A SIFT-Based DEM Extraction Approach Using GEOEYE-1 Satellite Stereo Pairs

Ioannis N Daliakopoulos; Ioannis K Tsanis

doi:10.3390/s19051123

A SIFT-Based DEM Extraction Approach Using GEOEYE-1 Satellite Stereo Pairs

Sensors (Basel). 2019 Mar 5;19(5):1123. doi: 10.3390/s19051123.

Authors

Ioannis N Daliakopoulos¹, Ioannis K Tsanis^{2

3}

Affiliations

¹ Department of Environmental Engineering, Technical University of Crete, 73100 Chania, Greece. daliakopoulos@hydromech.gr.
² Department of Environmental Engineering, Technical University of Crete, 73100 Chania, Greece. tsanis@hydromech.gr.
³ Department of Civil Engineering, McMaster University, Hamilton, ONL8S 4L8, Canada. tsanis@hydromech.gr.

Abstract

A module for Very High Resolution (VHR) satellite stereo-pair imagery processing and Digital Elevation Model (DEM) extraction is presented. A large file size of VHR satellite imagery is handled using the parallel processing of cascading image tiles. The Scale-Invariant Feature Transform (SIFT) algorithm detects potentially tentative feature matches, and the resulting feature pairs are filtered using a variable distance threshold RANdom SAmple Consensus (RANSAC) algorithm. Finally, point cloud ground coordinates for DEM generation are extracted from the homologous pairs. The criteria of average point spacing irregularity is introduced to assess the effective resolution of the produced DEMs. The module is tested with a 0.5 m × 0.5 m Geoeye-1 stereo pair over the island of Crete, Greece. Sensitivity analysis determines the optimum module parameterization. The resulting 1.5-m DEM has superior detail over reference DEMs, and results in a Root Mean Square Error (RMSE) of about 1 m compared to ground truth measurements.

Keywords: RANSAC; SIFT; algorithm; digital elevation model; satellite stereo pair.