Article Sidebar

PDF
Issue: Vol. 2 No. 3 (2026)
Section: Research articles
DOI: 10.65154/ijmst.56
Date Published: 30/09/2026
Views 0
Downloads 0
How to Cite
Duc Hai Duong, N., Trung Kien, D., Hai Dang, B., Quang Ninh, P., & Van Hung, N. (2026). Tracking Control of a Pan–Tilt Camera System in Maritime Search and Rescue. International Journal of Marine Science and Technology, 2(3), 15-27. https://doi.org/10.65154/ijmst.56
Crossref
Scopus
Google Scholar
Europe PMC

Tracking Control of a Pan–Tilt Camera System in Maritime Search and Rescue

Nguyen Duc Hai Duong1, , Do Trung Kien2, Bui Hai Dang2, Pham Quang Ninh2, Nguyen Van Hung1
1 Faculty of Electrical and Electronic Engineering, Vietnam Maritime University, Haiphong, Vietnam
2 Faculty of Electrical and Electronic Engineering, Vietnam Maritime University, Haiphong, Vietnam

Main Article Content

Abstract

Maritime search and rescue requires target detection and tracking systems that are highly accurate and capable of achieving the shortest possible response time. Therefore, pan–tilt–zoom (PTZ) camera systems must satisfy these requirements. This study proposes an intelligent pan–tilt camera system for maritime search and rescue under conditions of fluctuating water surfaces, changing illumination, and targets that are easily obscured by waves. Previous methods mainly relied on PTZ tracking, You Only Look Once version 8 (YOLOv8) combined with tracking algorithms, and several image enhancement techniques; however, they remained limited in terms of real–time stability and adaptability to nonlinear noise in the marine environment. In this paper, YOLOv8 is integrated for human detection, while the ByteTrack algorithm is used to maintain object identity and estimate the image–centering error. An optimized Adaptive Neuro–Fuzzy Inference System (ANFIS) controller is designed for the two pan–tilt axes based on red–green–blue (RGB) and thermal imaging. Experimental results in four scenarios demonstrate that the target tracking system is stable, with the error gradually decreasing to acceptable limits. The YOLOv8 model achieved a precision above 0.8, a recall of approximately 0.7–0.75, and a mean Average Precision at an Intersection over Union threshold of 0.50 (mAP@50) of approximately 0.7. In real–world testing, the pan error was reduced from –674 pixels to 5 pixels.

Keywords

ANFIS, ByteTrack, maritime search and rescue, pan–tilt camera, target tracking, YOLOv8

