Active shape model-based object tracking in panoramic video
- Authors
- Kim, Daehee; Maik, Vivek; Lee, Dongeun; Shin, Jeongho; Paik, Joonki
- Issue Date
- May-2006
- Publisher
- SPRINGER-VERLAG BERLIN
- Citation
- COMPUTATIONAL SCIENCE - ICCS 2006, PT 4, PROCEEDINGS, v.3994, pp 922 - 929
- Pages
- 8
- Journal Title
- COMPUTATIONAL SCIENCE - ICCS 2006, PT 4, PROCEEDINGS
- Volume
- 3994
- Start Page
- 922
- End Page
- 929
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/40219
- DOI
- 10.1007/11758549_123
- ISSN
- 0302-9743
- Abstract
- Active Shape Model (ASM) paradigm is a popular method for image segmentation where a priori information about the shape of the object of interest is available. The effectiveness of the method is contingent upon a correct correspondence between model points and the features extracted from the image. Extensive application of these models soon revealed one of their limitations when, for a given model point, no obvious salient point can be found in the image. The primary cause of such limitation is due to weak edges and presence of abrupt noise which is the case with low light surveillance video images. In this paper we propose a fusion-based panoramic tracking algorithm of in low light images using multiple sensors. The proposed algorithm uses an IR and CCD sensor for image capture. The proposed tracking system consists of three steps: (i) pyramid based fusion algorithm, (ii) reconstruction of panoramic image, and (iii) active shape model (ASM)-based tracking algorithm. The experimental results show that the proposed tracking system can robustly extract and track objects on panoramic images in real-time.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - Graduate School of Advanced Imaging Sciences, Multimedia and Film > Department of Imaging Science and Arts > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/40219)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.