Graph-based people segmentation using a genetically optimized combination of classifiers - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Journal of Electronic Imaging Année : 2018

Graph-based people segmentation using a genetically optimized combination of classifiers

Résumé

Many approaches for background subtraction and people detection have been developed so far. However, the best state-of-the-art methods do not give yet satisfactory results in real transportation environments. Indeed, these latter configurations imply several difficulties such as fast brightness changes, noise, shadows, scrolling background, etc., and a single approach cannot deal with all these. In this paper, we propose a new approach for people segmen-tation and tracking in videos that is suited for real-world conditions. Our strategy combines several state-of-the-art methods for people detection, silhouette appearance modeling and tracking. Each process also uses its own frame pre-processing pipeline. The optimal combination of the people classifiers used, as well as the optimal parameters of each of the combined methods, being too difficult to be determined altogether, a genetic algorithm is used to determine the optimal classifier parameters and their combination weights. The output of the latter is used as an initialization for a multi-frame graph-cut operating on superpixel graphs. Our proposed approach is evaluated on the BOSS Euro-pean project database that was acquired in moving trains and that contains typical scientific locks encountered in real transportation systems.
Fichier principal
Vignette du fichier
jei_ivadr_2018_vfc.pdf (1.93 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01731507 , version 1 (14-03-2018)

Identifiants

Citer

Cyril Meurie, Olivier Lézoray, Christophe Coniglio, Marion Berbineau. Graph-based people segmentation using a genetically optimized combination of classifiers. Journal of Electronic Imaging, 2018, 27 (5), pp.16-47. ⟨10.1117/1.JEI.27.5.051210⟩. ⟨hal-01731507⟩
199 Consultations
139 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More