Extracting accurate long-term behavior changes from a large pig dataset

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

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

43 Downloads (Pure)

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.

Original languageEnglish
Title of host publicationProceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
EditorsGiovanni Maria Farinella, Petia Radeva, Jose Braz, Kadi Bouatouch
PublisherSciTePress
Pages524-533
Number of pages10
Volume4
ISBN (Electronic)9789897584886
DOIs
Publication statusPrint publication - 2021
Event16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2021 - Virtual, Online
Duration: 8 Feb 202110 Feb 2021

Conference

Conference16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2021
CityVirtual, Online
Period8/02/2110/02/21

Keywords

  • Behavior classification
  • Long-term temporal analysis
  • Pig detection
  • Pig farming
  • Pig tracking

Fingerprint

Dive into the research topics of 'Extracting accurate long-term behavior changes from a large pig dataset'. Together they form a unique fingerprint.

Cite this