Human Detection using HOG-SVM, Mixture of Gaussian and Background Contours Subtraction - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Human Detection using HOG-SVM, Mixture of Gaussian and Background Contours Subtraction

Résumé

Automatic moving object/Human detection in a video sequence is one of the most difficult problems in the field of image processing and computer vision. The HOG-SVM provides a detection windows that is not perfectly adjusted to the silhouette of the Human detected. It is possible to apply a postprocess based on background subtraction to improve the segmentation of the detection. In this paper, we present thus a detection method that improves results provided by HOG-SVM with a combination of mixture of Gaussian and background contours subtraction.
Fichier non déposé

Dates et versions

hal-01763188 , version 1 (10-04-2018)

Identifiants

Citer

Abdourahman Houssein Ahmed, Kidiyo Kpalma, Abdoulkader Osman Guedi. Human Detection using HOG-SVM, Mixture of Gaussian and Background Contours Subtraction. 13th International Conference on SIGNAL IMAGE TECHNOLOGY & INTERNET BASED SYSTEMS, Dec 2017, Jaipur, India. ⟨10.1109/SITIS.2017.62⟩. ⟨hal-01763188⟩
442 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More