[논문]어류의 외부형질 측정 자동화 개발 현황

이명기

doi:10.5657/kfas.2022.0638

어류의 외부형질 측정 자동화 개발 현황
Current Status of Automatic Fish Measurement 원문보기

한국수산과학회지 = Korean journal of fisheries and aquatic sciences, v.55 no.5, 2022년, pp.638 - 644

Abstract ▼ AI-Helper

The measurement of morphological features is essential in aquaculture, fish industry and the management of fishery resources. The measurement of fish requires a large investment of manpower and time. To save time and labor for fish measurement, automated and reliable measurement methods have been developed. Automation was achieved by applying computer vision and machine learning techniques. Recently, machine learning methods based on deep learning have been used for most automatic fish measurement studies. Here, we review the current status of automatic fish measurement with traditional computer vision methods and deep learning-based methods.

주제어

표/그림 (5)

그림 Fig. 1. Conventional fish measurement boards.
그림 Fig. 2. A, An example of the neural network with two hidden layers; B, 2010-2015 ILSVRC (imagenet large scale visual recognition challenge) results and the best networks or companies. Since 2012 AlexNet, deep learning methods were the best.
그림 Fig. 3. A typical CNN architecture for image classification. CNN, Convolution neural network.
그림 Fig. 4. A, Object detection; B, Segmentation.
표 Table 1. A literature review of automated fish measurement

AI 본문요약
AI-Helper

제안 방법

본 총설에서는 어류의 외부 형질을 전통적인 방법으로 측정하는 연구부터 최근 발달한 딥러닝을 활용한 방법까지 다양하게 살펴보았다. 최근 딥러닝 기반의 기계학습은 영상분야 외에도 많은 연구에 활용되고 있다.
최근 딥러닝 기반의 기계학습은 영상분야 외에도 많은 연구에 활용되고 있다. 우리는 최근 활발히 진행되는 딥러닝을 활용한 방법들을 이해하기 위해 AI, 기계학습 및 딥러닝의 기초적인 이론에 대해 살펴보았고 이를 응용한 다양한 기법들에 대해 알아보았다. 국내 연구에서는 전통적 컴퓨터 비전을 활용한 방법에 비해 딥러닝을 활용한 어류 외부 형질 측정 자동화 연구가 아직 활발하지 않은 것을 확인할 수 있었다.

참고문헌 (29)

Alvarez-Ellacuria A, Palmer M, Catalan IA and Lisani J. 2020. Image-based, unsupervised estimation of fish size from commercial landings using deep learning. ICES J Mar Sci 77, 1330-1339. https://doi.org/10.1093/icesjms/fsz216.

상세보기
Badrinarayanan V, Handa A and Cipolla R. 2015. Segnet: A deep convolutional encoder-decoder architecture for robust semantic pixel-wise labelling. Retrieved from https://doi.org/10.48550/arXiv.1505.07293 on Sep 30, 2022.
Chaurasia A and Culurciello E. 2017. Linknet: Exploiting Encoder Representations for Efficient Semantic Segmentation. Retrieved from https://arxiv.org/abs/1707.03718 on Sep 30, 2022.
FAO (Food and Agriculture Organization of the United Nations). 2020. The State of World Fisheries and Aquaculture 2020. FAO, Rome, Italy. https://doi.org/10.4060/ca9229en.
Fernandes AFA, Turra EM, de Alvarenga ER, Passafaro TL, Lopes FB, Alves GFO, Singh V and Rosa GJM. 2020. Deep Learning image segmentation for extraction of fish body measurements and prediction of body weight and carcass traits in Nile tilapia. Comput Electron Agric 170, 105274. https://doi.org/10.1016/j.compag.2020.105274.

상세보기
Garrido-Jurado S, Munoz-Salinas R, Madrid-Cuevas FJ and Marin-Jimenez MJ. 2014. Automatic generation and detection of highly reliable fiducial markers under occlusion. Pattern Recognit 47, 2280-2292. https://doi.org/10.1016/j.patcog.2014.01.005.

상세보기
Han HJ, Kim SJ, Kim TH, Kim MS, Cho MY and Choi HS. 2021. Current status and future directions of fish vaccines in Korea. Korean J Fish Aquat Sci 54, 369-376. https://doi.org/10.5657/KFAS.2021.0369.

원문보기 상세보기
Harvey E, Cappo M, Shortis M, Robson S, Buchanan J and Speare P. 2003. The accuracy and precision of underwater measurements of length and maximum body depth of southern bluefin tuna (Thunnus maccoyii) with a stereovideo camera system. Fish Res 63, 315-326. https://doi.org/10.1016/S0165-7836(03)00080-8.

