Open AccessAutomatic counting methods in aquaculture: A review
Author(s) -
Li Daoliang,
Miao Zheng,
Peng Fang,
Wang Liang,
Hao Yinfeng,
Wang Zhenhu,
Chen Tao,
Li Hui,
Zheng Yingying
Publication year - 2021
Publication title -
journal of the world aquaculture society
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.655
H-Index - 60
eISSN - 1749-7345
pISSN - 0893-8849
DOI - 10.1111/jwas.12745
Subject(s) - aquaculture , underwater , biology , object (grammar) , fishery , population , object detection , fish <actinopterygii> , computer science , marine engineering , artificial intelligence , oceanography , pattern recognition (psychology) , engineering , demography , sociology , geology
Abstract Object counting in aquaculture is an important task, and has been widely applied in fish population estimation, estimation of lobster abundance and scallop stocks, and so forth. However, underwater object counting is challenging for biologists and marine scientists because of the diversity of backgrounds of the lake or ocean, the uncertainty of the object motion, and the occlusion between objects. With the rapid development of sensor, computer vision, and acoustic technologies, advanced and efficient counting methods are available in aquaculture. We reviewed underwater object counting methods in aquaculture, provided a survey including more than 50 articles in the recent 10 years, and analyzed the pros and cons of the counting methods and the applicable scenarios of those methods. Finally, the major challenges and future trends of underwater object counting in aquaculture are discussed.