Full metadata record
DC FieldValueLanguage
dc.contributorMulti-disciplinary Studiesen_US
dc.contributorDepartment of Electronic and Information Engineeringen_US
dc.creatorLun, Tak-chuen-
dc.publisherHong Kong Polytechnic University-
dc.rightsAll rights reserveden_US
dc.titleTechniques for video segmentation and object trackingen_US
dcterms.abstractTo take advantage of the potential new applications created by the emerging MPEG-4 and MPEG-7 object-based coding and indexing standards, video content must be structured as a composition of objects, for which a number of features are available. In some cases, these data are made available by the visual information production process itself. In other cases, this type of information is only partly available and thus some video analysis must be performed. Video analysis usually consists of identifying the relevant objects that-compose a scene (segmentation), and extracting relevant features for the individual objects or for the composed scene. The analysed data can be used both for content-based video coding and indexing. To provide the requested content-based functionalities, analysed data should be consistent in time, guaranteeing a correct tracking of the segmentation partition labels, and an appropriate handling of the extracted features. Two potentially useful video analysis results are: segmentation of the scene, and tracking of objects along the sequence. In this work, different techniques for video segmentation are first studied. The characteristics and constrains of different segmentation methods are investigated. A new block based recursive shortest spanning tree (BRSST) method is developed for object-based video segmentation. An application of the proposed techniques in car occupant detection is discussed. One of the most common applications of object-based video segmentation is object tracking. A software platform is then developed to study different techniques for object tracking.en_US
dcterms.extent87 leaves : ill. ; 30 cmen_US
dcterms.isPartOfPolyU Electronic Thesesen_US
dcterms.educationalLevelAll Masteren_US
dcterms.LCSHImage processingen_US
dcterms.LCSHHong Kong Polytechnic University -- Dissertationsen_US
dcterms.accessRightsrestricted accessen_US

Files in This Item:
File Description SizeFormat 
b15995811.pdfFor All Users (off-campus access for PolyU Staff & Students only)2.58 MBAdobe PDFView/Open

Copyright Undertaking

As a bona fide Library user, I declare that:

  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
  3. I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.

By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.

Show simple item record

Please use this identifier to cite or link to this item: https://theses.lib.polyu.edu.hk/handle/200/2174