Title :
Feature point correspondence in the presence of occlusion
Author :
Salari, V. ; Sethi, Ishwar K.
Author_Institution :
Dept. of Comput. Sci., Wayne State Univ., Detroit, MI, USA
fDate :
1/1/1990 12:00:00 AM
Abstract :
Occlusion and poor feature point detection are two of the main difficulties in the use of multiple frames for establishing correspondence of feature points. A formulation of the correspondence problem as an optimization problem is used to handle these difficulties. Modifications to an existing iterative optimization procedure for solving the formulation of the correspondence problem are discussed. Experimental results are presented to show the merits of the formulation
Keywords :
iterative methods; optimisation; pattern recognition; feature point correspondence; feature point detection; iterative optimization; multiple frames; occlusion; pattern recognition; Computer science; Computer vision; Geometry; Image edge detection; Image sequences; Laplace equations; Layout; Lighting; Remuneration; Tracking;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on