Stereo Matching with Weighted Feature Constraints for Aerial Images

The stereo correspondence problem represents a great challenge in Photogrammetry. In recent years, the Semi-Global Matching (SGM) method proposed by Hirschmüller et. al. is a promising approach for solving stereo matching problems in different applications and data sets, including aerial images. In this paper, a Ground Control Points based Semi-Global stereo Matching (GCP-SGM) method is proposed for aerial images. Ground Control Points are incorporated into the global energy function model in SGM to lessen matching ambiguities. Significant accuracy improvement is obtained by utilizing the prior information in the ground control points as soft constraints. Experimental results in real scenes show that when such prior information exists, the GCP-SGM method can effectively improve accuracy.