Detection and Tracking of Low-Frame-Rate Water Surface Dynamic Multi-Target Based on the YOLOv7-DeepSORT Fusion Algorithm
Abstract
:1. Introduction
2. Algorithm Principle
2.1. Algorithm Flow
2.2. Image Preprocessing
2.3. Improvement of YOLOv7 Detector
2.4. Improvement of DeepSORT Algorithm
3. Experimental Results
3.1. Comparison of Image Enhancement Results
3.2. Comparison of Attention Mechanism Effect
3.3. Comparison of Euclidean Distance Matching Effect
3.4. Ablation Experiments
3.5. Confidence–MOTA Contrast Analysis
3.6. Execution Time and Accuracy Analysis
3.7. Discussion
4. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Ye, C.; Lu, T.; Xiao, B.; Lu, H.; Yang, Q. Current status and outlook of target detection of ships in maritime surveillance video. Chin. J. Image Graph. 2022, 27, 2078–2093. [Google Scholar]
- Durve, M.; Orsini, S.; Tiribocchi, A.; Montessori, A.; Tucny, J.M.; Lauricella, M.; Camposeo, A.; Pisignano, D.; Succi, S. Benchmarking YOLOv5 and YOLOv7 models with DeepSORT for droplet tracking applications. Eur. Phys. J. E 2023, 46, 32. [Google Scholar] [CrossRef] [PubMed]
- Shan, Y.; Liu, S.; Zhang, Y.; Jing, M.; Xu, H. LMD-TShip: Vision Based Large-Scale Maritime Ship Tracking Benchmark for Autonomous Navigation Applications. IEEE Access 2021, 9, 74370–74384. [Google Scholar] [CrossRef]
- Zhang, P. Design and Implementation of Marine Ship Tracking System Based on Multi-Target Tracking Algorithm. J. Coast. Res. 2020, 110, 47–49. [Google Scholar] [CrossRef]
- Hu, X.; Zhang, Q. Nighttime trajectory extraction framework for traffic investigations at intersections based on improved SSD and DeepSort. Signal Image Video Process. 2023, 17, 2907–2914. [Google Scholar] [CrossRef]
- Chen, Y.; Wu, B. Multi-target tracking algorithm based on YOLO+DeepSORT. J. Phys. Conf. Ser. 2022, 2414, 012018. [Google Scholar] [CrossRef]
- Wang, J.; Zhao, H. Improved YOLOv8 Algorithm for Water Surface Object Detection. Sensors 2024, 24, 5059. [Google Scholar] [CrossRef] [PubMed]
- Xavier, J.A.; Valarmathy, S.; Gowrishankar, J.; Devi, B.N. Multi-Class Flower Counting Model with Zha-KNN Labelled Images Using Ma-Yolov9. Int. J. Adv. Comput. Sci. Appl. 2024, 15, 416–426. [Google Scholar] [CrossRef]
- Jia, H.; Li, B.; Fei, Q.; Wang, Q. Fast-Moving Target Tracking Based on KCF with Motion Prediction. In Proceedings of the 2023 42nd Chinese Control Conference (CCC), Tianjin, China, 24–26 July 2023; p. 6. [Google Scholar] [CrossRef]
- Yang, X.; Huang, X.; Huang, Z.; Zhu, L.; Li, X. A dynamic target tracking model for uavs based on the fusion of twin networks and deep learning. J. Phys. Conf. Ser. 2024, 2807, 012030. [Google Scholar] [CrossRef]
- Vatsavai, K.S.L.; Mantena, V.S.K. Camshift Algorithm with GOA-Neural Network for Drone Object Tracking. Ing. Syst. d’Inf. 2023, 28, 491. [Google Scholar] [CrossRef]
- Yu, G.; San, J.; Li, J. Real-time target tracking and recognition technology for ships based on improved convolutional neural network. Ship Sci. Technol. 2022, 44, 152–155. [Google Scholar]
- Song, H.; Zhang, X.; Song, J.; Zhao, J. Detection and tracking of safety helmet based on DeepSort and YOLOv5. Multimed. Tools Appl. 2022, 82, 10781–10794. [Google Scholar] [CrossRef]
