Automatic Georeferencing of Aerial Images Using Stereo High-Resolution Satellite Images

Oh, Jaehong; Toth, Charles K.; Grejner‐Brzezinska, Dorota A.

doi:10.14358/pers.77.11.1157

Cited by 21 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is also assumed that the satellite image has been ortho-rectified using Rational Polynomial Coefficients (RPC) and a Digital Terrain Model (DTM). The method for image registration used here is the one that is described in Mendoza-Schrock et al (2009) andOh et al (2011). Full interior and exterior orientations are necessary for the generation of ortho-rectified images, which can both be calculated via photogrammetric resection.…”

Section: Proposed Change Detection Methodologymentioning

confidence: 99%

A methodology for near real-time change detection between Unmanned Aerial Vehicle and wide area satellite images

Fytsilis

Prokos

Koutroumbas

et al. 2016

ISPRS Journal of Photogrammetry and Remote Sensing

View full text Add to dashboard Cite

Section: Proposed Change Detection Methodologymentioning

confidence: 99%

A methodology for near real-time change detection between Unmanned Aerial Vehicle and wide area satellite images

Fytsilis

Prokos

Koutroumbas

et al. 2016

ISPRS Journal of Photogrammetry and Remote Sensing

View full text Add to dashboard Cite

“…Oh et al. () proposed the use of high‐resolution satellite images as a ground control source for automatic aerial image georeferencing. The authors used the scale‐invariant feature transform (SIFT) and random sample consensus (RANSAC) to match the images.…”

Section: Introductionmentioning

confidence: 99%

Locating Control Points In Aerial Images With A Multi‐Scale Approach Based On Terrestrial Image Patches

Berveglieri

Tommaselli

2015

The Photogrammetric Record

View full text Add to dashboard Cite

The objective of the proposed approach is to locate and measure ground control points in aerial images when large image search spaces are defined due to the use of inaccurate initial exterior orientation parameters, such as those provided by consumer-grade navigation systems. Vertical terrestrial image patches covering control point areas are generated and compared with aerial patches using feature-and area-based matching algorithms to automatically determine their corresponding positions in aerial images with sub-pixel precision. The approach is based on techniques for both image search space reduction and adaptive least squares matching. Experiments with real data were performed with bundle block triangulation and the results were analysed using control and check points in both object and image spaces. The proposed technique enabled a significant reduction in the search space within which it was feasible to successfully locate control points. Compared with manual measurements, the results obtained by the automatic technique were more accurate, achieving one-fifth of the ground sample distance in planimetric check point discrepancies.

show abstract

“…It is also used in medicine [7,8], robotics [9,10], computer vision [11,12], image matching [13] and engineering [14]. In geodesy it is used for segmentation and registration of laser scanning point clouds [15][16][17], satellite images registration [18,19] and improvement of the transformation parameters estimates between two coordinate systems [20,21].…”

Section: Introductionmentioning

confidence: 99%

The Influence of the Input Parameters Selection on the RANSAC Results

Urbančič¹,

Fras²,

Stopar³

2014

Int. j. simul. model.

View full text Add to dashboard Cite

The RANSAC (RANdom SAmpling and Consensus) enables us to search within a given group of points for subgroups of points that belong to a mathematically describable object or a part of an object. The number of iterations within a single repetition depends on the data, selection and settings of the input parameters (percentage of inliers, probability and minimum number of points that uniquely define a geometrical shape). In our research we applied simulation modelling to analyse the influence of the selection of input parameters on the approximation of the sphere and plane models.

show abstract

Automatic Georeferencing of Aerial Images Using Stereo High-Resolution Satellite Images

Cited by 21 publications

References 13 publications

A methodology for near real-time change detection between Unmanned Aerial Vehicle and wide area satellite images

A methodology for near real-time change detection between Unmanned Aerial Vehicle and wide area satellite images

Locating Control Points In Aerial Images With A Multi‐Scale Approach Based On Terrestrial Image Patches

The Influence of the Input Parameters Selection on the RANSAC Results

Contact Info

Product

Resources

About