Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XL-5/W4, 315-323, 2015
http://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XL-5-W4/315/2015/
doi:10.5194/isprsarchives-XL-5-W4-315-2015
© Author(s) 2015. This work is distributed
under the Creative Commons Attribution 3.0 License.
 
18 Feb 2015
ADVANCES IN IMAGE PRE-PROCESSING TO IMPROVE AUTOMATED 3D RECONSTRUCTION
A. Ballabeni1, F. I. Apollonio1, M. Gaiani1, and F. Remondino2 1Dept. of Architecture – University of Bologna, Italy
23D Optical Metrology (3DOM) unit, Bruno Kessler Foundation (FBK), Trento, Italy
Keywords: Pre-processing, Filtering, Matching, Automation, Denoising, RGB to Gray, Color, 3D reconstruction Abstract. 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.
Conference paper (PDF, 2903 KB)


Citation: Ballabeni, A., Apollonio, F. I., Gaiani, M., and Remondino, F.: ADVANCES IN IMAGE PRE-PROCESSING TO IMPROVE AUTOMATED 3D RECONSTRUCTION, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XL-5/W4, 315-323, doi:10.5194/isprsarchives-XL-5-W4-315-2015, 2015.

BibTeX EndNote Reference Manager XML