A coarse-to-fine approach for the generation and tracking of mesh objects from a natural image sequence

J. T. Ko, Sheng-Jyh Wang*

*Corresponding author for this work

Research output: Contribution to conferencePaperpeer-review

Abstract

In this paper, a new scheme, which automatically generates a hierarchical mesh from a real image, is proposed. First, three distinct meshes are generated according to a three-layer image pyramid. By eliminating the duplicated mesh nodes between these three meshes, a hierarchical mesh is formed. Because each hierarchy represents the image in different resolutions, this hierarchical structure can achieve progressive coding. Furthermore, to generate a dynamic mesh for an image sequence, this hierarchical structure can help to reduce the computation complexity through the tracking of mesh nodes in the sequence. A method is also proposed to predict the moving direction of mesh nodes and to facilitate the motion estimation.

Original languageEnglish
Pages883-886
Number of pages4
StatePublished - 1 Dec 2000
EventInternational Conference on Image Processing (ICIP 2000) - Vancouver, BC, Canada
Duration: 10 Sep 200013 Sep 2000

Conference

ConferenceInternational Conference on Image Processing (ICIP 2000)
CountryCanada
CityVancouver, BC
Period10/09/0013/09/00

Fingerprint Dive into the research topics of 'A coarse-to-fine approach for the generation and tracking of mesh objects from a natural image sequence'. Together they form a unique fingerprint.

Cite this