A Hybrid Architecture for Tracking People in Real-Time Using a Video Surveillance Camera : Application for Behavioural Marketing

Kheireddine Aziz (1) , Djamel Merad (2, 3) , Jean-Luc Damoiseaux (2, 3) , Pierre Drap (2, 3)

1 UTLN SeaTech - Université de Toulon - École d’ingénieurs SeaTech
2 LIS - Laboratoire d'Informatique et des Systèmes (LIS) (Marseille, Toulon)
3 I&M - Images et Modèles

This paper describes a novel method for tracking customers using images taken from video-surveillance cameras. This system analyzes the number of customers and their motions through the aisles of big-box stores (supermarkets) in real-time. The originality of our approach is based on the study of the blobs properties for managing the splitting/merging issues using a mathematical morphology operator. In the order hand, in order to manage a high number of customers in real-time, we combine the advantage of two tracking algorithms.

Mots clés: Deterministic tracking; splitting/merging blobs; behavioural marketing

Domaines: Informatique [cs]

Kheireddine Aziz, Djamel Merad, Jean-Luc Damoiseaux, Pierre Drap. A Hybrid Architecture for Tracking People in Real-Time Using a Video Surveillance Camera : Application for Behavioural Marketing. Signal & Image Processing : An International Journal, 2015, 6 (6), pp.01-11. ⟨10.5121/sipij.2015.6601⟩. ⟨hal-03120105⟩