| Cluster-based distributed face tracking in camera networks. | |
| | |
MedLine Citation:
|
PMID: 20423804 Owner: NLM Status: MEDLINE |
Abstract/OtherAbstract:
|
In this paper, we present a distributed multicamera face tracking system suitable for large wired camera networks. Unlike previous multicamera face tracking systems, our system does not require a central server to coordinate the entire tracking effort. Instead, an efficient camera clustering protocol is used to dynamically form groups of cameras for in-network tracking of individual faces. The clustering protocol includes cluster propagation mechanisms that allow the computational load of face tracking to be transferred to different cameras as the target objects move. Furthermore, the dynamic election of cluster leaders provides robustness against system failures. Our experimental results show that our cluster-based distributed face tracker is capable of accurately tracking multiple faces in real-time. The overall performance of the distributed system is comparable to that of a centralized face tracker, while presenting the advantages of scalability and robustness. |
| | |
Authors:
|
Josiah Yoder; Henry Medeiros; Johnny Park; Avinash C Kak |
Related Documents
:
|
22456014 - A new software for dimensional measurements in 3d endodontic root canal instrumentation. 15989054 - Face recognition by using feature-specific imaging. 1631214 - Mandibular retrusion, temporomandibular joint derangement, and orthognathic surgery pla... 2759524 - Application of 3-d computer graphics for facial reconstruction and comparison with scul... 21890224 - Image-guided radiotherapy using surgical clips as fiducial markers after prostatectomy:... 20713314 - Eeg-based neonatal seizure detection with support vector machines. |
Publication Detail:
|
Type: Journal Article; Research Support, Non-U.S. Gov't Date: 2010-04-26 |
Journal Detail:
|
Title: IEEE transactions on image processing : a publication of the IEEE Signal Processing Society Volume: 19 ISSN: 1941-0042 ISO Abbreviation: IEEE Trans Image Process Publication Date: 2010 Oct |
Date Detail:
|
Created Date: 2010-09-20 Completed Date: 2011-01-10 Revised Date: - |
Medline Journal Info:
|
Nlm Unique ID: 9886191 Medline TA: IEEE Trans Image Process Country: United States |
Other Details:
|
Languages: eng Pagination: 2551-63 Citation Subset: IM |
Affiliation:
|
School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47907, USA. yoder2@purdue.edu |
Export Citation:
|
APA/MLA Format Download EndNote Download BibTex |
| MeSH Terms | |
Descriptor/Qualifier:
|
Algorithms Biometric Identification / methods* Cluster Analysis Computer Communication Networks Head Movements / physiology* Humans Nonverbal Communication / physiology* Pattern Recognition, Automated / methods* Photography / instrumentation*, methods* Population Surveillance / methods Posture / physiology* |
From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine
Previous Document: Scanned compound document encoding using multiscale recurrent patterns.
Next Document: A novel rotationally invariant region-based hidden Markov model for efficient 3-D image segmentation...