Video-based Locomotion Analysis for Fish Health Monitoring

TL;DR

This paper introduces a video-based system using multi-object tracking and YOLOv11 for monitoring fish locomotion, aiding early disease detection and health assessment in aquaculture.

Contribution

It presents a novel fish locomotion analysis system leveraging YOLOv11 and multi-frame extensions for improved detection accuracy in aquaculture settings.

Findings

Reliable measurement of swimming direction and speed

Effective detection accuracy with YOLOv11 configurations

System evaluated on a new annotated dataset of Sulawesi ricefish

Abstract

Monitoring the health conditions of fish is essential, as it enables the early detection of disease, safeguards animal welfare, and contributes to sustainable aquaculture practices. Physiological and pathological conditions of cultivated fish can be inferred by analyzing locomotion activities. In this paper, we present a system that estimates the locomotion activities from videos using multi object tracking. The core of our approach is a YOLOv11 detector embedded in a tracking-by-detection framework. We investigate various configurations of the YOLOv11-architecture as well as extensions that incorporate multiple frames to improve detection accuracy. Our system is evaluated on a manually annotated dataset of Sulawesi ricefish recorded in a home-aquarium-like setup, demonstrating its ability to reliably measure swimming direction and speed for fish health monitoring. The dataset will be made publicly available upon publication.