Extracting Accurate Long-term Behavior Changes from a Large Pig Dataset

Luca Bergamini, Stefano Pini, Alessandro Simoni, Roberto Vezzani, Simone Calderara, Rick D’Eath, Robert Fisher

Abstract

Visual observation of uncontrolled real-world behavior leads to noisy observations, complicated by occlusions, ambiguity, variable motion rates, detection and tracking errors, slow transitions between behaviors, etc. We show in this paper that reliable estimates of long-term trends can be extracted given enough data, even though estimates from individual frames may be noisy. We validate this concept using a new public dataset of approximately 20+ million daytime pig observations over 6 weeks of their main growth stage, and we provide annotations for various tasks including 5 individual behaviors. Our pipeline chains detection, tracking and behavior classification combining deep and shallow computer vision techniques. While individual detections may be noisy, we show that long-term behavior changes can still be extracted reliably, and we validate these results qualitatively on the full dataset. Eventually, starting from raw RGB video data we are able to both tell what pigs main daily activities are, and how these change through time.

Download


Paper Citation


in Harvard Style

Bergamini L., Pini S., Simoni A., Vezzani R., Calderara S., D’Eath R. and Fisher R. (2021). Extracting Accurate Long-term Behavior Changes from a Large Pig Dataset.In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, ISBN 978-989-758-488-6, pages 524-533. DOI: 10.5220/0010288405240533


in Bibtex Style

@conference{visapp21,
author={Luca Bergamini and Stefano Pini and Alessandro Simoni and Roberto Vezzani and Simone Calderara and Rick D’Eath and Robert Fisher},
title={Extracting Accurate Long-term Behavior Changes from a Large Pig Dataset},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,},
year={2021},
pages={524-533},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010288405240533},
isbn={978-989-758-488-6},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,
TI - Extracting Accurate Long-term Behavior Changes from a Large Pig Dataset
SN - 978-989-758-488-6
AU - Bergamini L.
AU - Pini S.
AU - Simoni A.
AU - Vezzani R.
AU - Calderara S.
AU - D’Eath R.
AU - Fisher R.
PY - 2021
SP - 524
EP - 533
DO - 10.5220/0010288405240533