Multi-camera invariant appearance modeling for non-rigid object identification in a real-time environment

NCUIR > Engineering College > Departmant of Mechanical Engineering > journal & Dissertation > Item 987654321/108971

Please use this identifier to cite or link to this item: https://ir.lib.ncu.edu.tw/handle/987654321/108971

Title:	Multi-camera invariant appearance modeling for non-rigid object identification in a real-time environment
Authors:	林智揚;Lin, Chih-Yang;Kang, Li-Wei;Kao, Jau-Hong;Lu, Chun-Shien;Wu, Yi-Ta
Contributors:	工學院機械工程學系
Keywords:	Appearance model;Gaussian mixture model;Hierarchical tree structures;Identification;Invariant features;Multi-camera;Real-time system;Surveillance
Date:	2013-01-01
Issue Date:	2026-04-23 15:18:29 (UTC+8)
Publisher:	Academic Press Inc.;Elsevier Inc
Abstract:	摘要： ► Propose a new multi-level and coarse-to-fine structure for a human appearance. ► Combining multiple structures into a unified model by Gaussian mixture models. ► Identify a person using only one frame. ► Proposed model is invariant to rotation, scaling, translation, and shape changes. Surveillance of wide areas requires a system of multiple cameras to keep observing people, the non-rigid objects. In such a multiple view system, the appearance of people obtained in one camera is usually different from the appearance obtained in other cameras. In order to correctly identify people, the unique appearance model of each specific object should be invariant to such changes. Unlike previous methods building an appearance model by using only single camera, our appearance modeling, in this paper, is based on the multi-camera environment to fit real cases. Our appearance model is represented by two hierarchical tree structures that are responsible for color and texture information, respectively, where each layer of a tree is maintained by a Gaussian mixture model (GMM). The identification process is performed with a delicate voting scheme without complicated computations to meet the requirements of real-time applications. Experimental results show that our unique appearance model is robust to translation, rotation, scaling, and shape variations. Furthermore, it is equipped with automatic model updating, and it achieves a high precision rate and high processing performance. 出版者： Elsevier Inc 出版日期： 2013-08-01 出處： Journal of visual communication and image representation, 2013-08, Vol.24 (6), p.717-728 資源來源： Elsevier ScienceDirect Journals Complete 版權： 2012 Elsevier Inc. 識別號： ISSN: 1047-3203 識別號： EISSN: 1095-9076 識別號： DOI: 10.1016/j.jvcir.2012.01.018
Appears in Collections:	[Departmant of Mechanical Engineering ] journal & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	17	View/Open

社群 sharing

Loading...