Title :
Multiple Objects Tracking via Topology Adaptive Active Membrane
Author :
Das, Sitansu Kumar ; Mukherjee, Dipti Prasad
Author_Institution :
Electron. & Commun. Sci. Unit, Indian Stat. Inst., Kolkata
Abstract :
Tracking multiple deformable objects simultaneously in a video is a challenging problem. The tracking is more difficult when the objects are touching each other while they are moving or suddenly appear in or disappear from a frame of the video. In this paper we propose a parametric active membrane, which can change its topology to detect and track multiple objects present in the video. The membrane evolves in image space and also along the image intensity surface and if requires, splits into multiple membranes to track multiple objects. The methodology is tested on real video segments that demonstrates the efficacy of the proposed scheme.
Keywords :
biocomputing; image segmentation; object detection; surface fitting; topology; tracking; video signal processing; adaptive active membrane; image intensity surface; object detection; parametric active membrane; tracking multiple deformable object; video segment; Biomembranes; Computer vision; Finite element methods; Image segmentation; Layout; Object detection; Object recognition; Shape; TV; Topology; Active membrane; topology adaptive parametric model;
Conference_Titel :
Computer Vision, Graphics & Image Processing, 2008. ICVGIP '08. Sixth Indian Conference on
Conference_Location :
Bhubaneswar
Print_ISBN :
978-0-7695-3476-3
Electronic_ISBN :
978-0-7695-3476-3
DOI :
10.1109/ICVGIP.2008.35