A Combined Motion and Appearance Model for Human Tracking in Multiple Cameras Environments - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2010

A Combined Motion and Appearance Model for Human Tracking in Multiple Cameras Environments

Résumé

The aim of this paper is to present an algorithm for multiple object tracking in a scene filmed by one or several cameras. We propose a computationally efficient real time human tracking algorithm, which can 1) track objects inside the field of view (FOV) of a camera even in case of occlusions; 2) recognize objects that quit and then return on a camera’s FOV; 3) recognize objects passing through different cameras FOV. We propose a simple 1-D appearance model, called vertical feature (VF), view and appearance size invariant, which is stored in a database in order to help object recognition. We combine it with other motion features like position and velocity for real-time tracking. We find the k closest matches of current object and select the one whose predicted position is closest to the current object position. Our algorithm shows good capabilities for objects tracking even with the change of object view angle and also with the partial change of shape. We compare our algorithm with appearance based and motion based algorithms and show the advantage of a combined approach.
Fichier non déposé

Dates et versions

hal-01381552 , version 1 (14-10-2016)

Identifiants

Citer

Atif Ilyas, Mihaela Scuturici, Serge Miguet. A Combined Motion and Appearance Model for Human Tracking in Multiple Cameras Environments. 6th IEEE International Conference on Emerging Technologies (ICET 2010), Oct 2010, Islamabad, Pakistan. pp.198-203, ⟨10.1109/ICET.2010.5638491⟩. ⟨hal-01381552⟩
85 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More