E, Michan M. Maritime energy transition: Future fuels and future emissions. Journal of Marine Science and Application, 2023, 22(4): 681-692.

[17] Redmon J, Divvala S, Girshick R, Farhadi A. You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016779-788

[18] Redmon J, Farhadi A. YOLO9000: better, faster, stronger. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 20177263-7271

[19] Redmon J, Farhadi A. YOLOv3: An incremental improvement, 2018ArXiv Preprint, arXiv:1804.02767

[20] Ren S, He K, Girshick R, Sun J. Faster R-CNN: Towards realtime object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 39(6): 1137-1149.

[21] Steccanella L, Bloisi DD, Castellini A, Farinelli A. Waterline and obstacle detection in images from low-cost autonomous boats for environmental monitoring. Robotics and Autonomous Systems, 2020, 124: 103346.

[22] Tsuda ME, Miller NA, Saito R, Park J, Oozeki Y. Automated VIIRS boat detection based on machine learning and its application to monitoring fisheries in the East China Sea. Remote Sensing, 2023, 15(11): 2911.

[23] Wang C, Pei J, Luo S, Huo W, Huang Y, Zhang Y, Yang J. SAR ship target recognition via multiscale feature attention and adaptive-weighed classifier. IEEE Geoscience and Remote Sensing Letters, 2023, 20: 1-5

[24] Wang CY, Bochkovskiy A, Liao HYM. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 20237464-7475

[25] Wang F, Yang X, Zhang Y, Yuan J. Ship target detection algorithm based on improved YOLOv3. 3rd International Conference on Big Data Technologies, 2020162-166.

[26] Wu W, Li X, Hu Z, Liu X. Ship detection and recognition based on improved YOLOv7. Comput. Mater. Contin., 2023, 76(1): 489-498

[27] Xu H, Guedes Soares C. Review of path-following control systems for maritime autonomous surface ships. Journal of Marine Science and Application, 2023, 22(2): 153-171.

[28] Zhang D, Zhan J, Tan L, Gao Y, Župan R. Comparison of two deep learning methods for ship target recognition with optical remotely sensed data. Neural Computing and Applications, 2021, 33: 4639-4649.

[29] Zhang X, Xu Z, Qu S, Qiu W, Di Z. Recognition algorithm of marine ship based on improved YOLOv5 deep learning. Journal of Dalian Ocean University, 2022, 37(5): 866-872(in Chinese)

[30] Zhou J, Jiang P, Zou A, Chen X, Hu W. Ship target detection algorithm based on improved YOLOv5. Journal of Marine Science and Engineering, 2021, 9(8): 908.

[31] Zhu X, Lyu S, Wang X, Zhao Q. TPH-YOLOv5: Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios. 2021 IEEE International Conference on Computer Vision (ICCV), 20212778-2788

RIGHTS & PERMISSIONS

Harbin Engineering University and Springer-Verlag GmbH Germany, part of Springer Nature