스마트미디어저널 (Smart Media Journal)

  • 제12권3호
  • /
  • Pages.112-119
  • /
  • 2023
  • /
  • 2287-1322(pISSN)
  • /
  • 2288-9671(eISSN)
한국스마트미디어학회 (THE KOREAN INSTITUTE OF SMART MEDIA)
권호 표지
DOI QR코드

DOI QR Code

Size Estimation for Shrimp Using Deep Learning Method

  • Heng Zhou (Department of Electronics and Information Engineering, Jeonbuk National University) ;
  • Sung-Hoon Kim (Department of Electronics and Information Engineering, Jeonbuk National University) ;
  • Sang-Cheol Kim (Core Institute of Intelligent Robots, Jeonbuk National University) ;
  • Cheol-Won Kim (Korea National University of Agriculture and Fisheries) ;
  • Seung-Won Kang (Daesang The Fishingunion corporation)
  • 투고 : 2022.10.07
  • 심사 : 2023.03.08
  • 발행 : 2023.04.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Shrimp farming has been becoming a new source of income for fishermen in South Korea. It is often necessary for fishers to measure the size of the shrimp for the purpose to understand the growth rate of the shrimp and to determine the amount of food put into the breeding pond. Traditional methods rely on humans, which has huge time and labor costs. This paper proposes a deep learning-based method for calculating the size of shrimps automatically. Firstly, we use fine-tuning techniques to update the Mask RCNN model with our farm data, enabling it to segment shrimps and generate shrimp masks. We then use skeletonizing method and maximum inscribed circle to calculate the length and width of shrimp, respectively. Our method is simple yet effective, and most importantly, it requires a small hardware resource and is easy to deploy to shrimp farms.

키워드

과제정보

This research was supported by Korea Institute of Marine Science & Technology Promotion (KIMST) funded by the Ministry of Oceans and Fisheries (20210460).

참고문헌

  1. Seong, Hoon Je, Jin Ju Kim, Taeyune Kim, Sung Jae Ahn, Mina Rho, and Woo Jun Sul, "A case study on the distribution of the environmental resistome in Korean shrimp farms," Ecotoxicology and Environmental Safety, 227 (2021): 112858
  2. KWON, Woo-Taeg, Min-Jae JUNG, Hyun-Jin Woo, Woo-Sik LEE and Lee-Seung KWON, "Effect of Improving Quality by Changing the Distribution Method of Shrimp Culture," Journal of Distribution Science, vol. 19, no. 4 (April 30, 2021): 53-60
  3. Roy, Luke A., D. Allen Davis and Gregory N. Whitis, "Effect of feeding rate and pond primary productivity on growth of Litopenaeus vannamei reared in inland saline waters of West Alabama," North American Journal of Aquaculture, vol. 74, no. 1 (2012): 20-26 https://doi.org/10.1080/15222055.2011.638416
  4. He, Kaiming, Georgia Gkioxari, Piotr Dollar and Ross Girshick, "Mask r-cnn," In Proceedings of the IEEE international conference on computer vision, pp. 2961-2969, 2017
  5. Harbitz, Alf, "Estimation of shrimp (Pandalus borealis) carapace length by image analysis," ICES Journal of Marine Science, vol. 64, no. 5 (2007): 939-944 https://doi.org/10.1093/icesjms/fsm047
  6. Zhou, Heng and Sang-Cheol Kim, "Estimation of shrimp's size based on 3D instance segmentation using deep learning technology," Proceedings of the Korean Conference on Control and Robot System, pp.311-312
  7. Zhang, Tongjie Y. and Ching Y. Suen, "A fast parallel algorithm for thinning digital patterns," Communications of the ACM, vol. 27, no. 3 (1984): 236-239 https://doi.org/10.1145/357994.358023
  8. Wu, Yuxin, Alexander Kirillov, Francisco Massa, Wan-Yen Lo and Ross Girshick, "Detectron2," https://github.com/facebookresearch/detectron2 (accessed Oct., 22, 2022)
  9. Lin, Tsung-Yi, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollar and C. Lawrence Zitnick, "Microsoft coco: Common objects in context," In European conference on computer vision, pp. 740-755, Springer, Cham, 2014
  10. Everingham, Mark, Luc Van Gool, Christopher KI Williams, John Winn and Andrew Zisserman, "The pascal visual object classes (voc) challenge," International journal of computer vision, vol. 88, no. 2 (2010): 303-338 https://doi.org/10.1007/s11263-009-0275-4