A hybrid tracking method for scaled and oriented objects in crowded scenes |
| |
| Authors: | M Fatih Talu ?brahim Türko?lu Mehmet Cebeci |
| |
| Affiliation: | 1. Inonu University, Computer Engineering Department, 44280 Malatya, Turkey;2. Firat University, Department of Electronics and Computer Science, Elazig, Turkey;3. Firat University, Department of Electrical–Electronic Engineering, Elazig, Turkey;1. Department of Electrical and Electronics Engineering, Bitlis Eren University, Bitlis, Turkey;2. Department of Software Engineering, Samsun University, Samsun, Turkey;3. Department of Computer Engineering, Bitlis Eren University, Bitlis, Turkey;4. Department of Electrical and Electronics Engineering, Technology Faculty, Firat University, Elazig, Turkey;1. Department of Electrical-Electronics Engineering, Bingöl University, 12000 Bingöl, Turkey;2. Department of Electrical and Electronics Engineering, F?rat University, 23000 Elaz?g, Turkey;1. Bingol University, Engineering and Architecture Faculty, Electrical-Electronics Eng. Dept., Bingol, Turkey;2. Centre for Applied Informatics, College of Engineering and Science, Victoria University, Melbourne, Australia;3. Discipline of Electronics and Communication Engineering, PDPM Indian Institute of Information Technology, Design and Manufacturing, Jabalpur, India;4. Department of Computer Science, University of Illinois at Springfield, Springfield, IL, USA;5. Firat University, Technology Faculty, Electrical and Electronics Engineering Dept., Elazig, Turkey |
| |
| Abstract: | Traditional kernel based means shift assumes constancy of the object scale and orientation during the course of tracking and uses a symmetric/asymmetric kernel, such as a circle or an ellipse for target representation. In a tracking scenario, it is not uncommon to observe objects with complex shapes whose scale and orientation constantly change due to the camera and object motions. In this paper, we propose a multi object tracking method which tracks the complete object regions, adapts to changing scale and orientation, and assigns consistent labels to each object throughout real world video sequences. Our approach has five major components: (1) dynamic background subtraction, (2) level sets, (3) mean shift convergence, (4) object identification, and (5) occlusion handling. The experimental results show that the proposed method is superior to the traditional mean shift tracking in the following aspects: (1) it provides consistent multi objects tracking instead of single object throughout the video, (2) it is not affected by the scale and orientation changes of the tracked objects, (3) its computational complexity is much less than traditional mean shift due to using level set method instead of probability density. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