- Hong, Y.; Ye, R.; Feng, G. A fish counting method in freshwater environment based on improved DeepSORT. Mar. Fish. 2023, 1–12. [Google Scholar] [CrossRef]
- Ren, C. Research on Hydroacoustic Target Recognition Technology Based on Joint Neural Network. Master’s Thesis, North University of China, Taiyuan, China, 2022. [Google Scholar]
- Lin, X.; Yao, L.; Sun, W.; Liu, Y.; Chen, J.; Jian, T. Target tracking of moving ships by GF-4 satellite under broken cloud environment. Space Return Remote Sens. 2021, 42, 127–139. [Google Scholar]
- Mohammad, B.S.; Ali, N.; Mahmoud, S. Evaluating the spatial effects of environmental influencing factors on the frequency of urban crashes using the spatial Bayes method based on Euclidean distance and contiguity. Transp. Eng. 2023, 12, 100181. [Google Scholar]
- Xie, T.; Yao, X. Smart Logistics Warehouse Moving-Object Tracking Based on YOLOv5 and DeepSORT. Appl. Sci. 2023, 13, 9895. [Google Scholar] [CrossRef]
- Wu, B.; Liu, C.; Jiang, F.; Li, J.; Yang, Z. Dynamic identification and automatic counting of the number of passing fish species based on the improved DeepSORT algorithm. Front. Environ. Sci. 2023, 11, 1059217. [Google Scholar] [CrossRef]
- Wu, H.; Wu, F.; Shang, S.; Liu, Z.; Yang, Y.; Li, D.; Li, P. Shadow tracking for airborne terahertz video-SAR based on SORT algorithm. In Proceedings of the SPIE-CLP Conference on Advanced Photonics, San Diego, CA, USA, 22–23 August 2023. [Google Scholar]
R | P | mAP50 | |
---|---|---|---|
YOLOv7 | 0.768 | 0.951 | 0.979 |
MSRN+YOLOv7 | 0.791 | 0.973 | 0.98 |
No Attention | CoordAtt | SE | SimAM | CBAM | SA | |
---|---|---|---|---|---|---|
P | 0.973 | 0.981 | 0.974 | 0.915 | 0.986 | 0.998 |
R | 0.791 | 0.812 | 0.815 | 0.743 | 0.925 | 0.972 |
mAP50 | 0.98 | 0.994 | 0.994 | 0.992 | 0.99 | 0.995 |
mAP50-95 | 0.831 | 0.757 | 0.868 | 0.814 | 0.842 | 0.925 |
MOTA/% | HOTA/% | IDF1/% | IDSW/% | |
---|---|---|---|---|
YOLOv7+SORT | 58.3 | 46.9 | 54.3 | 1126 |
YOLOv7+CenterTrack | 61.7 | 48.5 | 56.8 | 834 |
YOLOv7+DeepSORT | 66.2 | 55.8 | 69.5 | 673 |
The algorithms in this paper | 71.4 | 59.1 | 76.1 | 549 |
R | P | mAP50 | |
---|---|---|---|
YOLOv7 | 0.768 | 0.951 | 0.979 |
YOLOv7+MSRN | 0.791 | 0.973 | 0.98 |
YOLOv7+CBAM | 0.838 | 0.975 | 0.988 |
YOLOv7+SA | 0.841 | 0.979 | 0.984 |
YOLOv7+CBAM+SA | 0.844 | 0.972 | 0.985 |
YOLOv7+MSRN+CBAM | 0.925 | 0.986 | 0.99 |
The target recognition algorithm in this paper | 0.972 | 0.998 | 0.995 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Han, X.; Fu, S.; Han, J. Detection and Tracking of Low-Frame-Rate Water Surface Dynamic Multi-Target Based on the YOLOv7-DeepSORT Fusion Algorithm. J. Mar. Sci. Eng. 2024, 12, 1528. https://doi.org/10.3390/jmse12091528
Han X, Fu S, Han J. Detection and Tracking of Low-Frame-Rate Water Surface Dynamic Multi-Target Based on the YOLOv7-DeepSORT Fusion Algorithm. Journal of Marine Science and Engineering. 2024; 12(9):1528. https://doi.org/10.3390/jmse12091528
Chicago/Turabian StyleHan, Xingcheng, Shiwen Fu, and Junxuan Han. 2024. "Detection and Tracking of Low-Frame-Rate Water Surface Dynamic Multi-Target Based on the YOLOv7-DeepSORT Fusion Algorithm" Journal of Marine Science and Engineering 12, no. 9: 1528. https://doi.org/10.3390/jmse12091528