Object segmentation in video via graph cut built on superpixels

Issue title: Cognitive Informatics, Cognitive Computing, and Their Denotational Mathematical Foundations (II)

Article type: Research Article

Authors: Kwolek, Bogdan

Affiliations: Rzeszów University of Technology, Rzeszów, Poland. [email protected]

Note: [] Address for correspondence: Rzeszów University of Technology, W. Pola 2, 35-959 Rzeszów, Poland

Abstract: This paper proposes a real-time scheme for object segmentation in video. In the first stage a segmentation based on pairwise region comparison is utilized to oversegment image through extracting superpixels. Next, the algorithmapplies the graph cut built on such superpixels, instead of the image pixels. Owing to the optimization is performed on a simpler graph and in consequence the object segmentation runs in shorter time. Tracking of object features over time contributes toward improved segmenting the object from one image to another. The segmentation information supports following the entire object, instead of just a few features on it. The objects are segmented correctly as complete entities, despite the high variability of the object shape and cluttered background. Experimental results illustrate the efficiency and effectiveness of the algorithm.

Keywords: Cognitive Vision Systems, Image Segmentation, Object Recognition

DOI: 10.3233/FI-2009-0025

Journal: Fundamenta Informaticae, vol. 90, no. 4, pp. 379-393, 2009