期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：2012
卷号：XXXIX-B5
页码：387-392
DOI：10.5194/isprsarchives-XXXIX-B5-387-2012
出版社：Copernicus Publications
摘要：Implicit in the projective transformation between object and image space in photogrammetry is the requirement that measured coordinates of points in the digital images accurately represent true values within the image coordinate system. This means that the integrity of image point positions has to be retained throughout the in-camera image preprocessing stage. However, the process of image formation and formatting for storage can impact upon image point position and it is imperative for subsequent photogrammetric measurement that image perturbations due to both sensor non-linearities and digital image file creation be fully described, modelled and mitigated to the maximum extent possible. Given that the integrity of image geometry is such an important factor in the optimisation of measurement accuracy in close-range photogrammetry, investigations into digital image formation are warranted. This paper describes such an investigation and it reports the development of a preprocessing approach for RAW imagery than can yield significant photogrammetric accuracy improvements over those obtained with JPEG imagery.
