Optimizing Coral Fish Detection: Faster R-CNN, SSD MobileNet, YOLOv5 Comparison


Syifa Afnani Santoso(1*), Indra Jaya(2), Karlisa Priandana(3)

(1) IPB University
(2) IPB University
(3) IPB University
(*) Corresponding Author


This study underscores the critical role of accurate Chaetodontidae fish abundance observations, particularly in assessing coral reef health. By integrating deep learning algorithms (Faster R-CNN, SSD-MobileNet, and YOLOv5) into Autonomous Underwater Vehicles (AUVs), the research aims to expedite fish identification in aquatic environments. Evaluating the algorithms, YOLOv5 emerges with the highest accuracy, followed by Faster R-CNN and SSD-MobileNet. Despite this, SSD-MobileNet showcases superior computational speed with a mean average precision (mAP) of around 92.21% and a framerate of about 1.24 fps. Furthermore, employing the Coral USB Accelerator enhances computational speed on the Raspberry Pi 4, enabling real-time detection capabilities. This study incorporates centroid tracking, facilitating accurate counting by assigning unique IDs to identified objects per class. Ultimately, the real-time implementation of the system achieves 87.18% accuracy and 87.54% precision at 30 fps, empowering AUVs to conduct real-time fish detection and tracking, thereby significantly contributing to underwater research and conservation efforts.


Object detection; Faster R-CNN; SSD MobileNet; YOLOv5; Centroid tracking

Full Text:



[1] A. J. Woodhead, C. C. Hicks, A. V. Norstrom, G. J. Williams, and N. A. J. Graham, “Coral reef ecosystem services in the Anthropocene”, Coral Reef Functional Ecology in the Anthropocene, vol. 33, no. 6, pp. 1023-1034, Mar. 2019 [Online]. Available: https://doi.org/10.1111/1365-2435.13331

[2] A. Tuwo, and J. Tresnati, “Coral reef ecosystem” in Advances in Biological Sciences and Biotechnology, vol. 1, Y. Singh, India: Integrated Publications, 2020, pp. 75-104. Available: https://www.researchgate.net/publication/349485597_Coral_Reef_Ecosystem

[3] L. Fudjaja et al., “Anthropogenic activity and the destruction of coral reefs in the waters of small islands”, in IOP Conf. Series: Earth and Environmental Science, 2020, pp. 1-8. Available: https://iopscience.iop.org/article/10.1088/1755-1315/575/1/012057

[4] R. Iskandar, K. Z. Soemarno, and D. G. R. Wiadnya, “Coral reef condition with Chaetodontidae fish as the indicators in the waters of the Samber Gelap island of Kotabaru, South Kalimantan”, RJOAS, vol. 11, no. 107, Nov. 2020 [Online]. Available: https://doi.org/10.18551/rjoas.2020-11.10

[5] E. S. Reese, “Predation on Corals by Fishes of the Family Chaetodontidae: Implications for Conservation and Management of Coral Reef Ecosystems”, Bulletin of Marine Science, vol. 31, no. 3, pp. 594-604, Jul. 1981 [Online]. Available: https://www.ingentaconnect.com/content/umrsmas/bullmar/1981/00000031/00000003/art00011

[6] K. Wibowo, M. Adrim, and P. C. Makatipu, “Community structure of Chaetodontidae in the west of Banda Sea”, Mar. Res. Indonesia, vol. 38, no. 1, pp. 1-8, Feb. 2013 [Online]. Available: http://dx.doi.org/10.14203/mri.v38i1.51

[7] S. English, C. Wilkinson, and V. Baker, “Survey manual for tropical marine resources,” Townsville: Australian Institute of Marine Sciences, 1997. Available: https://www.aims.gov.au/sites/default/files/Survey%20Manual-sm01.pdf

[8] S. Villon et al., “A deep learning method for accurate and fast identification of coral reef fishes in underwater images,” Ecological Informatics, vol. 48, pp. 238-244, Nov. 2018 [Online]. Available: https://doi.org/10.1016/j.ecoinf.2018.09.007

[9] D. Pelletier, K. Leleu, G. Mou-tham, N. Guillemot, and P. Chabanet, “Comparison of visual census and high definition video transects for monitoring coral reef fish assemblages,” Fisheries Research, vol. 107, no. 1-3, pp. 84-93, Jan. 2011 [Online]. Available: https://doi.org/10.1016/j.fishres.2010.10.011

