Matching of straight line segments from aerial stereo images of urban areas

Reliable extraction of corresponding straight lines in overlapping images can be used for different purposes such as 3D object extraction, image registration, automated triangulation, etc. In this study, a new approach for the matching of straight line features from stereo aerial images is presented. Initial correspondences between stereo images are generated using a pair-wise stereo matching approach, which involves a total of seven relational constraints. The final straight line correspondences between the stereo images are established in a line-to-line matching stage. The optimal settings for the parameters guiding the matching phase are determined after analysing the probability density functions (PDFs). The proposed approach is tested on 30 image patches of two different urban areas, and as a result, very successful and promising stereo line matching performances are achieved. Besides, the comparison of the results of the proposed approach with the results of one of the state-of-the-art stereo matching approaches proves the superiority and potential of the proposed approach.

► New approach for the matching of line segments from stereo aerial images is proposed. ► An empirical analysis based on training data is developed to select the parameters. ► Proposed measures are very useful to separate correct and incorrect line matches. ► Global thresholding provides a good balance between correctness and completeness. ► The analyses revealed that occlusion is still the major reason for the mismatches.