Fish Detection and Measurement based on Mask R-CNN
Abstract
Morphological measurements of fish, extracted from their contour, are essential indicators, with applications in the fishing industry as well as for monitoring and preserving species. Thus, automatic contour extraction techniques have been explored, and the development of methods for segmenting fish images is necessary. Therefore, the goal of this work was to develop an approach to automatically measure the length of the fish, using the Mask R-CNN network in the fish segmentation task. Comparing the fish length measurements of the proposed method with the size performed manually, an average relative error of only 2.26% was obtained. Thus, a system for automating this process can be faster, more productive, and more scalable.
References
C. Yu, X. Fan, H. Zhuhua, X. Xia, Y. Zhao, R. Li, and Y. Bai, "Segmentation and measurement scheme for fish morphological features based on mask r-cnn," Information Processing in Agriculture, January 2020.
R. E. X. Meante and C. R. d. C. Dória, "Caracterização da cadeia produtiva da piscicultura no estado de Rondônia: Desenvolvimento e fatores limitantes," Revista de Administração e Negócios da Amazônia, vol. 9, no. 4, pp. 164–181, 2018.
G. Wang, J.-N. Hwang, F. Wallace, and C. Rose, "Multi-scale fish segmentation refinement and missing shape recovery," IEEE Access, vol. 7, pp. 52 836–52 845, January 2019.
H. Yao, Q. Duan, D. Li, and J. Wang, "An improved k-means clustering algorithm for fish image segmentation," Mathematical and Computer Modelling, vol. 58, p. 790–798, August 2013.
T. Bouwmans, S. Javed, M. Sultana, and S. Jung, "Deep neural network concepts for background subtraction: A systematic review and comparative evaluation," Neural Networks, vol. 1, p. 40, May 2019.
R. Mieloszyk and P. Bhargava, "Convolutional neural networks: The possibilities are almost endless," Current Problems in Diagnostic Radiology, vol. 47, January 2018.
M. Sung, S. Yu, and Y. Girdhar, "Vision based real-time fish detection using convolutional neural network," in OCEANS 2017 - Aberdeen, 2017, pp. 1–6.
K. O’Shea and R. Nash, "An introduction to convolutional neural networks," CoRR, vol. abs/1511.08458, 2015.
K. He, G. Gkioxari, P. Dollár, and R. Girshick, "Mask r-cnn," in 2017 IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2980–2988.
"Software LabelImg." [Online]. Available: https://github.com/tzutalin/ labelImg
A. Tiwari, S. Srivastava, and M. Pant, "Brain tumor segmentation and classification from magnetic resonance images: Review of selected methods from 2014 to 2019," Pattern Recognition Letters, vol. 131, November 2019.
R. E. X. Meante and C. R. d. C. Dória, "Caracterização da cadeia produtiva da piscicultura no estado de Rondônia: Desenvolvimento e fatores limitantes," Revista de Administração e Negócios da Amazônia, vol. 9, no. 4, pp. 164–181, 2018.
G. Wang, J.-N. Hwang, F. Wallace, and C. Rose, "Multi-scale fish segmentation refinement and missing shape recovery," IEEE Access, vol. 7, pp. 52 836–52 845, January 2019.
H. Yao, Q. Duan, D. Li, and J. Wang, "An improved k-means clustering algorithm for fish image segmentation," Mathematical and Computer Modelling, vol. 58, p. 790–798, August 2013.
T. Bouwmans, S. Javed, M. Sultana, and S. Jung, "Deep neural network concepts for background subtraction: A systematic review and comparative evaluation," Neural Networks, vol. 1, p. 40, May 2019.
R. Mieloszyk and P. Bhargava, "Convolutional neural networks: The possibilities are almost endless," Current Problems in Diagnostic Radiology, vol. 47, January 2018.
M. Sung, S. Yu, and Y. Girdhar, "Vision based real-time fish detection using convolutional neural network," in OCEANS 2017 - Aberdeen, 2017, pp. 1–6.
K. O’Shea and R. Nash, "An introduction to convolutional neural networks," CoRR, vol. abs/1511.08458, 2015.
K. He, G. Gkioxari, P. Dollár, and R. Girshick, "Mask r-cnn," in 2017 IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2980–2988.
"Software LabelImg." [Online]. Available: https://github.com/tzutalin/ labelImg
A. Tiwari, S. Srivastava, and M. Pant, "Brain tumor segmentation and classification from magnetic resonance images: Review of selected methods from 2014 to 2019," Pattern Recognition Letters, vol. 131, November 2019.
Published
2020-11-07
How to Cite
ROCHA, Wan Song; DORIA, Carolina Rodrigues da Costa; WATANABE, Carolina Yukari Veludo.
Fish Detection and Measurement based on Mask R-CNN. In: WORKSHOP OF UNDERGRADUATE WORKS - CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 33. , 2020, Evento Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2020
.
p. 183-186.
DOI: https://doi.org/10.5753/sibgrapi.est.2020.13007.
