Kraken: Open-Source Computer Vision for Underwater Fish Detection and Measurement
Resumo
Brazil’s extensive river networks, particularly in the Amazon Basin, are characterized by high turbidity and low underwater visibility, presenting significant challenges for aquatic monitoring and fish farming operations. This study introduces Kraken, an open-source computational system designed for automated fish detection, counting, and size estimation in turbid freshwater environments. Kraken integrates state-of-the-art computer vision frameworks—including YOLO, OpenCV, and TensorFlow—with open hardware platforms such as Arduino and Raspberry Pi, enabling cost-effective and scalable deployment. The system employs a pre-trained Inception convolutional neural network for robust fish classification and utilizes image preprocessing techniques to enhance detection accuracy under challenging conditions. Experimental evaluation demonstrates Kraken’s reliability, achieving an average size estimation at a fixed distance of 30 cm and a classification accuracy of up to 90%. By automating fish counting and measurement, Kraken reduces manual labor and operational costs, while its open-source architecture fosters collaborative innovation and adaptability. The results confirm Kraken’s effectiveness for real-world aquatic monitoring, highlighting its potential to advance research and practical applications in fish farming and ecosystem management.
Palavras-chave:
computer system, computer vision, aquatic ecosystem
Referências
W. J. Junk, M. G. M. Soares, and P. B. Bayley, “Freshwater fishes of the amazon river basin: their biodiversity, fisheries, and habitats,” Aquatic Ecosystem Health & Management, 2007.
H. Sioli, The Amazon: limnology and landscape ecology of a mighty tropical river and its basin. Springer Science & Business Media, 2012.
R. B. Barthem and N. N. Fabré, “Biologia e diversidade dos recursos pesqueiros da Amazônia,” A pesca e os recursos pesqueiros na Amazônia brasileira, vol. 1, pp. 17–62, 2004.
G. M. d. Santos and A. C. M. d. Santos, “Sustentabilidade da pesca na Amazônia,” Estudos Avançados, vol. 19, no. 54, pp. 165–182, 2005.
H. Qin, X. Li, J. Liang, Y. Peng, and C. Zhang, “DeepFish: Accurate underwater live fish recognition with a deep architecture,” Neurocomputing, vol. 187, pp. 49–58, 2016.
T. Van Damme, “Computer vision photogrammetry for underwater archaeological site recording in a low-visibility environment,” The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. 40, no. 5, p. 231, 2015.
H. Lu, Y. Li, and S. Serikawa, “Computer vision for ocean observing,” Studies in Computational Intelligence, vol. 672, pp. 1–16, 2017.
D. L. Watson, E. S. Harvey, M. J. Anderson, and G. A. Kendrick, “A comparison of temperate reef fish assemblages recorded by three underwater stereo-video techniques,” Marine Biology, vol. 148, no. 2, pp. 415–425, 2005.
Martin˜Abadi, Ashish˜Agarwal, Paul˜Barham, Eugene˜Brevdo, Zhifeng˜Chen, Craig˜Citro, Greg˜S.˜Corrado, Andy˜Davis, Jeffrey ˜Dean, Matthieu˜Devin, Sanjay˜Ghemawat, Ian˜Goodfellow, Andrew˜Harp, Geoffrey˜Irving, Michael˜Isard, Y. Jia, Rafal˜Jozefowicz, Lukasz˜Kaiser, Manjunath˜Kudlur, Josh˜Levenberg, Dandelion˜Mané, Rajat˜Monga, Sherry˜Moore, Derek˜Murray, Chris˜Olah, Mike˜Schuster, Jonathon˜Shlens, Benoit˜Steiner, Ilya˜Sutskever, Kunal˜Talwar, Paul˜Tucker, Vincent˜Vanhoucke, Vijay˜Vasudevan, Fernanda˜Viégas, Oriol˜Vinyals, Pete˜Warden, Martin˜Wattenberg, Martin˜Wicke, Yuan˜Yu, and Xiaoqiang˜Zheng, “TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems,” 2015. [Online]. Available: [link]
J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
S. Heath, Embedded Systems Design. Elsevier Science, 2002.
E. White, Making Embedded Systems: Design Patterns for Great Software. O’Reilly Media, 2011, vol. 2011.
J. Boxall, Arduino for Arduinians: 70 Projects for the Experienced Programmer. No Starch Press, 2023.
G. Halfacree, The Official Raspberry Pi Beginner’s Guide: How to use your new computer. Raspberry Pi Press, 2023.
R. Szeliski, Computer Vision : Algorithms and Applications. Springer Science & Business Media, 2010, vol. 5.
M. Marengoni and S. Stringhini, “Tutorial: Introdução à visão computacional usando opencv,” Revista de Informática Teórica e Aplicada, 2009.
