Highly Nonrigid Object Tracking via Patch-Based Dynamic Appearance Modeling
- Authors
- Kwon, Junseok; Lee, Kyoung Mu
- Issue Date
- Oct-2013
- Publisher
- IEEE COMPUTER SOC
- Keywords
- Object tracking; nonrigid object; local patch-based appearance model; Basin Hopping Sampling; Markov Chain Monte Carlo; likelihood landscape analysis
- Citation
- IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, v.35, no.10, pp 2427 - 2441
- Pages
- 15
- Journal Title
- IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
- Volume
- 35
- Number
- 10
- Start Page
- 2427
- End Page
- 2441
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/40681
- DOI
- 10.1109/TPAMI.2013.32
- ISSN
- 0162-8828
1939-3539
- Abstract
- A novel tracking algorithm is proposed for targets with drastically changing geometric appearances over time. To track such objects, we develop a local patch-based appearance model and provide an efficient online updating scheme that adaptively changes the topology between patches. In the online update process, the robustness of each patch is determined by analyzing the likelihood landscape of the patch. Based on this robustness measure, the proposed method selects the best feature for each patch and modifies the patch by moving, deleting, or newly adding it over time. Moreover, a rough object segmentation result is integrated into the proposed appearance model to further enhance it. The proposed framework easily obtains segmentation results because the local patches in the model serve as good seeds for the semi-supervised segmentation task. To solve the complexity problem attributable to the large number of patches, the Basin Hopping (BH) sampling method is introduced into the tracking framework. The BH sampling method significantly reduces computational complexity with the help of a deterministic local optimizer. Thus, the proposed appearance model could utilize a sufficient number of patches. The experimental results show that the present approach could track objects with drastically changing geometric appearance accurately and robustly.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Software > School of Computer Science and Engineering > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/40681)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.