Online Multiple Target Tracking (MTT) is often addressed within the tracking-by-detection paradigm. Detections are previously extracted independently in each frame and then objects trajectories are built by maximizing specifically designed coherence functions. Nevertheless, ambiguities arise in presence of occlusions or detection errors. In this paper we claim that the ambiguities in tracking could be solved by a selective use of the features, by working with more reliable features if possible and exploiting a deeper representation of the target only if necessary. To this end, we propose an online divide and conquer tracker for static camera scenes, which partitions the assignment problem in local subproblems and solves them by selectively choosing and combining the best features. The complete framework is cast as a structural learning task that unifies these phases and learns tracker parameters from examples. Experiments on two different datasets highlights a significant improvement of tracking performances (MOTA +10%) over the state of the art.

Learning to Divide and Conquer for Online Multi-Target Tracking / Solera, Francesco; Calderara, Simone; Cucchiara, Rita. - ELETTRONICO. - 11-18-December-2015:(2015), pp. 4373-4381. (Intervento presentato al convegno 2015 IEEE International Conference on Computer Vision tenutosi a Santiago (Chile) nel 11-18 December 2015) [10.1109/ICCV.2015.497].

Learning to Divide and Conquer for Online Multi-Target Tracking

SOLERA, FRANCESCO;CALDERARA, Simone;CUCCHIARA, Rita
2015

Abstract

Online Multiple Target Tracking (MTT) is often addressed within the tracking-by-detection paradigm. Detections are previously extracted independently in each frame and then objects trajectories are built by maximizing specifically designed coherence functions. Nevertheless, ambiguities arise in presence of occlusions or detection errors. In this paper we claim that the ambiguities in tracking could be solved by a selective use of the features, by working with more reliable features if possible and exploiting a deeper representation of the target only if necessary. To this end, we propose an online divide and conquer tracker for static camera scenes, which partitions the assignment problem in local subproblems and solves them by selectively choosing and combining the best features. The complete framework is cast as a structural learning task that unifies these phases and learns tracker parameters from examples. Experiments on two different datasets highlights a significant improvement of tracking performances (MOTA +10%) over the state of the art.
2015
2015 IEEE International Conference on Computer Vision
Santiago (Chile)
11-18 December 2015
11-18-December-2015
4373
4381
Solera, Francesco; Calderara, Simone; Cucchiara, Rita
Learning to Divide and Conquer for Online Multi-Target Tracking / Solera, Francesco; Calderara, Simone; Cucchiara, Rita. - ELETTRONICO. - 11-18-December-2015:(2015), pp. 4373-4381. (Intervento presentato al convegno 2015 IEEE International Conference on Computer Vision tenutosi a Santiago (Chile) nel 11-18 December 2015) [10.1109/ICCV.2015.497].
File in questo prodotto:
File Dimensione Formato  
Solera_Learning_to_Divide_ICCV_2015_paper.pdf

Open access

Tipologia: Versione pubblicata dall'editore
Dimensione 1.26 MB
Formato Adobe PDF
1.26 MB Adobe PDF Visualizza/Apri
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/11380/1083506
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 44
  • ???jsp.display-item.citation.isi??? 25
social impact