Home // PATTERNS 2011, The Third International Conferences on Pervasive Patterns and Applications // View article

Application of Feature Point Detection and matching in 3D Objects Reconstruction

Authors:
Jie Yuan
Ting Feng
Yu Zhou
Yao Yu

Keywords: feature points; image matching; 3D object reconstruction

Abstract:
In this paper, we present a novel wide baseline based approach to detect and match feature points in image series. We found the wide baseline correspondence problem with large scale, rotation, illumination and affine transformations is still not tackled very well. We proposed a new matching method which based on multi-scale Harris algorithm and two-way guided matching to achieve large number of accurate point correspondences between un-calibrated image sequences of the same scene for wide baseline. We apply our method in the experiments of 3D object reconstruction with satisfied results. It shows that the guided matching method can be used for severe scene variations and provide evidence of improved performance with respect to the SIFT distance and Harris matchers. It is also useful to the matching in short baseline, and the results of this method are better than that of the traditional method.

Pages: 19 to 24

Copyright: Copyright (c) IARIA, 2011

Publication date: September 25, 2011

Published in: conference

ISSN: 2308-3557

ISBN: 978-1-61208-158-8

Location: Rome, Italy

Dates: from September 25, 2011 to September 30, 2011