Detection and Tracking of Multiple Mice Using Part Proposal Networks

TL;DR

This paper introduces a marker-free, deep learning-based method for tracking multiple mice and their body parts in videos, utilizing a Bayesian Integer Linear Programming model, and provides a new dataset for benchmarking.

Contribution

The paper presents a novel deep learning detection scheme combined with a Bayesian ILP model for multi-mouse part tracking, along with a new challenging dataset for evaluation.

Findings

Our method outperforms state-of-the-art approaches in accuracy.

The proposed approach effectively tracks multiple mice without markers.

The new dataset enables robust benchmarking of mouse tracking algorithms.

Abstract

The study of mouse social behaviours has been increasingly undertaken in neuroscience research. However, automated quantification of mouse behaviours from the videos of interacting mice is still a challenging problem, where object tracking plays a key role in locating mice in their living spaces. Artificial markers are often applied for multiple mice tracking, which are intrusive and consequently interfere with the movements of mice in a dynamic environment. In this paper, we propose a novel method to continuously track several mice and individual parts without requiring any specific tagging. Firstly, we propose an efficient and robust deep learning based mouse part detection scheme to generate part candidates. Subsequently, we propose a novel Bayesian Integer Linear Programming Model that jointly assigns the part candidates to individual targets with necessary geometric constraints whilst establishing pair-wise association between the detected parts. There is no publicly available dataset in the research community that provides a quantitative test-bed for the part detection and tracking of multiple mice, and we here introduce a new challenging Multi-Mice PartsTrack dataset that is made of complex behaviours and actions. Finally, we evaluate our proposed approach against several baselines on our new datasets, where the results show that our method outperforms the other state-of-the-art approaches in terms of accuracy.