Chung, Chang-HanChang-HanChungChang, Fi-JohnFi-JohnChang2026-01-152026-01-152012-12-0104921505https://scholars.lib.ntu.edu.tw/handle/123456789/735386The purpose of this study is to count automatically the number of fish in pristine rivers. Traditional investigation methods such as shocking and fishing them are time-consuming and labor-intensive. Even more, those methods can influence the results and may harm the river ecosystem. Recent advances in image processing techniques enable the detecting of moving object through video sequences. In this study, we present a background termed as subtraction-based method in order to count the fish automatically. The experiment is performed in Jin-Gua-Liao River situated in the North of Taiwan and the underwater camera records the fish on the river during daytime and also during the night. In this experiment we perform a total of twenty-seven video samples, which have each a recording time of approximately five minutes. To date there are little references on monitoring river fish. We detail the monitoring method of river fish and provide recommendations to implement this method. Our results show that: (1) our approach is 80% accurate, (2) the studied river fish habitat preference is mainly in the glide environment, (3) the monitoring of fish at night is available, (4) the developed methodology provides not only long-term statistics but also delivers useful information on the fish behavior which is to assist hydrologists and ecological researcher in preserving the ecosystem.zhfalseFish monitorImage processingjournal article2-s2.0-84874182523