상세보기
He K, Gkioxari G, Dollar P and Girshick R. 2017. Mask R-CNN. Retrieved from https://doi.org/10.48550/arXiv.1703.06870 on Sep 30, 2022.
He K, Zhang X, Ren S and Sun J. 2015. Deep Residual Learning for Image Recognition. Retrieved from https://arxiv.org/abs/1512.03385 on Sep 30, 2022.
Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M and Adam H. 2017. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. Retrieved from https://doi.org/10.48550/arXiv.1704.04861 on Sep 30, 2022.
Konovalov DA, Saleh A, Efremova DB, Domingos JA and Jerry DR. 2019. Automatic Weight Estimation of Harvested Fish from Images. Retrieved from https://arxiv.org/abs/1909.02710 on Sep 30, 2022.
KOSIS (Korean Statistical Information Service). 2021. Fishery Production Survey: Statistics by Type of Fishery and Species. Retrieved from https://kosis.kr on Sep 30, 2022.
Lee D, Yang Y, Kim S, Choi J, Kang J and Kim H. 2012a. A study on system for measuring morphometric characteristis of fish using morphological image processing. J Kor Soc Fish Tech 48, 469-478. https://doi.org/10.3796/KSFT.2012.48.4.469.

원문보기 상세보기
Lee D, Yang Y, Park S, Cha B, Xu G and Kim J. 2012b. Development of a vaccine automation injection system for flatfish using a template matching. J Kor Soc Fish Tech 48, 165-173, https://doi.org/10.3796/KSFT.2012.48.2.165.

원문보기 상세보기
Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C and Berg AC. 2016. SSD: Single Shot MultiBox Detector. Retrieved from https://arxiv.org/abs/1512.02325 on Sep 30, 2022.
Monkman GG, Hyder K, Kaiser MJ, Vidal FP and Codling E. 2019. Using machine vision to estimate fish length from images using regional convolutional neural networks. Methods Ecol Evol 10, 2045-2056. https://doi.org/10.1111/2041-210X.13282.

상세보기
Park JW, Cho M, Lee UH and Choi HS. 2021. INHV (Infectious Hematopoietic Necrosis Virus): Past, present and future. Korean J Fish Aquat Sci 54, 596-616. https://doi.org/10.5657/KFAS.2021.0596.

원문보기 상세보기
Palmer M, Alvarez-Ellacuria A, Molto V and Catalan IA. 2022. Automatic, operational, high-resolution monitoring of fish length and catch numbers from landings using deep learning. Fish Res 246, 106166. https://doi.org/10.1016/j.fishres.2021.106166.

상세보기
Redmon J, Divvala S, Girshick R and Farhadi A. 2015. You Only Look Once: Unified, Real-Time Object Detection. Retrieved from https://arxiv.org/abs/1506.02640 on Sep 30, 2022.
Ren S, He K, Girshick R and Sun J. 2015. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. Retrieved from https://arxiv.org/abs/1506.01497 on Sep 30, 2022.
Shin Y, Choi H and Choi HS. 2021. Deep learning based fish object detection and tracking for smart aqua farm. J Kor Con A 21, 552-560. https://doi.org/10.5392/JKCA.2021.21.01.552.

원문보기 상세보기
Shvets AA, Rakhlin A, Kalinin AA and Iglovikov VI. 2018. Automatic Instrument Segmentation in Robot-Assisted Surgery Using Deep Learning. Retrieved from https://arxiv.org/abs/1803.01207 on Sep 30, 2022.
Strachan NJC. 1994. Sea trials of a computer vision based fish species sorting and size grading machine. Mechatronics 4, 773-783. https://doi.org/10.1016/0957-4158(94)90052-3.

상세보기
Strachan NJC. 1993. Length measurement of fish by computer vision. Comput Electron Agric 8, 93-104. https://doi.org/10.1016/0168-1699(93)90009-P.

상세보기
Viazzi S, Van Hoestenberghe S, Goddeeris BM and Berckmans D. 2015. Automatic mass estimation of Jade perch Scortum barcoo by computer vision. Aquac Eng 64, 42-48, https://doi.org/10.1016/j.aquaeng.2014.11.003.

상세보기
White DJ, Svellingen C and Strachan NJC. 2006. Automated measurement of species and length of fish by computer vision. Fish Res 80, 203-210. https://doi.org/10.1016/j.fishres.2006.04.009.

상세보기
Yang Y, Lee K, Ji S, Jeong S, Kim K and Park S. 2011. Measurement of size and swimming speed of bluefin tuna (Thunnus thynnus) using by a stereo vision method. J Kor Soc Fish Tech 47, 214-221. https://doi.org/10.3796/KSFT.2011.47.3.214.

원문보기 상세보기
Zoph B and Le QV. 2016. Neural Architecture Search with Reinforcement Learning. Retrieved from https://arxiv.org/abs/1611.01578 on Sep 30, 2022.

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증