Fish Tracking, Counting, and Behaviour Analysis in Digital Aquaculture: A Comprehensive Survey

2024-06-20

Reviews in Aquaculture

AI Summary

This work addresses three core challenges in digital aquaculture: scarcity of annotated datasets, absence of standardized evaluation protocols, and suboptimal joint performance across fish tracking, counting, and behavioral analysis tasks. To this end, we propose the first multimodal unified analytical framework covering all three tasks. We systematically survey technical approaches across visual, acoustic, and biosensing modalities, identifying shared bottlenecks. Our method uniquely fuses image/video, acoustic signals, and physiological sensor data, integrating multi-task learning with large language model–enhanced semantic understanding. We establish a standardized benchmark dataset and evaluation protocol, and present a comprehensive technology comparison map. The contributions include a reproducible, scalable integrated monitoring paradigm for digital aquaculture and a practical implementation guide grounded in empirical validation. This framework bridges critical gaps between sensing modalities, task objectives, and real-world deployment requirements.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multimodal Learning

Application Category

• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Digital aquaculture leverages advanced technologies and data‐driven methods, providing substantial benefits over traditional aquaculture practices. This article presents a comprehensive review of three interconnected digital aquaculture tasks, namely, fish tracking, counting, and behaviour analysis, using a novel and unified approach. Unlike previous reviews which focused on single modalities or individual tasks, we analyse vision‐based (i.e., image‐ and video‐based), acoustic‐based, and biosensor‐based methods across all three tasks. We examine their advantages, limitations, and applications, highlighting recent advancements and identifying critical cross‐cutting research gaps. The review also includes emerging ideas such as applying multitask learning and large language models to address various aspects of fish monitoring, an approach not previously explored in aquaculture literature. We identify the major obstacles hindering research progress in this field, including the scarcity of comprehensive fish datasets and the lack of unified evaluation standards. To overcome the current limitations, we explore the potential of using emerging technologies such as multimodal data fusion and deep learning to improve the accuracy, robustness, and efficiency of integrated fish monitoring systems. In addition, we provide a summary of existing datasets available for fish tracking, counting, and behaviour analysis. This holistic perspective offers a roadmap for future research, emphasizing the need for comprehensive datasets and evaluation standards to facilitate meaningful comparisons between technologies and to promote their practical implementations in real‐world settings.

Problem

• Review fish tracking, counting, and behavior analysis in digital aquaculture.
• Analyze vision-based, acoustic-based, and biosensor-based methods across tasks.
• Address research gaps like dataset scarcity and lack of unified standards.

Innovation

• Multimodal data fusion for fish monitoring
• Deep learning enhances tracking accuracy
• Multi-task learning in aquaculture analysis