Application of MID-SVM for online person identification using appearance-based features - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

Application of MID-SVM for online person identification using appearance-based features

Résumé

Person identification is an important but still challenging problem in video surveillance. This work designs a complete automatic appearance-based person identification system in online setting. The proposed system consists of three modules: background extraction and silhouette extraction; feature extraction and selection; and person identification. Grey-world normalized color features and Haralick texture features are extracted as initial feature subset. The multi-category incremental and decremental SVM (MID-SVM) algorithm is used to adaptively classify persons with the advantage of training only with few initial images and updating the needed parts. A new video database with 22 persons is created in real-life environments. The experimental results show that the proposed system succeed in person identification. In order to improve the performance of this system, a comparison of RGB and HSV colors is performed and the comparison experimental results indicate that the initial feature with HSV color and Haralick texture features works better.
Fichier non déposé

Dates et versions

hal-01470289 , version 1 (17-02-2017)

Identifiants

Citer

Yanyun Lu, Anthony Fleury, Jacques Boonaert, Stéphane Lecoeuche, Sébastien Ambellouis. Application of MID-SVM for online person identification using appearance-based features. IEEE Conference on Evolving andEAIS 2015 - IEEE International Conference on Evolving and Adaptive Intelligent Systems Adaptive Intelligent Systems, Dec 2015, DOUAI, France. 8p, ⟨10.1109/EAIS.2015.7368794⟩. ⟨hal-01470289⟩
48 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More