Foreground-Background Segmentation Based on Codebook and Edge Detector

Mikaël A. Mousse (1, 2) , Eugène C. Ezin (2) , Cina Motamed (1)

1 LISIC - Laboratoire d'Informatique Signal et Image de la Côte d'Opale
2 URISA - Unité de Recherche en Informatique et Sciences appliquées

Background modeling techniques are used for moving object detection in video. Many algorithms exist in the field of object detection with different purposes. In this paper, we propose an improvement of moving object detection based on codebook segmentation. We associate the original codebook algorithm with an edge detection algorithm. Our goal is to prove the efficiency of using an edge detection algorithm with a background modeling algorithm. Throughout our study, we compared the quality of the moving object detection when codebook segmentation algo-rithm is associated with some standard edge detectors. In each case, we use frame-based metrics for the evaluation of the detection. The different results are presented and analyzed.

Mots clés: edge detector; video segmentation; mixture of gaussian; -codebook

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Traitement du signal et de l'image [eess.SP]

Mikaël A. Mousse, Eugène C. Ezin, Cina Motamed. Foreground-Background Segmentation Based on Codebook and Edge Detector. Signal-Image Technology and Internet-Based Systems (SITIS), 2014 Tenth International Conference on, Nov 2014, Marrakech, Morocco. ⟨10.1109/SITIS.2014.55⟩. ⟨hal-01119135⟩