ABSTRACT
A novel approach for object categorization suitable for video surveillance is proposed. We describe shapes only using radius and arclength of their curvatures, which allow differentiating between objects that appear in the monitored area. We conducted experiments on classes such as pedestrians, cars, cyclists, and animals (horse, cow, dog, and cat). Our approach achieves a reasonable accuracy () on Kimia dataset, surpasses the accuracy of the state-of-the-art methods (
) on CDnet videos, and allows handling cases of object merge and split usually present in foreground masks issued from background subtraction of videos.
Disclosure statement
No potential conflict of interest was reported by the authors.
Notes on contributors
Insaf Setitra received the bachelor degree in Information systems and the master degree in Software engineering from the University of Sciences and Technology Houari Boumediene, Algeria in 2008 and 2010, respectively. She also received a bachelor degree in management from the University of Management and Economics of Algiers in 2006. She worked on pattern recognition at Ecole de Technology Superieure (ETS), Montreal, Canada in 2013. And she worked in National Institute of Informatics, Tokyo, Japan, as invited researcher where she achieved tasks concerning video tracking and image analysis. She is currently working as a research engineer in the Information and Multimedia Systems’ Laboratory (DSISM) of the Research Center on Scientific and Technical Information (Cerist) in Algeria. She is also a PhD student at the University of Sciences and Technology Houari Boumediene, Algeria under Professor Larabi's supervision. Her current research interests concern image and video analysis, content-based image retrieval and pattern recognition.
Slimane Larabi received his Ph.D. degree in Computer Science from the National Institute Polytechnic of Toulouse, France, 1991. In January 1992, he joined the Computer Science Department of USTHB University in Algeria, where he is currently Professor and leads research in Computer Vision Group of the Laboratory of Artificial Intelligence Research. His work spans a range of topics in vision including image description, human action recognition, head and body pose estimation and video analysis.
ORCID
Slimane Larabi http://orcid.org/0000-0001-8994-5980