ENHANCING UNDERWATER LIVE FISH DETECTION PERFORMANCE WITH YOLOV11 AND IMAGE ENHANCEMENT TECHNIQUES IN A REAL-TIME SYSTEM: PENINGKATAN KINERJA DETEKSI IKAN HIDUP BAWAH AIR MENGGUNAKAN YOLOV11 DAN TEKNIK PENINGKATAN CITRA WAKTU NYATA

Muhammad Iqbal; Indra Jaya; Yeni Herdiyeni; Dedi Jusadi; Totok Hestirianoto

doi:10.24319/jtpk.17.401-412

Authors

Muhammad Iqbal Study Program of Marine Technology, Department of Marine Science and Technology, Faculty of Fisheries and Marine Sciences, IPB University, Jl. Agatis, IPB Dramaga Campus, Bogor 16680, Indonesia
Indra Jaya Department of Marine Science and Technology, Faculty of Fisheries and Marine Sciences, IPB University, Jl. Agatis, IPB Dramaga Campus, Bogor 16680, Indonesia
Yeni Herdiyeni Study Program of Artificial Intelligence, School of Data Science, Mathematics, and Informatics, IPB University, Jl. Meranti, IPB Dramaga Campus, Bogor 16680, Indonesia
Dedi Jusadi Department of Aquaculture, Faculty of Fisheries and Marine Sciences, IPB University, Jl. Agatis, IPB Dramaga Campus, Bogor 16680, Indonesia
Totok Hestirianoto Department of Marine Science and Technology, Faculty of Fisheries and Marine Sciences, IPB University, Jl. Agatis, IPB Dramaga Campus, Bogor 16680, Indonesia

DOI:

https://doi.org/10.24319/jtpk.17.401-412

Keywords:

CLAHE, fish detection, UDP, underwater image enhancement, YOLOv11

Abstract

Underwater fish detection is challenged by low light, turbidity, and blue-green color dominance from light attenuation. This study aims to compare six image-enhancement scenarios (baseline, CLAHE, Retinex Ultra Lite, UDP, UDP Super Lite, and Gamma Correction + White Balance) combined with YOLOv11 to evaluate their detection accuracy and inference speed under challenging underwater conditions, and identify the most suitable method for real-time embedded underwater vision. Experiments used a controlled fish tank, filmed with an OAK-D camera under five natural lighting conditions (09:00–16:00 WIB). Performance was assessed qualitatively and quantitatively on a 600-frame test set (four illumination conditions), computing precision, recall, and mAP@0.5 from YOLOv11 predictions, plus inference speed in frames per second (FPS) on a Raspberry Pi 5 + OAK-D. CLAHE gave the best balance (precision 0.86, recall 0.83, mAP@0.5 0.84, 17 FPS); Gamma + White Balance was slightly less accurate (mAP@0.5 0.82) but faster (19.8 FPS); both outperformed the baseline (mAP@0.5 0.69, 21.3 FPS). Retinex Ultra Lite, UDP Super Lite, and full UDP all fell below 15 FPS (5.8–8.7 FPS), making them unsuitable for real-time edge deployment despite similar or lower accuracy. Lightweight, effective enhancement significantly improves real-time underwater fish detection on embedded devices, with CLAHE identified as the most suitable method for underwater object identification and quantification systems.

Downloads

Download data is not yet available.

References

Amin A, Bahnasy S, Elghamry K, Samir A, Emad A, Darweesh MS, El-Sherif AA. 2021. Real-Time Fish Detection Approach on Self-Built Dataset Based on YOLOv3. 3rd Novel Intelligent and Leading Emerging Sciences Conference (NILES), 23–25 October 2021, Giza, Egypt. 41–46. DOI: https://doi.org/10.1109/NILES53778.2021.9600512.

Aruna S, Deepa N, Devi T. 2023. Underwater Fish Identification in Real-Time Using Convolutional Neural Network. 2023 7th International Conference on Intelligent Computing and Control Systems (ICICCS), 17–19 May 2023, Madurai, India. 586–591. DOI: https://doi.org/10.1109/ICICCS56967.2023.10142531.

Chan CJL, Reyes EJA, Linsangan NB, Juanatas RA. 2022. Real-time Detection of Aquarium Fish Species Using YOLOv4-tiny on Raspberry Pi 4. 2022 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET), 13–15 September 2022, Kota Kinabalu, Malaysia. 1–6. DOI: https://doi.org/10.1109/IICAIET55139.2022.9936790.

Garg D, Garg NK, Kumar M. 2018. Underwater Image Enhancement Using Blending of CLAHE and Percentile Methodologies. Multimedia Tools and Applications. 77(20): 26545–26561. DOI: https://doi.org/10.1007/s11042-018-5878-8.

