Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Cooperative Matching Paradigm for the Analysis of Stereo Image Sequences
 

Summary: Cooperative Matching Paradigm for the Analysis
of Stereo Image Sequences
Wen-Hung Liao, J. K. Aggarwal
Computer and Vision Research Center, Department of Electrical and Computer Engineering, University of Texas
at Austin, Austin, TX 78712-1084
ABSTRACT: A general framework for the analysis of sequences of most algorithms consider only two sets of features at a time, we
stereo images is presented in this article. The proposed paradigm choose to incorporate more feature sets (three or four) in the
integrates spatial and temporal information to achieve robustness in feature-matching stage to reduce the correspondence ambiguities.
establishing stereo correspondence from images that possess a lim- Even though the simultaneous consideration of features from both
ited number of salient features. Specifically, the recovery of dynamic
the spatial and the temporal domain unavoidably increases the
stereo information, and thus, the reconstruction of a three-dimen-
computational complexity, the resulting algorithm offers ro-sional object structure, is accomplished using a feature-based ap-
bustness that is particularly appropriate when the extracted fea-proach. The multiset feature correspondence problem is cast into a
tures are not stable [5]. Moreover, the generic paradigm can befour-dimensional problem which is subsequently solved using a
tuned according to domain-specific knowledge to achieve bettergreedy-type local search algorithm. No assumption is made about
the type of motion. The proposed algorithm may be applied to process efficiency, as will be shown later in the article.
image sequences containing both rigid and nonrigid shapes. The ef- The rest of the article is organized as follows. In Section II,
ficacy of the proposed approach is tested using both synthetic data we present a brief review of techniques in shape and motion
and real images of a live frog's ventricle acquired by a stereo light analysis based on the cooperative matching principle. We moti-

  

Source: Aggarwal, J. K. - Department of Electrical and Computer Engineering, University of Texas at Austin

 

Collections: Computer Technologies and Information Sciences; Engineering