Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Animal Behavior Analysis Methods Using Deep Learning: A Survey

Edoardo Fazzari, Donato Romano, Fabrizio Falchi, Cesare Stefanini

TL;DR

This survey addresses how deep learning can advance animal behavior analysis, a field historically dominated by manual observation. It organizes the literature into pose-estimation and non-pose methodologies across audio, visual, and sensor domains, and catalogs publicly available datasets to support research. The authors identify key trends (pose-based methods like DeepLabCut and SLEAP dominating behavior analysis) and highlight gaps, including underrepresented species, data scarcity, and the need for cross-domain, unsupervised, and reinforcement-learning driven approaches. The work provides a practical roadmap for researchers and practitioners, bridging ethology with modern DL techniques and datasets to accelerate discovery and welfare-oriented applications.

Abstract

Animal behavior serves as a reliable indicator of the adaptation of organisms to their environment and their overall well-being. Through rigorous observation of animal actions and interactions, researchers and observers can glean valuable insights into diverse facets of their lives, encompassing health, social dynamics, ecological relationships, and neuroethological dimensions. Although state-of-the-art deep learning models have demonstrated remarkable accuracy in classifying various forms of animal data, their adoption in animal behavior studies remains limited. This survey article endeavors to comprehensively explore deep learning architectures and strategies applied to the identification of animal behavior, spanning auditory, visual, and audiovisual methodologies. Furthermore, the manuscript scrutinizes extant animal behavior datasets, offering a detailed examination of the principal challenges confronting this research domain. The article culminates in a comprehensive discussion of key research directions within deep learning that hold potential for advancing the field of animal behavior studies.

Animal Behavior Analysis Methods Using Deep Learning: A Survey

TL;DR

This survey addresses how deep learning can advance animal behavior analysis, a field historically dominated by manual observation. It organizes the literature into pose-estimation and non-pose methodologies across audio, visual, and sensor domains, and catalogs publicly available datasets to support research. The authors identify key trends (pose-based methods like DeepLabCut and SLEAP dominating behavior analysis) and highlight gaps, including underrepresented species, data scarcity, and the need for cross-domain, unsupervised, and reinforcement-learning driven approaches. The work provides a practical roadmap for researchers and practitioners, bridging ethology with modern DL techniques and datasets to accelerate discovery and welfare-oriented applications.

Abstract

Animal behavior serves as a reliable indicator of the adaptation of organisms to their environment and their overall well-being. Through rigorous observation of animal actions and interactions, researchers and observers can glean valuable insights into diverse facets of their lives, encompassing health, social dynamics, ecological relationships, and neuroethological dimensions. Although state-of-the-art deep learning models have demonstrated remarkable accuracy in classifying various forms of animal data, their adoption in animal behavior studies remains limited. This survey article endeavors to comprehensively explore deep learning architectures and strategies applied to the identification of animal behavior, spanning auditory, visual, and audiovisual methodologies. Furthermore, the manuscript scrutinizes extant animal behavior datasets, offering a detailed examination of the principal challenges confronting this research domain. The article culminates in a comprehensive discussion of key research directions within deep learning that hold potential for advancing the field of animal behavior studies.
Paper Structure (22 sections, 4 figures, 3 tables)

This paper contains 22 sections, 4 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Survey structure
  3. Contributions
  4. Motivation and problem statement
  5. Limitations in studying animal behaviors
  6. Objectives in studying animal behaviors
  7. Research questions
  8. Method for literature survey
  9. Search and selection strategies
  10. Comprehensive science mapping analysis
  11. Annual scientific production
  12. Scientific production based on animal considered
  13. Research field of authors
  14. Pose estimation-based methods
  15. Non pose estimation-based methods
  16. ...and 7 more sections

Figures (4)

  • Figure 1: a) illustrates a histogram depicting the distribution of research articles per year, focusing exclusively on papers obtained and cataloged during the initial scavenging phase. b) presents a pie chart detailing the variety of animals utilized in behavioral studies leveraging deep learning techniques. c) displays another pie chart showcasing the diverse research fields of the authors.
  • Figure 2: a) shows the architecture of LEAP pereira2019fast; b) the one exploited in T-LEAP russello2022t
  • Figure 3: Comprehensive schema illustrating the pose estimation architectures covered in this survey, accompanied by detailed methodologies for accurate classification of predictions into distinct behavioral classes.
  • Figure 4: Comprehensive schema illustrating the non-pose estimation architectures covered in this survey. To improve readability we divided them into blocks using the same structure employed in the survey.