Saved in:
Bibliographic Details
Main Author: Wang, Bo
Format: Recurso digital
Language:
Published: Zenodo 2025
Online Access:https://doi.org/10.5281/zenodo.17518455
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • <p>The dataset was generated during the development of the <strong>FHA-MTT algorithm</strong>, which aims to enable automated health assessment of fish based on swimming behavior. It includes video recordings of <strong>crucian carp (Carassius auratus)</strong> exhibiting both healthy and diseased states, together with <strong>annotation files</strong> used for training object detection and keypoint recognition models. In addition, the dataset contains <strong>tracking results</strong> produced by different multi-object tracking algorithms.</p> <p> FHA-MTT integrates object and keypoint detection with trajectory-based behavioral analysis, providing an efficient and reliable framework for evaluating the health status of fish in aquaculture environments.</p>