Fast Mosaicking Panoramic Images with Parallax Scene from a PTZ Camera

This paper presents a fast panoramic mosaic algorithm from a video sequence with parallax scene taken by a PTZ camera. A new approach that uses a four-step automatic imaging mosaic, based on interest points, is proposed. The four steps are extraction of interest points, finding corresponding points in the stitching images, deriving the spatial transform matrix then image mosaic. In order to reduce the cost of searching best match of feature points, we employ SIFT-16 descriptor and the LMPs descriptor as index . Our method preserves the efficiency and accuracy of image mosaic.

[1]  Biswajit Bose,et al.  From video sequences to motion panoramas , 2002, Workshop on Motion and Video Computing, 2002. Proceedings..

[2]  Dan Xu,et al.  Complex wavelet-based image mosaics using edge-preserving visual perception modeling , 1999, Comput. Graph..

[3]  Richard Szeliski,et al.  Efficiently registering video into panoramic mosaics , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[4]  Luigi di Stefano,et al.  An effective real-time mosaicing algorithm apt to detect motion through background subtraction using a PTZ camera , 2005, IEEE Conference on Advanced Video and Signal Based Surveillance, 2005..

[5]  Hui Zhou,et al.  A Novel Hierarchical Method of Ship Detection from Spaceborne Optical Image Based on Shape and Texture Features , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[6]  Gui Yun Tian,et al.  Comprehensive interest points based imaging mosaic , 2003, Pattern Recognit. Lett..

[7]  Cordelia Schmid,et al.  A performance evaluation of local descriptors , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[9]  Li Zhao,et al.  Mosaic image method: a local and global method , 1999, Pattern Recognit..

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