Khanam R, Hussain M. 2024. YOLOv11: An Overview of the Key Architectural Enhancements. arXiv preprint. arXiv:2410.17725. DOI: https://doi.org/10.48550/arXiv.2410.17725.

Lee J, Hwang K. 2022. YOLO with Adaptive Frame Control for Real-Time Object Detection Applications. Multimedia Tools and Applications. 81: 36375–36396. DOI: https://doi.org/10.1007/s11042-021-11480-0.

Li X, Wei Z, Huang L, Nie J, Zhang W, Wang L. 2018. Real-Time Underwater Fish Tracking Based on Adaptive Multi-Appearance Model. 2018 25th IEEE International Conference on Image Processing (ICIP), 07–10 October 2018, Athens, Greece. 2710–2714. DOI: https://doi.org/10.1109/ICIP.2018.8451469.

Lopez-Marcano S, Jinks EL, Buelow CA, Brown CJ, Wang D, Kusy B, Ditria EM, Connolly RM. 2021. Automatic Detection of Fish and Tracking of Movement for Ecology. Ecology and Evolution. 11(12): 8254–8263. DOI: https://doi.org/10.1002/ece3.7656.

Lu H, Uemura T, Wang D, Zhu J, Huang Z, Kim H. 2020. Deep-Sea Organisms Tracking Using Dehazing and Deep Learning. Mobile Networks and Applications. 25(3): 1008–1015. DOI: https://doi.org/10.1007/s11036-018-1117-9.

Muniraj M, Dhandapani V. 2022. Underwater Image Enhancement by Color Correction and Color Constancy via Retinex for Detail Preserving. Computers and Electrical Engineering. 100: 107909. DOI: https://doi.org/10.1016/j.compeleceng.2022.107909.

Papadakis VM, Papadakis IE, Lamprianidou F, Glaropoulos A, Kentouri M. 2012. A Computer-Vision System and Methodology for the Analysis of Fish Behavior. Aquacultural Engineering. 46: 53–59. DOI: https://doi.org/10.1016/j.aquaeng.2011.11.002.

Powar OG, Wagdarikar N. 2017. A Review: Underwater Image Enhancement Using Dark Channel Prior with Gamma Correction. International Journal of Research in Applied Science and Engineering Technology. 5(3): 421–426. DOI: https://doi.org/10.22214/ijraset.2017.3077.

Sahu P, Gupta N, Sharma N. 2014. A Survey on Underwater Image Enhancement Techniques. International Journal of Computer Applications. 87(13): 19–23. DOI: https://doi.org/10.5120/15268-3743.

Schettini R, Corchs S. 2010. Underwater Image Processing: State of the Art of Restoration and Image Enhancement Methods. EURASIP Journal on Advances in Signal Processing. 746052: 1–14. DOI: https://doi.org/10.1155/2010/746052.

Tang C, von Lukas UF, Vahl M, Wang S, Wang Y, Tan M. 2019. Efficient Underwater Image and Video Enhancement Based on Retinex. Signal, Image, and Video Processing. 13(5): 1011–1018. DOI: https://doi.org/10.1007/s11760-019-01439-y.

Wang H, Zhang S, Zhao S, Wang Q, Li D, Zhao R. 2022. Real-time Detection and Tracking of Fish Abnormal Behavior Based on Improved YOLOV5 and SiamRPN++. Computers and Electronics in Agriculture. 192: 106512. DOI: https://doi.org/10.1016/j.compag.2021.106512.

Wu Q, Guo Y, Hou J, Yuan J, Kong F, Lyu W, Liu Z, Yang W, Liang Q. 2021. Underwater Optical Image Processing Based on Double Threshold Judgements and Optimized Red Dark Channel Prior Method. Multimedia Tools and Applications. 80(19): 29985–30002. DOI: https://doi.org/10.1007/s11042-021-11200-8.

Yang HY, Chen PY, Huang CC, Zhuang YZ, Shiau YH. 2011. Low Complexity Underwater Image Enhancement Based on Dark Channel Prior. 2011 Second International Conference on Innovations in Bio-inspired Computing and Applications, 16–18 December 2011, Shenzhen, China. 17–20. DOI: https://doi.org/10.1109/IBICA.2011.9.

Yusup I, Iqbal M, Jaya I. 2020. Real-time Reef Fishes Identification Using Deep Learning. The 3rd International Conference on Marine Science (ICMS) 2019 "Towards Sustainable Marine Resources and Environment", 4 September 2019, Bogor, Indonesia. IOP Conference Series: Earth and Environmental Science. DOI: https://doi.org/10.1088/1755-1315/429/1/012046.