Image matching is a key issue in Vision-Based UAV navigation problems. This paper presents an affine and rotation-invariant SIFT features descriptor for matching UAV image with satellite images. The SIFT and ASIFT algorithm are nowadays widely applied for robust image matching, but it also has a high computational complexity. SURF is used for real-time UAV position estimation but is not satisfied for affine invariant. We introduce the new SIFT feature descriptor based on pie chart region. This descriptor is invariant for rotation, affine, scale and the dimension of the feature vector is relatively reduced. Therefore, this method satisfies robustness and low computational complexity. Experiments show that this method can improve the matching accuracy and robustness.
Rotation and affine-invariant SIFT descriptor for matching UAV images with satellite images
01.08.2014
592421 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
A SIFT descriptor with global context
IEEE | 2005
|Local feature extraction and matching on range images: 2.5D SIFT
British Library Online Contents | 2009
|Applications for Affine Invariant Descriptor and Affine Parameter Estimation Based on Two-Source ICA
British Library Online Contents | 2006
|Image Matching Based on a Local Invariant Descriptor
British Library Conference Proceedings | 2005
|Image matching based on a local invariant descriptor
IEEE | 2005
|