People re-identification task has seen enormous improvements in the latest years, mainly due to the development of better image features extraction from deep Convolutional Neural Networks (CNN) and the availability of large datasets. However, little research has been conducted on animal identification and re-identification, even if this knowledge may be useful in a rich variety of different scenarios. Here, we tackle cattle re-identification exploiting deep CNN and show how this task is poorly related to the human one, presenting unique challenges that make it far from being solved. We present various baselines, both based on deep architectures or on standard machine learning algorithms, and compared them with our solution. Finally, a rich ablation study has been conducted to further investigate the unique peculiarities of this task.

Multi-views Embedding for Cattle Re-identification / Bergamini, Luca; Porrello, Angelo; Andrea Capobianco Dondona, ; Ercole Del Negro, ; Mauro, Mattioli; Nicola, D’Alterio; Calderara, Simone. - (2018), pp. 184-191. ((Intervento presentato al convegno 14th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2018 tenutosi a Las Palmas de Gran Canaria, Spain nel 26-29 November 2018 [10.1109/SITIS.2018.00036].

Multi-views Embedding for Cattle Re-identification

Luca Bergamini
;
PORRELLO, ANGELO;Simone Calderara
2018

Abstract

People re-identification task has seen enormous improvements in the latest years, mainly due to the development of better image features extraction from deep Convolutional Neural Networks (CNN) and the availability of large datasets. However, little research has been conducted on animal identification and re-identification, even if this knowledge may be useful in a rich variety of different scenarios. Here, we tackle cattle re-identification exploiting deep CNN and show how this task is poorly related to the human one, presenting unique challenges that make it far from being solved. We present various baselines, both based on deep architectures or on standard machine learning algorithms, and compared them with our solution. Finally, a rich ablation study has been conducted to further investigate the unique peculiarities of this task.
14th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2018
Las Palmas de Gran Canaria, Spain
26-29 November 2018
184
191
Bergamini, Luca; Porrello, Angelo; Andrea Capobianco Dondona, ; Ercole Del Negro, ; Mauro, Mattioli; Nicola, D’Alterio; Calderara, Simone
Multi-views Embedding for Cattle Re-identification / Bergamini, Luca; Porrello, Angelo; Andrea Capobianco Dondona, ; Ercole Del Negro, ; Mauro, Mattioli; Nicola, D’Alterio; Calderara, Simone. - (2018), pp. 184-191. ((Intervento presentato al convegno 14th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2018 tenutosi a Las Palmas de Gran Canaria, Spain nel 26-29 November 2018 [10.1109/SITIS.2018.00036].
File in questo prodotto:
File Dimensione Formato  
Multi_views_Embedding_for_Cattle_Re_identification.pdf

accesso aperto

Tipologia: Versione dell'editore (versione pubblicata)
Dimensione 7.38 MB
Formato Adobe PDF
7.38 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/11380/1169525
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 16
  • ???jsp.display-item.citation.isi??? 13
social impact