| EVALUATION OF SELECTED COST AGGREGATION METHODS ON HIGH RESOLUTION SATELLITE STEREO IMAGES |
| Paper ID : 1095-SMPR |
| Authors: |
|
Nurollah Tatar *1, Hossein Arefi2 1School of Surveying and Geomatics, College of Engineering, University of Tehran 2University of Tehran |
| Abstract: |
| Dense stereo processing requires a critical step that called cost aggregation or cost optimization. Most of the cost aggregation methods are evaluated on close range stereo images from Middlebury or KITTI datasets. In this paper, three typical cost aggregation methods together with another approach which is a combination of these methods are evaluated. The approaches have been implemented on high resolution satellite stereo images and then are compared with LiDAR ground truth. These methods including Semi-Global Matching (SGM), Guided Filtering (GF), iterative GF (IGF), and SGM followed by GF (SGM-GF) with Census and Zero Normalized Cross Correlation (ZNCC) cost functions. Although the Census cost function has a good performance on the border of the objects and low blurring effects, the results of both cost functions, i.e. Census and ZNCC, have same treatment on all stereo methods. Also, in order to make an impartial assessment, for all stereo methods, we do not perform any disparity map refinement. The experimental results on WV III stereo images demonstrate that the SGM method has lower accuracy and SGM-GF method is accurate than other methods. |
| Keywords: |
| Stereo matching, Cost aggregation, High-resolution satellite images, Satellite stereo images |
| Status : Conditional Accept (Oral Presentation) |
