ADVANCES IN IMAGE PRE-PROCESSING TO IMPROVE AUTOMATED 3D RECONSTRUCTION

Tools and algorithms for automated image processing and 3D reconstruction purposes have become more and more available, giving the possibility to process any dataset of unoriented and markerless images. Typically, dense 3D point clouds (or texture 3D polygonal models) are produced at reasonable proc...

Full description

Saved in:

Bibliographic Details
Published in:	International archives of the photogrammetry, remote sensing and spatial information sciences. Vol. XL-5/W4; no. 5; pp. 315 - 323
Main Authors:	Ballabeni, A., Apollonio, F. I., Gaiani, M., Remondino, F.
Format:	Journal Article Conference Proceeding
Language:	English
Published:	Gottingen Copernicus GmbH 01.01.2015 Copernicus Publications
ISSN:	2194-9034, 1682-1750, 2194-9034
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Tools and algorithms for automated image processing and 3D reconstruction purposes have become more and more available, giving the possibility to process any dataset of unoriented and markerless images. Typically, dense 3D point clouds (or texture 3D polygonal models) are produced at reasonable processing time. In this paper, we evaluate how the radiometric pre-processing of image datasets (particularly in RAW format) can help in improving the performances of state-of-the-art automated image processing tools. Beside a review of common pre-processing methods, an efficient pipeline based on color enhancement, image denoising, RGB to Gray conversion and image content enrichment is presented. The performed tests, partly reported for sake of space, demonstrate how an effective image pre-processing, which considers the entire dataset in analysis, can improve the automated orientation procedure and dense 3D point cloud reconstruction, even in case of poor texture scenarios.
Bibliography:	ObjectType-Article-1 ObjectType-Feature-2 SourceType-Conference Papers & Proceedings-1 content type line 22
ISSN:	2194-9034 1682-1750 2194-9034
DOI:	10.5194/isprsarchives-XL-5-W4-315-2015