An explicit growth model of the stereo region growing algorithm for parallel processing

Dongjoe Shin, J-P Muller

Research output: Chapter in Book/Report/Conference proceedingConference contribution

14 Downloads (Pure)

Abstract

GOTCHA is a well-tried and tested stereo region growing algorithm, which iteratively applies Adaptive Least Square Correlation (ALSC) matching to the adjacent neighbours of a seed point in order to achieve a dense reconstruction with sub-pixel precision. It is, however, a computationally expensive algorithm as every seed point collected by the ALSC matching produces quadrants or octants of new matching candidates. Accordingly, the computational complexity increases exponentially as the stereo matching region grows. To expedite the matching process of a traditional GOTCHA, this paper proposes a parallelised stereo region growing algorithm called a MT-GOTCHA. To achieve data parallelism, the proposed method initially divides a stereo image from arbitrary
distributed seed points, which are able to employ multiple GOTCHA’s. In addition, since it estimates a cluster of neighbours using a non-linear diffusion equation and performs multiple ALSC processes in parallel to verify local matching candidates, more tiepoints are obtained within less processing time. Experimental results demonstrate the proposed method can reduce the processing time of a dense reconstruction at a reasonable cost of memory consumption.
Original languageEnglish
Title of host publicationProceedings of the ISPRS Commission V Mid-Term Symposium 'Close Range Image Measurement Techniques'
EditorsJ. P. Mills, D. M. Barber, P. E. Miller, I. Newton
PublisherInternational Society for Photogrammetry and Remote Sensing
Pages543-548
VolumeXXXVIII
Publication statusPublished - Jun 2010
Externally publishedYes
EventISPRS Commission V Midterm Symposium on Close Range Image Measurement Techniques - Newcastle upon Tyne, United Kingdom
Duration: 21 Jun 201024 Jun 2010

Publication series

NameThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
ISSN (Print)1682-1750
ISSN (Electronic)2194-9034

Conference

ConferenceISPRS Commission V Midterm Symposium on Close Range Image Measurement Techniques
Abbreviated titleISPRS
Country/TerritoryUnited Kingdom
CityNewcastle upon Tyne
Period21/06/1024/06/10

Fingerprint

Dive into the research topics of 'An explicit growth model of the stereo region growing algorithm for parallel processing'. Together they form a unique fingerprint.

Cite this