[10] W. Xu and S. Watzner, “Underwater fish detection using deep learning for water power applications,” in 2018 International Conference on Computational Science and Computational Intelligence (CSCI), Nov. 2018, pp. 313-318 [Online]. Available: https://doi.org/10.1109/CSCI46756.2018.00067

[11] F. Han, J. Yao, H. Zhu, and C. Wang, “Underwater image processing and object detection based on deep CNN method,” Journal of Sensors, vol. 2020, pp. 1-20, May 2020 [Online]. Available: https://doi.org/10.1155/2020/6707328

[12] A. M. Munoz, M.-J. Moron-Fernandez, D. Cascado-Caballero, F. Diaz-del-Rio, and P. Real, “Autonomous Underwater Vehicles: Identifying Critical Issues and Future Perspectives in Image Acquisition,” Sensors, vol. 23, no. 10, pp. 1-27, May 2023 [Online]. Available: https://doi.org/10.3390/s23104986

[13] U. Alganci, M. Soydas, and E. Sertel, “Comparative research on deep learning approaches for airplane detection from very high-resolution satellite images,” Remote Sensing, vol. 12, no. 3, pp. 1-28, Feb. 2020 [Online]. Available: https://doi.org/10.3390/rs12030458

[14] R. Xu, H. Lin, K. Lu, L. Cao, and Y. Liu, “A forest fire detection system based on ensemble learning,” Forests, vol. 12, no. 2, pp. 1-17, Feb. 2021 [Online]. Available: https://doi.org/10.3390/f12020217

[15] A. Bakliwal et al., “Crowd counter: an application of centroid tracking algorithm,” International Research Journal of Modernization to Engineering Technology and Science, vol. 2, no. 4, pp. 1138-1141, April 2020 [Online]. Available: https://www.irjmets.com/uploadedfiles/paper/volume2/issue_4_april_2020/868/1628083008.pdf

[16] Purwono, A. Ma’arif, W. Rahmaniar, H. I. K. Fathurrahman, A. Z. K. Frisky, and Q. M. Haq, “Understanding Convolutional Neural Network (CNN): A Review,” International Journal of Robotics and Control Systems, vol. 2, no. 4, pp. 739-748, Dec. 2022 [Online]. Availabe: https://doi.org/10.31763/ijrcs.v2i4.888

[17] M. M. Fahmy, “Confusion Matrix in Binary Classification Problems: A Step-by-Step Tutorial,” Journal of Engineering Research, vol. 6, no. 5, pp. T1-T12, Dec. 2022 [Online]. Available: https://dx.doi.org/10.21608/erjeng.2022.274526

[18] R. Padilla, S. L. Netto, and E. A. B. da Silva, "A Survey on Performance Metrics for Object-Detection Algorithms," in 2020 International Conference on Systems, Signals and Image Processing (IWSSIP), Jul. 2020, pp. 237-242. Available: https://doi.org/10.1109/IWSSIP48289.2020.9145130

[19] D. Choe, E. Choi, and D. K. Kim, “The real-time mobile application for classifying of endangered parrot species using the cnn models based on transfer learning,” Deep Learning in Mobile Information System, vol. 2020, pp. 1-13, Mar. 2020 [Online]. Available: https://doi.org/10.1155/2020/1475164

[20] S. Sterckval, “Google Coral Edge TPU vs NVIDIA Jetson Nano: a quick deep dive into EdgeAI performance,” 2019 [Online]. Available: https://medium.com/@samsterckval/google-coral-edge-tpu-vs-nvidia-jetson-nano-a-quick-deep-dive-into-edgeai-performance-bc7860b8d87a. [Accessed: 18-Jun-2023]

DOI: https://doi.org/10.22146/ijccs.95011

Article Metrics

Abstract views : 1181 | views : 519


  • There are currently no refbacks.

Copyright (c) 2024 IJCCS (Indonesian Journal of Computing and Cybernetics Systems)

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Copyright of :
IJCCS (Indonesian Journal of Computing and Cybernetics Systems)
ISSN 1978-1520 (print); ISSN 2460-7258 (online)
is a scientific journal the results of Computing
and Cybernetics Systems
A publication of IndoCEISS.
Gedung S1 Ruang 416 FMIPA UGM, Sekip Utara, Yogyakarta 55281
Fax: +62274 555133
email:ijccs.mipa@ugm.ac.id | http://jurnal.ugm.ac.id/ijccs

View My Stats1
View My Stats2