R. C. Gonzalez, R. E. Woods, and others, Digital image processing. Addison-wesley Reading, 1992.
TensorFlow, “Image classification,” 2023. [Online]. Available: [link]
C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the Inception Architecture for Computer Vision,” CoRR, vol. abs/1512.0, 2015. [Online]. Available: [link]
OpenCV, “Opencv,” 2023. [Online]. Available: [link]
A. Sharma, J. Pathak, M. Prakash, and J. N. Singh, “Object detection using opencv and python,” in 3rd International Conference on Advances in Computing, Communication Control and Networking (ICAC3N), 2021.
M. Marengoni and D. Stringhini, “High level computer vision using opencv,” in 2011 24th SIBGRAPI Conference on Graphics, Patterns, and Images Tutorials, 2011, pp. 11–24.
P. Jiang, D. Ergu, F. Liu, Y. Cai, and B. Ma, “A review of yolo algorithm developments,” Procedia Computer Science, 2022, the 8th International Conference on Information Technology and Quantitative Management: Developing Global Digital Economy after COVID-19.
P. Agrawal, G. Jain, S. Shukla, S. Gupta, D. Kothari, R. Jain, and N. Malviya, “Yolo algorithm implementation for real time object detection and tracking,” in 2022 IEEE Students Conference on Engineering and Systems (SCES), 2022, pp. 01–06.
C. Cortes and V. Vapnik, “Support vector machine,” Machine learning, vol. 20, no. 3, pp. 273–297, 1995.
M. C. Chuang, J. N. Hwang, and K. Williams, “A feature learning and object recognition framework for underwater fish images,” IEEE Transactions on Image Processing, vol. 25, no. 4, pp. 1862–1872, 2016.
G. L. Foresti and S. Gentili, “A Vision Based System for Object Detection in Underwater Images,” International Journal of Pattern Recognition and Artificial Intelligence, no. 02, 2000.
S. Bazeille, I. Quidu, L. Jaulin, and J.-P. Malkasse, “Automatic underwater image pre-processing,” in Caracterisation Du Milieu Marin (CMM). HAL open science, 2006. [Online]. Available: [link]
N. Nachar, “The Mann-Whitney U: A test for assessing whether two independent samples come from the same distribution,” Tutorials in quantitative Methods for Psychology, vol. 4, no. 1, pp. 13–20, 2008.
A. Bewley, Z. Ge, L. Ott, F. Ramos, and B. Upcroft, “Simple online and realtime tracking,” in IEEE International Conference on Image Processing (ICIP), 2016.
H. Sioli, The Amazon: limnology and landscape ecology of a mighty tropical river and its basin. Springer Science & Business Media, 2012.
R. B. Barthem and N. N. Fabré, “Biologia e diversidade dos recursos pesqueiros da Amazônia,” A pesca e os recursos pesqueiros na Amazônia brasileira, vol. 1, pp. 17–62, 2004.
G. M. d. Santos and A. C. M. d. Santos, “Sustentabilidade da pesca na Amazônia,” Estudos Avançados, vol. 19, no. 54, pp. 165–182, 2005.
H. Qin, X. Li, J. Liang, Y. Peng, and C. Zhang, “DeepFish: Accurate underwater live fish recognition with a deep architecture,” Neurocomputing, vol. 187, pp. 49–58, 2016.
T. Van Damme, “Computer vision photogrammetry for underwater archaeological site recording in a low-visibility environment,” The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. 40, no. 5, p. 231, 2015.
H. Lu, Y. Li, and S. Serikawa, “Computer vision for ocean observing,” Studies in Computational Intelligence, vol. 672, pp. 1–16, 2017.
D. L. Watson, E. S. Harvey, M. J. Anderson, and G. A. Kendrick, “A comparison of temperate reef fish assemblages recorded by three underwater stereo-video techniques,” Marine Biology, vol. 148, no. 2, pp. 415–425, 2005.
