Published on Sat Nov 28 2020

Movement Tracks for the Automatic Detection of Fish Behavior in Videos

Declan McIntosh, Tunai Porto Marques, Alexandra Branzan Albu, Rodney Rountree, Fabio De Leo

Global warming is predicted to profoundly impact ocean ecosystems. Fish behavior is an important indicator of changes in such marine environments. Automatic identification of key fish behavior in videos represents a much needed tool for marine researchers.

0
0
0
Abstract

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.

Mon Jul 16 2018
Machine Learning
Assessing fish abundance from underwater video using deep neural networks
Underwater videos are being used to assess diversity and abundance of fish. Manual processing of videos for human analysts is time and labour intensive. The aim is to build an accurate and reliable fish detection and recognition system.
0
0
0
Sat Mar 06 2021
Computer Vision
Improving Automated Sonar Video Analysis to Notify About Jellyfish Blooms
0
0
0
Thu May 14 2020
Machine Learning
Temperate Fish Detection and Classification: a Deep Learning based Approach
A wide range of applications in marine ecology extensively uses underwater cameras. To efficiently process the vast amount of data generated, we need tools that can automatically detect and recognize species. Classifying fish species from videos and images in natural environments can be challenging.
0
0
0
Sat Feb 06 2021
Computer Vision
Video-based Hierarchical Species Classification for Longline Fishing Monitoring
Hierarchical classification based on videos allows for inexpensive and efficient fish species identification of catches. The flexibility of hierarchical classification mitigates the laborious efforts of human reviews by providing confidence scores in different hierarchical levels.
0
0
0
Mon Nov 05 2018
Computer Vision
Underwater Fish Detection using Deep Learning for Water Power Applications
A deep learning model, YOLO, was trained to recognize fish in underwater video using three very different data sets. The resulting model could not recognize fish in the dataset that was not part of the training set. Different methods are needed in order to produce a trained model that can generalize
0
0
0
Fri Dec 20 2019
Machine Learning
Analysis of Video Feature Learning in Two-Stream CNNs on the Example of Zebrafish Swim Bout Classification
Convolutional Neural Networks (CNNs) have reached superior performance in image recognition tasks over SVMs. Reaching better transparency helps to build trust in CNNs and makes learned features interpretable to experts.
0
0
0