Full metadata record
DC FieldValueLanguage
dc.contributor.authorLing, Chih-Hungen_US
dc.contributor.authorLiang, Yu-Mingen_US
dc.contributor.authorLin, Chia-Wenen_US
dc.contributor.authorChen, Yong-Shengen_US
dc.contributor.authorLiao, Hong-Yuan Marken_US
dc.date.accessioned2014-12-08T15:20:41Z-
dc.date.available2014-12-08T15:20:41Z-
dc.date.issued2011-11-01en_US
dc.identifier.issn1057-7149en_US
dc.identifier.urihttp://dx.doi.org/10.1109/TIP.2011.2158228en_US
dc.identifier.urihttp://hdl.handle.net/11536/14706-
dc.description.abstractWe propose a human object inpainting scheme that divides the process into three steps: 1) human posture synthesis; 2) graphical model construction; and 3) posture sequence estimation. Human posture synthesis is used to enrich the number of postures in the database, after which all the postures are used to build a graphical model that can estimate the motion tendency of an object. We also introduce two constraints to confine the motion continuity property. The first constraint limits the maximum search distance if a trajectory in the graphical model is discontinuous, and the second confines the search direction in order to maintain the tendency of an object's motion. We perform both forward and backward predictions to derive local optimal solutions. Then, to compute an overall best solution, we apply the Markov random field model and take the potential trajectory with the maximum total probability as the final result. The proposed posture sequence estimation model can help identify a set of suitable postures from the posture database to restore damaged/missing postures. It can also make a reconstructed motion sequence look continuous.en_US
dc.language.isoen_USen_US
dc.subjectDimensionality reductionen_US
dc.subjectisomapen_US
dc.subjectmanifold learningen_US
dc.subjectobject completionen_US
dc.subjectvideo inpaintingen_US
dc.titleHuman Object Inpainting Using Manifold Learning-Based Posture Sequence Estimationen_US
dc.typeArticleen_US
dc.identifier.doi10.1109/TIP.2011.2158228en_US
dc.identifier.journalIEEE TRANSACTIONS ON IMAGE PROCESSINGen_US
dc.citation.volume20en_US
dc.citation.issue11en_US
dc.citation.spage3124en_US
dc.citation.epage3135en_US
dc.contributor.department資訊工程學系zh_TW
dc.contributor.departmentDepartment of Computer Scienceen_US
dc.identifier.wosnumberWOS:000296016200011-
dc.citation.woscount2-
Appears in Collections:Articles


Files in This Item:

  1. 000296016200011.pdf

If it is a zip file, please download the file and unzip it, then open index.html in a browser to view the full text content.