Martin˜Abadi, Ashish˜Agarwal, Paul˜Barham, Eugene˜Brevdo, Zhifeng˜Chen, Craig˜Citro, Greg˜S.˜Corrado, Andy˜Davis, Jeffrey ˜Dean, Matthieu˜Devin, Sanjay˜Ghemawat, Ian˜Goodfellow, Andrew˜Harp, Geoffrey˜Irving, Michael˜Isard, Y. Jia, Rafal˜Jozefowicz, Lukasz˜Kaiser, Manjunath˜Kudlur, Josh˜Levenberg, Dandelion˜Mané, Rajat˜Monga, Sherry˜Moore, Derek˜Murray, Chris˜Olah, Mike˜Schuster, Jonathon˜Shlens, Benoit˜Steiner, Ilya˜Sutskever, Kunal˜Talwar, Paul˜Tucker, Vincent˜Vanhoucke, Vijay˜Vasudevan, Fernanda˜Viégas, Oriol˜Vinyals, Pete˜Warden, Martin˜Wattenberg, Martin˜Wicke, Yuan˜Yu, and Xiaoqiang˜Zheng, “TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems,” 2015. [Online]. Available: [link]
J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
S. Heath, Embedded Systems Design. Elsevier Science, 2002.
E. White, Making Embedded Systems: Design Patterns for Great Software. O’Reilly Media, 2011, vol. 2011.
J. Boxall, Arduino for Arduinians: 70 Projects for the Experienced Programmer. No Starch Press, 2023.
G. Halfacree, The Official Raspberry Pi Beginner’s Guide: How to use your new computer. Raspberry Pi Press, 2023.
R. Szeliski, Computer Vision : Algorithms and Applications. Springer Science & Business Media, 2010, vol. 5.
M. Marengoni and S. Stringhini, “Tutorial: Introdução à visão computacional usando opencv,” Revista de Informática Teórica e Aplicada, 2009.
R. C. Gonzalez, R. E. Woods, and others, Digital image processing. Addison-wesley Reading, 1992.
TensorFlow, “Image classification,” 2023. [Online]. Available: [link]
C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the Inception Architecture for Computer Vision,” CoRR, vol. abs/1512.0, 2015. [Online]. Available: [link]
OpenCV, “Opencv,” 2023. [Online]. Available: [link]
A. Sharma, J. Pathak, M. Prakash, and J. N. Singh, “Object detection using opencv and python,” in 3rd International Conference on Advances in Computing, Communication Control and Networking (ICAC3N), 2021.
M. Marengoni and D. Stringhini, “High level computer vision using opencv,” in 2011 24th SIBGRAPI Conference on Graphics, Patterns, and Images Tutorials, 2011, pp. 11–24.
P. Jiang, D. Ergu, F. Liu, Y. Cai, and B. Ma, “A review of yolo algorithm developments,” Procedia Computer Science, 2022, the 8th International Conference on Information Technology and Quantitative Management: Developing Global Digital Economy after COVID-19.
P. Agrawal, G. Jain, S. Shukla, S. Gupta, D. Kothari, R. Jain, and N. Malviya, “Yolo algorithm implementation for real time object detection and tracking,” in 2022 IEEE Students Conference on Engineering and Systems (SCES), 2022, pp. 01–06.
C. Cortes and V. Vapnik, “Support vector machine,” Machine learning, vol. 20, no. 3, pp. 273–297, 1995.
M. C. Chuang, J. N. Hwang, and K. Williams, “A feature learning and object recognition framework for underwater fish images,” IEEE Transactions on Image Processing, vol. 25, no. 4, pp. 1862–1872, 2016.
G. L. Foresti and S. Gentili, “A Vision Based System for Object Detection in Underwater Images,” International Journal of Pattern Recognition and Artificial Intelligence, no. 02, 2000.
S. Bazeille, I. Quidu, L. Jaulin, and J.-P. Malkasse, “Automatic underwater image pre-processing,” in Caracterisation Du Milieu Marin (CMM). HAL open science, 2006. [Online]. Available: [link]
N. Nachar, “The Mann-Whitney U: A test for assessing whether two independent samples come from the same distribution,” Tutorials in quantitative Methods for Psychology, vol. 4, no. 1, pp. 13–20, 2008.
A. Bewley, Z. Ge, L. Ott, F. Ramos, and B. Upcroft, “Simple online and realtime tracking,” in IEEE International Conference on Image Processing (ICIP), 2016.
Publicado
22/10/2025
Como Citar
GOHL, Pedro; ROCHA, Herbert; LOBO, Felipe; BALICO, Leandro.
Kraken: Open-Source Computer Vision for Underwater Fish Detection and Measurement. In: CONGRESSO LATINO-AMERICANO DE SOFTWARE LIVRE E TECNOLOGIAS ABERTAS (LATINOWARE), 22. , 2025, Foz do Iguaçu/PR.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 263-272.
DOI: https://doi.org/10.5753/latinoware.2025.16326.
