An Approach for Fish Detection in Underwater Images

  • Laura A. Martinho UFAM
  • Odalisio L. S. Neto UFAM
  • João M. B. Calvalcanti UFAM
  • José L. S. Pio UFAM
  • Felipe G. Oliveira UFAM

Resumo


Underwater images are widely used for understanding subaquatic environments. However, underwater images are severely degraded by light absorption and scattering, as it propagates in water during image acquisition causing color distortion, low contrast and noise. These problems can interfere in underwater vision tasks, such as recognition and detection. In this paper we propose an approach for fish detection in underwater environments. In order to achieve this goal, the proposed method is composed by two main steps: i) Image Restoration, processing the underwater images to enhance the image quality; and ii) Fish Detection, to identify the presence of fish in underwater images. Additionally, in this paper we introduce an underwater image dataset with the presence of fish. Through the experimental process using the proposed dataset, the obtained results demonstrate the precision and robustness of the proposed approach, achieving accuracy of 98.04% in the fish detection task.

Palavras-chave: Underwater images, Fish detection, Underwater image restoration, YOLO-NAS

Referências

Q. Jiang, Y. Zhang, F. Bao, X. Zhao, C. Zhang, and P. Liu, “Two-step domain adaptation for underwater image enhancement,” Pattern Recognition, vol. 122, p. 108324, 2022.

S. Sun, H. Wang, H. Zhang, M. Li, M. Xiang, C. Luo, and P. Ren, “Underwater image enhancement with reinforcement learning,” IEEE Journal of Oceanic Engineering, pp. 1–13, 2022.

X. Wang, X. Jiang, Z. Xia, and X. Feng, “Underwater object detection based on enhanced yolo,” in 2022 Int. Conf. on Image Processing and Media Computing, 2022, pp. 17–21.

H. Yang, Y. Shi, and X. Wang, “Detection method of fry feeding status based on yolo lightweight network by shallow underwater images,” Electronics, vol. 11, p. 3856, 2022.

A. A. Muksit, F. Hasan, M. F. Hasan Bhuiyan Emon, M. R. Haque, A. R. Anwary, and S. Shatabda, “Yolo-fish: A robust fish detection model to detect fish in realistic underwater environment,” Ecological Informatics, vol. 72, p. 101847, 2022.

A. Kuswantori, T. Suesut, W. Tangsrirat, G. Schleining, and N. Nunak, “Fish detection and classification for automatic sorting system with an optimized yolo algorithm,” Applied Sciences, vol. 13, no. 6, 2023.

X. Wang, X. Jiang, Z. Xia, and X. Feng, “Underwater object detection based on enhanced yolo,” in 2022 Int. Conf. on Image Processing and Media Computing, 2022, pp. 17–21.

R. Liu, X. Fan, M. Zhu, M. Hou, and Z. Luo, “Real-world underwater enhancement: Challenges, benchmarks, and solutions under natural light,” IEEE Trans. on Circuits and Systems for Video Technology, vol. 30, no. 12, pp. 4861–4875, 2020.

L. A. Martinho, F. G. Oliveira, J. M. B. Cavalcanti, and J. L. S. Pio, “Underwater image enhancement based on fusion of intensity transformation techniques,” in Latin American Robotics Symp., 2022.

M. J. Islam, Y. Xia, and J. Sattar, “Fast underwater image enhancement for improved visual perception,” IEEE Robotics and Automation Letters, vol. 5, no. 2, pp. 3227–3234, 2020.

C. Li, S. Anwar, and F. Porikli, “Underwater scene prior inspired deep underwater image and video enhancement,” Pattern Recognition, 2020.

S. Li, B. Pan, Y. Cheng, X. Yan, C. Wang, and C. Yang, “Underwater fish object detection based on attention mechanism improved ghost-yolov5,” in 2022 7th Int. Conf. on Intelligent Computing and Signal Processing (ICSP), 2022, pp. 599–603.

A. F. Ayob, K. Khairuddin, Y. M. Mustafah, A. R. Salisa, and K. Kadir, “Analysis of pruned neural networks (mobilenetv2-yolo v2) for underwater object detection,” in 11th National Technical Seminar on Unmanned System Technology 2019. Springer Nature Singapore, 2021, pp. 87–98.

W. S. Q. H. Minghua Zhang, Shubo Xu and Q. Wei., “”lightweight underwater object detection based on yolo v4 and multi-scale attentional feature fusion”,” in Remote Sensing, vol. 13, no. 22, 2021.

J.-H. Park and C. Kang, “A study on enhancement of fish recognition using cumulative mean of yolo network in underwater video images,” Journal of Marine Science and Engineering, vol. 8, p. 952, 2020.

Z. Wang, H. Liu, G. Zhang, X. Yang, L. Wen, and W. Zhao, “Diseased fish detection in the underwater environment using an improved yolov5 network for intensive aquaculture,” Fishes, vol. 8, no. 3, 2023.

S. Sun, H. Wang, H. Zhang, M. Li, M. Xiang, C. Luo, and P. Ren, “Underwater image enhancement with reinforcement learning,” IEEE Journal of Oceanic Engineering, pp. 1–13, 2022.

J.-M. M. A. B. P. Nicolas Limare, Jose-Luis Lisani and C. Sbert, “Simplest color balance,” IPOL Journal, pp. 297–315, 2011.

Y.-T. Peng and P. Cosman, “Underwater image restoration based on image blurriness and light absorption,” IEEE Transactions on Image Processing, vol. PP, p. 1, 2017.

F. M. S. B. M. C. P. Drews-Jr, E. Nascimento, “Transmission estimation in underwater single images,” IEEE ICCV - Workshop on Underwater Vision, p. 825–830, 2013.
Publicado
13/11/2023
MARTINHO, Laura A.; NETO, Odalisio L. S.; CALVALCANTI, João M. B.; PIO, José L. S.; OLIVEIRA, Felipe G.. An Approach for Fish Detection in Underwater Images. In: WORKSHOP DE VISÃO COMPUTACIONAL (WVC), 18. , 2023, São Bernardo do Campo/SP. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2023 . p. 6-11. DOI: https://doi.org/10.5753/wvc.2023.27524.