Algorithm for Sequence Image Automatic Mosaic Based on SIFT Feature

Constraining by cameras’ 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.

[1]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[2]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[3]  Bernt Schiele,et al.  Local features for object class recognition , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[4]  Cordelia Schmid,et al.  Scale & Affine Invariant Interest Point Detectors , 2004, International Journal of Computer Vision.

[5]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[6]  Matthew A. Brown,et al.  Recognising panoramas , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[7]  T. Lindeberg,et al.  Scale-Space Theory : A Basic Tool for Analysing Structures at Different Scales , 1994 .

[8]  David G. Lowe,et al.  Shape indexing using approximate nearest-neighbour search in high-dimensional spaces , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[9]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.