This work proposes a method to characterize the appearance of individuals exploiting body visual cues.The method is based on a symmetry-driven appearance-based descriptor and a matching policy that allows to recognize an individual.The descriptor encodes three complementary visual characteristics of the human appearance: theoverall chromatic content, the spatial arrangement of colors intostable regions, and the presence of recurrent local motifs with highentropy. The characteristics are extracted by following symmetry and asymmetryperceptual principles, that allow to segregate meaningful body parts and to focus on the human body only, pruning out the background clutter.The descriptor exploits the case where we have a single image of the individual, as so as the eventuality that multiple pictures of the same identity are available, as in a tracking scenario.The descriptor is dubbed Symmetry-Driven Accumulation of LocalFeatures (SDALF).Our approach is applied to two different scenarios: re-identification and multi-target tracking.In the former, we show the capabilities of SDALF in encoding peculiar aspects of an individual, focusing on its robustness properties across dramatic low resolution images, in presence of occlusions and pose changes, and variations of viewpoints and scene illumination.SDALF has been tested on various benchmark datasets, obtaining in general convincing performances, and setting the state of the art in some cases.The latter scenario shows the benefits of using SDALF as observation model for different trackers, boosting their performances under different respects on the CAVIAR dataset.

Symmetry-Driven Accumulation of Local Features for Human Characterization and Re-identification

BAZZANI, Loris;CRISTANI, Marco;MURINO, Vittorio
2013-01-01

Abstract

This work proposes a method to characterize the appearance of individuals exploiting body visual cues.The method is based on a symmetry-driven appearance-based descriptor and a matching policy that allows to recognize an individual.The descriptor encodes three complementary visual characteristics of the human appearance: theoverall chromatic content, the spatial arrangement of colors intostable regions, and the presence of recurrent local motifs with highentropy. The characteristics are extracted by following symmetry and asymmetryperceptual principles, that allow to segregate meaningful body parts and to focus on the human body only, pruning out the background clutter.The descriptor exploits the case where we have a single image of the individual, as so as the eventuality that multiple pictures of the same identity are available, as in a tracking scenario.The descriptor is dubbed Symmetry-Driven Accumulation of LocalFeatures (SDALF).Our approach is applied to two different scenarios: re-identification and multi-target tracking.In the former, we show the capabilities of SDALF in encoding peculiar aspects of an individual, focusing on its robustness properties across dramatic low resolution images, in presence of occlusions and pose changes, and variations of viewpoints and scene illumination.SDALF has been tested on various benchmark datasets, obtaining in general convincing performances, and setting the state of the art in some cases.The latter scenario shows the benefits of using SDALF as observation model for different trackers, boosting their performances under different respects on the CAVIAR dataset.
2013
Re-identification; tracking; video surveillance
File in questo prodotto:
File Dimensione Formato  
Bazzanietal_CVIU13.pdf

accesso aperto

Tipologia: Documento in Post-print
Licenza: Dominio pubblico
Dimensione 11.25 MB
Formato Adobe PDF
11.25 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11562/472354
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 273
  • ???jsp.display-item.citation.isi??? 228
social impact