A Multi-purpose Tracking Framework for Salmon Welfare Monitoring in Challenging Environments

2025-09-30

AI Summary

Severe occlusions, high inter-individual appearance similarity, and dense motion in underwater salmon farming lead to frequent identity switches, hindering reliable welfare monitoring. Method: We propose the first multi-part-aware tracking framework specifically designed for salmon welfare analysis. It integrates a pose estimation network to localize fish bodies and key anatomical parts (e.g., caudal fins), introduces a part-level association and occlusion recovery module, and couples these with a multi-object tracking backbone for end-to-end training. Contribution/Results: Our body-part-aware mechanism enables high-precision trajectory modeling of fine-grained behavioral features—such as caudal fin oscillation wavelength—thereby supporting joint inference of multiple welfare indicators. Evaluated on a novel in-house underwater salmon dataset, our method significantly outperforms the state-of-the-art pedestrian tracker BoostTrack in ID switch rate (−42.3%) and turning stability (+38.7%), establishing an interpretable and deployable paradigm for intelligent aquaculture welfare assessment.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multimodal Learning

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications

Abstract

Computer Vision (CV)-based continuous, automated and precise salmon welfare monitoring is a key step toward reduced salmon mortality and improved salmon welfare in industrial aquaculture net pens. Available CV methods for determining welfare indicators focus on single indicators and rely on object detectors and trackers from other application areas to aid their welfare indicator calculation algorithm. This comes with a high resource demand for real-world applications, since each indicator must be calculated separately. In addition, the methods are vulnerable to difficulties in underwater salmon scenes, such as object occlusion, similar object appearance, and similar object motion. To address these challenges, we propose a flexible tracking framework that uses a pose estimation network to extract bounding boxes around salmon and their corresponding body parts, and exploits information about the body parts, through specialized modules, to tackle challenges specific to underwater salmon scenes. Subsequently, the high-detail body part tracks are employed to calculate welfare indicators. We construct two novel datasets assessing two salmon tracking challenges: salmon ID transfers in crowded scenes and salmon ID switches during turning. Our method outperforms the current state-of-the-art pedestrian tracker, BoostTrack, for both salmon tracking challenges. Additionally, we create a dataset for calculating salmon tail beat wavelength, demonstrating that our body part tracking method is well-suited for automated welfare monitoring based on tail beat analysis. Datasets and code are available at https://github.com/espenbh/BoostCompTrack.

Problem

• Developing automated salmon welfare monitoring in aquaculture
• Addressing underwater challenges like occlusion and similar appearance
• Creating flexible tracking framework using pose estimation

Innovation

• Uses pose estimation network for salmon bounding boxes
• Exploits body part information through specialized modules
• Employs high-detail body part tracks for welfare indicators