Movement Tracks for the Automatic Detection of Fish Behavior in Videos
This work provides a tool for marine researchers to automatically identify key fish behaviors in videos, which is crucial for studying climate change impacts on ocean ecosystems.
This paper addresses the problem of automatically detecting fish behavior in underwater videos, specifically focusing on sablefish startle behaviors. The authors created a dataset for this purpose and developed a system that uses deep learning to identify fish, track their movements, extract behavior-specific features, and employ LSTMs to detect startle behavior.
Global warming is predicted to profoundly impact ocean ecosystems. Fish behavior is an important indicator of changes in such marine environments. Thus, the automatic identification of key fish behavior in videos represents a much needed tool for marine researchers, enabling them to study climate change-related phenomena. We offer a dataset of sablefish (Anoplopoma fimbria) startle behaviors in underwater videos, and investigate the use of deep learning (DL) methods for behavior detection on it. Our proposed detection system identifies fish instances using DL-based frameworks, determines trajectory tracks, derives novel behavior-specific features, and employs Long Short-Term Memory (LSTM) networks to identify startle behavior in sablefish. Its performance is studied by comparing it with a state-of-the-art DL-based video event detector.