Feasibility Research on Fish Pose Estimation Based on Rotating Box Object Detection

• Published in: Fishes Vol. 6; no. 4; p. 65
• Main Authors: Lin, Bin, Jiang, Kailin, Xu, Zhiqi, Li, Feiyi, Li, Jiao, Mou, Chaoli, Gong, Xinyao, Duan, Xuliang
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.12.2021
• Subjects: algorithms; Animal behavior; Animals; Aquaculture; aquaculture automation; Artificial intelligence; Attitudes; Behaviour; Breeding; cameras; Carp; computer vision; data collection; Datasets; Deep learning; Detection; Feasibility studies; Fish; fish detection; fish pose; Fisheries; Fishing; flocks; Neural networks; physiological state; Physiology; Posture; rotating box; skeleton; Teaching methods; Underwater cameras

A video-based method to quantify animal posture movement is a powerful way to analyze animal behavior. Both humans and fish can judge the physiological state through the skeleton framework. However, it is challenging for farmers to judge the breeding state in the complex underwater environment. Ther...