The MATLAB/MEX code for pSIFT by Peter Hansen is available from Google code.
pSIFT is a feature detector and descriptor that is correct for wide angle images such as fisheye or panoramic cameras, that is, it explicitly accounts for the extreme spatial variability that occurs for windows near the edge
of the image. The original paper is:
Wide-angle Visual Feature Matching for Outdoor Localization
- Peter Hansen## Queensland University of Technology, Brisbane, Australia,firstname.lastname@example.org
- Peter Corke## CSIRO ICT Centre, Brisbane, Australia, email@example.com
- Wageeh Boles## Queensland University of Technology, Brisbane, Australia,firstname.lastname@example.org
Wide-angle images exhibit significant distortion for which existing scale-space detectors such as the scale-invariant feature transform (SIFT) are inappropriate. The required scale-space images for feature detection are correctly obtained through the convolution of the image, mapped to the sphere, with the spherical Gaussian. A new visual key-point detector, based on this principle, is developed and several computational approaches to the convolution are investigated in both the spatial and frequency domain. In particular, a close approximation is developed that has comparable computation time to conventional SIFT but with improved matching performance. Results are presented for monocular wide-angle outdoor image sequences obtained using fisheye and equiangular catadioptric cameras. We evaluate the overall matching performance (recall versus 1-precision) of these methods compared to conventional SIFT. We also demonstrate the use of the technique for variable frame-rate visual odometry and its application to place recognition.