Algorithm for Sequence Image Automatic Mosaic Based on SIFT Feature

摘要

Constraining by camerasȁ9; view-angles of the outdoor monitoring systems, the panoramic digital images fail to be obtained directly from photographing. A method is proposed on the basis of the scale invariance feature transform (i.e. SIFT) algorithm to stitch images captured by the turning video cameras together to form panoramic images. Based on the SIFT features and the retrofitted KD-Tree structure, the BBF searching strategy is employed to match feature points. Then in a post-processing pass, the Ransac algorithm is adopted to remove the mismatching feature points. Photos captured by a surveillance camera are taken as the input to test the proposed method. According to the test, the whole processing time of stitch is reduced while the fidelity of resulting stitched panoramic images is ensured.