Efficient cost aggregation for feature-vector-based wide-baseline stereo matching

Abstract ■■■ In stereo matching applications, local cost aggregation techniques are usually preferred over global methods due to their speed and ease of implementation. Local methods make implicit smoothness assumptions by aggregating costs within a finite window; however, cost aggregation is a time...

Full description

Bibliographic Details
Main Authors: Xiaoming Peng, Abdesselam Bouzerdoum, Son Lam Phung
Format: Article
Language:English
Published: SpringerOpen 2018-04-01
Series:EURASIP Journal on Image and Video Processing
Subjects:
Online Access:http://link.springer.com/article/10.1186/s13640-018-0249-y
id doaj-2c1a1243cab14158873e31c2c8051be5
record_format Article
spelling doaj-2c1a1243cab14158873e31c2c8051be52020-11-25T00:26:00ZengSpringerOpenEURASIP Journal on Image and Video Processing1687-52812018-04-012018111610.1186/s13640-018-0249-yEfficient cost aggregation for feature-vector-based wide-baseline stereo matchingXiaoming Peng0Abdesselam Bouzerdoum1Son Lam Phung2School of Electrical, Computer and Telecommunications Engineering, University of WollongongSchool of Electrical, Computer and Telecommunications Engineering, University of WollongongSchool of Electrical, Computer and Telecommunications Engineering, University of WollongongAbstract ■■■ In stereo matching applications, local cost aggregation techniques are usually preferred over global methods due to their speed and ease of implementation. Local methods make implicit smoothness assumptions by aggregating costs within a finite window; however, cost aggregation is a time-consuming process. Furthermore, most existing local methods are based on pixel intensity values, and hence are not efficient with feature vectors used in wide-baseline stereo matching. In this paper, a new cost aggregation method is proposed, where a Per-Column Cost matrix is combined with a feature-vector-based weighting strategy to achieve both matching accuracy and computational efficiency. Here, the proposed cost aggregation method is applied with the DAISY feature descriptor for wide-baseline stereo matching; however, this method can also be applied to a fast growing number of stereo matching techniques that are based on feature descriptors. A performance comparison with several benchmark local cost aggregation approaches is presented, along with a thorough analysis of the time and storage complexity of the proposed method.http://link.springer.com/article/10.1186/s13640-018-0249-yStereo matchingCost aggregationFeature vectorDAISY
collection DOAJ
language English
format Article
sources DOAJ
author Xiaoming Peng
Abdesselam Bouzerdoum
Son Lam Phung
spellingShingle Xiaoming Peng
Abdesselam Bouzerdoum
Son Lam Phung
Efficient cost aggregation for feature-vector-based wide-baseline stereo matching
EURASIP Journal on Image and Video Processing
Stereo matching
Cost aggregation
Feature vector
DAISY
author_facet Xiaoming Peng
Abdesselam Bouzerdoum
Son Lam Phung
author_sort Xiaoming Peng
title Efficient cost aggregation for feature-vector-based wide-baseline stereo matching
title_short Efficient cost aggregation for feature-vector-based wide-baseline stereo matching
title_full Efficient cost aggregation for feature-vector-based wide-baseline stereo matching
title_fullStr Efficient cost aggregation for feature-vector-based wide-baseline stereo matching
title_full_unstemmed Efficient cost aggregation for feature-vector-based wide-baseline stereo matching
title_sort efficient cost aggregation for feature-vector-based wide-baseline stereo matching
publisher SpringerOpen
series EURASIP Journal on Image and Video Processing
issn 1687-5281
publishDate 2018-04-01
description Abstract ■■■ In stereo matching applications, local cost aggregation techniques are usually preferred over global methods due to their speed and ease of implementation. Local methods make implicit smoothness assumptions by aggregating costs within a finite window; however, cost aggregation is a time-consuming process. Furthermore, most existing local methods are based on pixel intensity values, and hence are not efficient with feature vectors used in wide-baseline stereo matching. In this paper, a new cost aggregation method is proposed, where a Per-Column Cost matrix is combined with a feature-vector-based weighting strategy to achieve both matching accuracy and computational efficiency. Here, the proposed cost aggregation method is applied with the DAISY feature descriptor for wide-baseline stereo matching; however, this method can also be applied to a fast growing number of stereo matching techniques that are based on feature descriptors. A performance comparison with several benchmark local cost aggregation approaches is presented, along with a thorough analysis of the time and storage complexity of the proposed method.
topic Stereo matching
Cost aggregation
Feature vector
DAISY
url http://link.springer.com/article/10.1186/s13640-018-0249-y
work_keys_str_mv AT xiaomingpeng efficientcostaggregationforfeaturevectorbasedwidebaselinestereomatching
AT abdesselambouzerdoum efficientcostaggregationforfeaturevectorbasedwidebaselinestereomatching
AT sonlamphung efficientcostaggregationforfeaturevectorbasedwidebaselinestereomatching
_version_ 1725346502079938560