-
- Komeyama Kazuyoshi
- Faculty of Fisheries Sciences, Hokkaido University
-
- Tanaka Tatsuya
- Graduate School of Fisheries Sciences, Hokkaido University
-
- Yamaguchi Takeharu
- FURUNO Electric Co., Ltd.
-
- Asaumi Shigeru
- FURUNO Electric Co., Ltd.
-
- Torisawa Shinsuke
- Department of Agriculture, Kindai University
-
- Takagi Tsutomu
- Faculty of Fisheries Sciences, Hokkaido University
この論文をさがす
抄録
<p>For aquaculture management, aquaculture farmers require a new, inexpensive device that can obtain the size of a fish without touching them, replacing the conventional spoon-net sampling method. Conventional sampling involves the risks of physical injury and mental stress to the fish, which may affect their growth rate and mortality. Therefore, we developed methods for monitoring the size of fish, considering red sea bream (RSB) aquaculture, using commercially available cameras. This study evaluates the sample size using the estimated mean fork length value in a cage, and its value is approximately 20 samples with a 2% error rate for a fork length of greater than 30 cm. We measured the fish fork length under water in the cage using both stereo vision and net-sampling methods simultaneously. The examination demonstrated that for RSB aquaculture, the estimated values of fork length from the two methods have no statistical difference. This result implies that our stereo vision system can be effectively applied to monitor RSB growth.</p>
収録刊行物
-
- Journal of Robotics and Mechatronics
-
Journal of Robotics and Mechatronics 30 (2), 231-237, 2018-04-20
富士技術出版株式会社
- Tweet
詳細情報 詳細情報について
-
- CRID
- 1390564238036753920
-
- NII論文ID
- 130007498580
-
- NII書誌ID
- AA10809998
-
- ISSN
- 18838049
- 09153942
-
- NDL書誌ID
- 028940392
-
- 本文言語コード
- en
-
- データソース種別
-
- JaLC
- NDL
- Crossref
- CiNii Articles
- KAKEN
-
- 抄録ライセンスフラグ
- 使用不可