Automated mosaicking of UAV images based on SFM method

Optical sensors onboard an unmanned aerial vehicle (UAV) can collect high resolution images with small dimensions. Image mosaicking is necessary to cover a larger geographic area. This paper presents a novel approach to mosaicking UAV images automatically. The "Orthophoto Map" is based on Structure From Motion (SFM). This method can fully automatic mosaic generate a wide range, and with well visual effects, and no evident deformation. This method can not only get a panoramic image of wide range of areas, and can get the corresponding three-dimensional terrain model.

[1]  Manolis I. A. Lourakis,et al.  SBA: A software package for generic sparse bundle adjustment , 2009, TOMS.

[2]  Jennifer A. Scott,et al.  Algorithm 891: A Fortran virtual memory system , 2009, TOMS.

[3]  Frank Dellaert,et al.  Structure from motion without correspondence , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[4]  Matthew A. Brown,et al.  Unsupervised 3D object recognition and reconstruction in unordered datasets , 2005, Fifth International Conference on 3-D Digital Imaging and Modeling (3DIM'05).

[5]  Juha Röning,et al.  Intelligent Robots and Computer Vision XXIII: Algorithms, Techniques, and Active Vision , 1992 .

[6]  Ernest L. Hall,et al.  Intelligent Robots and Computer Vision VI , 1987 .