Article Details

References

M. I. H. Zaidi Farouk, Z. Jamil, and M. F. Abdul Latip, “Towards online surface water quality monitoring technology: A review,” Environ. Res., vol. 238, p. 117147, 2023.
[2] F. Ponzini, D. Van Hamme, and M. Martelli, “Human detection in marine disaster search and rescue scenario: A multi–modal early fusion approach,” Ocean Engineering, vol. 340, Art. no. 122341, 2025.
[3] A. Alshibli and Q. A. Memon, “Benchmarking YOLO models for marine search and rescue in variable weather conditions,” Automation, vol. 6, no. 3, Art. no. 35, 2025.
[4] M. Pobar, “Detekcija objekata s pomorskih nadzornih kamera,” Politehnika, vol. 8, no. 1, pp. 42–49, 2024.
[5] H. Karnan et al., “Visual Servoing of unmanned surface vehicle from small tethered unmanned aerial vehicle,” arXiv, Cornell Univ., 2022.
[6] K. Bhaganagar et al., “Design control system for pan–tilt camera for visual tracking based on ADAR method taking into account energy output,” E3S Web Conf., vol. 279, pp. 2007, 2021.
[7] K. Bhaganagar et al., “A novel machine–learning framework with a moving platform for maritime drift calculations,” Front. Mar. Sci., vol. 9, 2022.
[8] F. Lu et al., “Active tracking of moving objects with speed variations using a novel PTZ camera–based machine vision technique,” Elektron. ir Elektrotechnika, vol. 31, no. 2, pp. 60–70, 2025.
[9] M. H. Lui et al., “An adaptive YOLO11 framework for the localisation, tracking, and imaging of small aerial targets using a pan–tilt–zoom camera network,” Eng, vol. 5, no. 4, pp. 3488–3516, 2024.
[10] P. C. Tran et al., “Design control system for pan–tilt camera for visual tracking based on ADAR method taking into account energy output,” E3S Web Conf., vol. 279, p. 2007, 2021.
[11] F. Luo et al., “ShipsMOT: A comprehensive benchmark and framework for multiobject tracking of ships,” IET Computer Vision, 2025.
[12] A. Hakimi and H. Farjami, “Enhanced significant wave height prediction in the Southern ocean using an ANFIS model optimized with subtractive clustering,” Sci. Rep., vol. 15, no. 1, 2025.
[13] A. Menteş and M. Yetkin, “An application of soft computing techniques to predict dynamic behaviour of mooring systems,” Brodogradnja, vol. 73, no. 2, pp. 121–137, 2022.
[14] H. Fakhruddin et al., “Strategi implementasi adaptive neuro fuzzy inference system (ANFIS) pada kendali motor induksi 3 fase metode vektor–tidak langsung,” ELKOMIKA J. Tek. Energi Elektr. Tek. Telekomun. Tek. Elektron., vol. 9, no. 4, p. 786, 2021.
[15] O. Hassanein et al., “Unmanned underwater vehicles: applications and challenges,” J. Hunan Univ. Nat. Sci., vol. 50, no. 11, 2023.
[16] M. Rizk et al., “Optimization of deep–learning detection of humans in marine environment on edge devices,” 28th IEEE International Conference on Electronics, Circuits, and Systems (ICECS), pp. 1–4, 2022.
[17] Y. Chen et al., “A novel method for water surface debris detection based on YOLOV8 with polarization interference suppression,” Photonics, vol. 12, no. 6, p. 620, 2025.
[18] Y. Yuan et al., “Adaptive fuzzy game–based energy–efficient localization in 3D underwater sensor networks,” ACM Trans. Internet Technol., vol. 22, no. 2, pp. 1–20, 2021.
[19] L. Duan et al., Research on seismic signal denoising model based on DnCNN network,” Applied Sciences, vol. 15, no. 4, 2025.
[20] Y. Wang and V. Y. Mariano, “A multi object tracking framework based on YOLOv8s and bytetrack algorithm,” IEEE Access, vol. 12, pp. 120711–120719, 2024.
[21] S. Yun et al., “Action–decision networks for visual tracking with deep reinforcement learning,” in 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1349–1358, 2017.
[22] M. Doloiu et al., “Modeling and control of a pan–tilt servo system for face tracking using deep learning and PID,” Eng. Proc., vol. 113, p. 75, 2025.
[23] Y. Sun, “Analysis for center deviation of circular target under perspective projection,” Eng. Comput., vol. 36, no. 7, pp. 2403–2413, 2019.
[24] W. Choi and S. Savarese, “Multiple target tracking in world coordinate with single, minimally calibrated camera BT – Computer Vision – ECCV 2010,” K. Daniilidis, P. Maragos, and N. Paragios, Eds., Berlin, Heidelberg: Springer Berlin Heidelberg, pp. 553–567, 2010.
[25] H. M. Lee and W. C. Choi, “Algorithm of 3D spatial coordinates measurement using a camera image,” J. Image Graph., vol. 3, no. 1, pp. 30–33, 2015.
[26] D. Xu et al., “EMA–YOLO: A Novel target–detection algorithm for immature yellow peach based on YOLOv8,” Sensors, vol. 24, p. 3783, 2024.
[27] P. Singh, R. Gottumukkala, and A. Maida, An analysis of kalman filter based object tracking methods for fast–moving tiny objects. 2025.
[28] D. Mlakić, H. R. Baghaee, and S. Nikolovski, “A novel ANFIS–based islanding detection for inverter–interfaced microgrids,” IEEE Trans. Smart Grid, vol. 10, no. 4, pp. 4411–4424, 2019.
[29] P. Mehta and M. Jain, “ANFIS and metaheuristics for double orbit retrial queue with complete and working vacations,” Appl. Soft Comput., vol. 167, p. 112473, 2024.
[30] D. Joshi, A. Mishra, and S. Anand, “ANFIS based knee angle prediction: An approach to design speed adaptive contra lateral controlled AK prosthesis,” Appl. Soft Comput., vol. 11, no. 8, pp. 4757–4765, 2011.
[31] C. Volosencu, Adaptive Neuro–Fuzzy Inference System as a Universal Estimator, 2024.
[32] M. A. AbouElaz et al., “ANFIS–optimized control for resilient and efficient supply chain performance in smart manufacturing,” Results Eng., vol. 25, pp. 104262, 2025.
[33] H.–C. Liao et al., “Automatic zooming mechanism for capturing clear moving object image using high definition fixed camera,” in 2017 19th International Conference on Advanced Communication Technology (ICACT), pp. 869–876, 2017.
[34] N. AL–Rousan, N. A. Mat Isa, and M. K. Mat Desa, “Efficient single and dual axis solar tracking system controllers based on adaptive neural fuzzy inference system,” J. King Saud Univ. – Eng. Sci., vol. 32, no. 7, pp. 459–469, 2020.
[35] M. N. S. Jagirdar et al., “Implementation of adaptive neuro–fuzzy inference system in design and process optimization of latent heat storage system,” J. Energy Storage, vol. 89, p. 111810, 2024.
[36] X. Chen et al., “Augmented ship tracking under occlusion conditions from maritime surveillance videos,” IEEE Access, vol. 8, pp. 42884–42897, 2020.
[37] F. Ponzini, D. Van Hamme, and M. Martelli, “Human detection in marine disaster search and rescue scenario: A multi–modal early fusion approach,” Ocean Engineering, vol. 340, Art. no. 122341, 2025.
[38] Z. Jin et al., “MES–YOLO: An efficient lightweight maritime search and rescue object detection algorithm with improved feature fusion pyramid network,” Journal of Visual Communication and Image Representation, 2025, Art. no. 104453.
[39] Z. Gao et al., “HPRT–YOLO: Enhanced lightweight UAV maritime search and rescue model based on YOLOv11n,” iScience, vol. 29, no. 4, Art. no. 115366, 2026.
[40] B. Zhao et al., “Enhanced YOLO11 for lightweight and accurate drone–based maritime search and rescue object detection,” PLOS ONE, vol. 20, no. 7, e0321920, 2025.