A Sub-Harris Operator Coupled with SIFT for Fast Images Matching in Low-altitude Photogrammetry

Fast and robust images matching are of vital importance in low-altitude photogrammetric process. Among the most popular features of images matching are currently SIFT and Harris etc. For time-critical applications such as disaster monitoring, the SIFT features extraction are too slow, and the location accuracy of SIFT and Harris is insufficient in photogrammetric process. In this paper, we present a sub-Harris operator coupled with SIFT for fast images matching in low-altitude photogrammetry. Firstly, the original stereopair is down-sampled to small scaling images, in which rough relative orientation is computed by the corresponding points obtained from SIFT matching. Then sub-pixel level precise Harris corners are extracted within original scale images. Finally, the corresponding points are found in the sets of sub-Harris corners consistent with epipolar geometry obtained from rough images matching. Experimental results show that the proposed method can achieve more excellent performances in accuracy than SIFT and Harris operator based method in the relative orientation, and significantly improve the computational efficiency compared with SIFT.