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.

Extracting accurate long-term behavior changes from a large pig dataset / Bergamini, L.; Pini, S.; Simoni, A.; Vezzani, R.; Calderara, S.; Eath, R. B. D.; Fisher, R. B.. - 5:(2021), pp. 524-533. ((Intervento presentato al convegno 16th International Conference on Computer Vision Theory and Applications tenutosi a Online nel 8-10 February 2021 [10.5220/0010288405240533].

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

Bergamini L.;Pini S.;Simoni A.;Vezzani R.;Calderara S.;
2021

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.
16th International Conference on Computer Vision Theory and Applications
Online
8-10 February 2021
5
524
533
Bergamini, L.; Pini, S.; Simoni, A.; Vezzani, R.; Calderara, S.; Eath, R. B. D.; Fisher, R. B.
Extracting accurate long-term behavior changes from a large pig dataset / Bergamini, L.; Pini, S.; Simoni, A.; Vezzani, R.; Calderara, S.; Eath, R. B. D.; Fisher, R. B.. - 5:(2021), pp. 524-533. ((Intervento presentato al convegno 16th International Conference on Computer Vision Theory and Applications tenutosi a Online nel 8-10 February 2021 [10.5220/0010288405240533].
File in questo prodotto:
File Dimensione Formato  
VISAPP 2021.pdf

accesso aperto

Tipologia: Pre-print dell'autore (bozza pre referaggio)
Dimensione 4.03 MB
Formato Adobe PDF
4.03 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/1239408
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 4
  • ???jsp.display-item.citation.isi??? 3
social impact