Consistent multi-animal pose estimation in cattle using dynamic Kalman filter based tracking
Authors:
Preprint
- 16 January 2024
- preprint
- Published by Springer Nature in Research Square
Abstract
The usage of computer vision to study animal behaviour has gained popularity during the last decade. Replacing human observers by computer vision lowers the cost of data collection and therefore allows to collect more extensive datasets. However, the majority of available computer vision algorithms to study animal behaviour is highly tailored towards a single research objective, limiting possibilities for data reuse. In this perspective, pose-estimation in combination with animal tracking offers opportunities to yield a higher level representation capturing both the spatial and temporal component of animal behaviour. Such a higher level representation allows to answer a wide variety of research questions simultaneously, without the need to develop repeatedly tailored computer vision algorithms. In this paper, we therefore first cope with several weaknesses of current pose-estimation algorithms and thereafter introduce KeySORT (Keypoint Simple and Online Realtime Tracking). KeySORT deploys an adaptive Kalman filter to construct tracklets in a bounding-box free manner and improves the temporal consistency of detected keypoints to a large extent. In this paper, we focus on pose estimation in cattle, but our methodology can easily be generalised to any other animal species. Our test results indicate our algorithm is able to detect up to 80% of the ground truth keypoints with high accuracy, with only a limited drop in performance when daylight recordings are compared to nightvision recordings. Moreover, by using KeySORT to construct skeletons, the temporal consistency of generated keypoint coordinates was largely improved, offering opportunities with regard to automated behaviour monitoring of animals.Keywords
All Related Versions
This publication has 23 references indexed in Scilit:
- Assessment of dairy cow heat stress by monitoring drinking behaviour using an embedded imaging systemBiosystems Engineering, 2020
- Image analysis for individual identification and feeding behaviour monitoring of dairy cows based on Convolutional Neural Networks (CNN)Biosystems Engineering, 2020
- Use of social network analysis to improve the understanding of social behaviour in dairy cattle and its impact on disease transmissionApplied Animal Behaviour Science, 2019
- Comprehensive analysis of affiliative and agonistic social networks in lactating dairy cattle groupsApplied Animal Behaviour Science, 2019
- Multi-target tracking using CNN-based features: CNNMTTMultimedia Tools and Applications, 2018
- Multi-person Pose Estimation with Local Joint-to-Person Associations2016
- Exploiting relationship between attributes for improved face verificationComputer Vision and Image Understanding, 2014
- Object Bank: An Object-Level Image Representation for High-Level Visual RecognitionInternational Journal of Computer Vision, 2013
- An Optimal Adaptive Kalman FilterJournal of Geodesy, 2006
- The Hungarian method for the assignment problemNaval Research Logistics Quarterly, 1955