A Review of Research on Fish Feeding Behavior Based on Computer Vision

DOI: https://doi.org/10.62517/jbdc.202501107

Author(s)

Yongchao Yang, Liangquan Jia, Wei Long, Linhua Jiang*

Affiliation(s)

School of Information Engineering, Huzhou University, Huzhou, China *Corresponding Author.

Abstract

With the development of aquaculture, monitoring fish feeding behavior is crucial for breeding efficiency and resource utilization. Traditional manual observation methods are inefficient and subjective, while computer vision technology provides a new solution for real-time quantitative analysis of fish feeding behavior. This article summarizes the key steps in monitoring fish feeding behavior, including fish species selection, image information collection methods, and details various quantitative methods applicable to feeding behavior analysis, such as area method, behavior feature statistics, image texture features, and Delaunay triangulation method. These methods each have their own advantages and can adapt to different research needs. Deeply understanding and quantifying the feeding patterns of fish not only helps optimize aquaculture management and improve resource utilization, but also provides scientific basis for ecological protection.

Keywords

Computer Vision; Fish; Feeding Behavior; Monitor; Quantitative Algorithm

References

[1] Li Daoliang, Liu Chang. Analysis of the application of artificial intelligence in aquaculture and future prospects. Smart Agriculture, 2020, 2(3): 1. [2] He Jia, Huang Zhitao, Song Xiefan, et al. Advances in fish behavior recognition and quantification based on computer vision technology in aquaculture. Modern Fisheries, 2019, 46(3): 7-14. [3] Li Daoliang, Wang Zhiqiang, Wu Sheng, et al. Automatic recognition methods of fish feeding behavior in aquaculture: A review. Aquaculture, 2020, 528: 735508. [4] Wang Li, Chen Qiuwen, Chen Kai, et al. Study on target fish selection for ecological flow in the Huai River. Acta Scientiae Circumstantiae, 2017, 37(6): 2379-2386. [5] Fu Shijian, Cao Zhendong, Xie Xiaojun. Advances in research on fish feeding metabolism and movement metabolism. Chinese Journal of Zoology, 2008, 43(2): 150-159. [6] Lu Huanda, Liu Ying, Fan Lizhong. Design and implementation of an automatic fish behavior monitoring system based on computer vision. Modern Fisheries, 2011 (1): 19-23. [7] Cao Xiaohui, Liu Huang. Research progress and applications of feature extraction of feeding behavior in cultured fish. Modern Fisheries, 2021, 48(2): 1-8. [8] Cao Yuyin. Research on the use of computer vision to quantify fish behavior. Agriculture and Technology, 2022. [9] Watson D L, Harvey E S, Anderson M J, et al. A comparison of temperate reef fish assemblages recorded by three underwater stereo-video techniques. Marine Biology, 2005, 148: 415-425. [10] Guo Qiang, Yang Xinting, Zhou Chao, et al. A method for detecting fish feeding status based on shape and texture features. Aquaculture Technology, 2018. [11]Zhou Chao, Xu Daming, Lin Kai, et al. Research on fish feeding intensity assessment using near-infrared machine vision. Smart Agriculture, 2019, 1(1): 76. [12]Hu Liyong, Wei Yuyan, Zheng Di, et al. Research on intelligent baiting methods based on machine vision technology. Journal of Tropical Oceanography, 2015, 34(4): 90-95. [13]Liu Ziyi. Research on automatic grading of Atlantic salmon flesh color and feeding activity measurement based on computer vision. Aquaculture Engineering, 2013. [14]Zhao Jian. Precision feeding of swimming fish in recirculating aquaculture systems. Hangzhou: Zhejiang University, 2018. [15]Yu Xin, Hou Xiaojiao, Lu Huanda, et al. Detection of abnormal fish behavior based on optical flow and feature statistics. Transactions of the Chinese Society of Agricultural Engineering, 2014, 30(2): 162-168. [16]Gao Chengcheng, Hui Xiaowei. Texture feature extraction based on gray-level co-occurrence matrix. Computer Systems & Applications, 2010, 19(6): 195-198. [17]Guo Dejun, Song Zicun. Research on texture image classification based on gray-level co-occurrence matrix. Forestry Machinery and Woodworking Equipment, 2005, 33(7): 21-23. [18]Torisawa S, Kadota M, Komeyama K, et al. A digital stereo-video camera system for three-dimensional monitoring of free-swimming Pacific bluefin tuna, Thunnus orientalis, cultured in a net cage. Aquatic Living Resources, 2011, 24(2): 107-112. [19]Zhou Chao, Zhang Bin, Lin Kai, et al. Near-infrared imaging to quantify the feeding behavior of fish in aquaculture. Computers and Electronics in Agriculture, 2017, 135: 233-241. [20]Cao Haiyang. Detection of fish feeding behavior and precision feeding decision-making based on deep learning. Jiangsu University, 2023. [21]Liu Ying, Pang Yuliang, Zhang Weidong, etc Image classification technology based on active learning: current status and future. Journal of Electronic Science, 2023, 51(10): 2960-2984. [22]Lei Gaohui, Liu Feng, Dong Xiaoning, etc Research progress on intelligent feeding technology in aquaculture. Feed Industry, 2024, 45 (14) [23]Zhao Siqi and Ding Weimin Research progress on key technologies for precision feeding in aquaculture. Journal of Intelligent Agricultural Equipment (Chinese and English), 2023, 4(1): 42