Share Email Print
cover

Proceedings Paper

Object localization using adaptive feature selection
Author(s): S. Youngkyoo Hwang; Jungbae Kim; Seongdeok Lee
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

'Fast and robust' are the most beautiful keywords in computer vision. Unfortunately they are in trade-off relationship. We present a method to have one's cake and eat it using adaptive feature selections. Our chief insight is that it compares reference patterns to query patterns, so that it selects smartly more important and useful features to find target. The probabilities of pixels in the query to belong to the target are calculated from importancy of features. Our framework has three distinct advantages: 1 - It saves computational cost dramatically to the conventional approach. This framework makes it possible to find location of an object in real-time. 2 - It can smartly select robust features of a reference pattern as adapting to a query pattern. 3- It has high flexibility on any feature. It doesn't matter which feature you may use. Lots of color space, texture, motion features and other features can fit perfectly only if the features meet histogram criteria.

Paper Details

Date Published: 19 January 2009
PDF: 8 pages
Proc. SPIE 7252, Intelligent Robots and Computer Vision XXVI: Algorithms and Techniques, 72520Q (19 January 2009); doi: 10.1117/12.805840
Show Author Affiliations
S. Youngkyoo Hwang, Samsung Advanced Institute of Technology (South Korea)
Jungbae Kim, Samsung Advanced Institute of Technology (South Korea)
Seongdeok Lee, Samsung Advanced Institute of Technology (South Korea)


Published in SPIE Proceedings Vol. 7252:
Intelligent Robots and Computer Vision XXVI: Algorithms and Techniques
David P. Casasent; Ernest L. Hall; Juha Röning, Editor(s)

© SPIE. Terms of Use
Back to Top