Scale invariant feature matching with wide angle images

• Published in: 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems pp. 1689 - 1694
• Main Authors: Hansen, Peter, Corke, Peter, Boles, Wageeh, Daniilidis, Kostas
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.10.2007
• Subjects: Cameras; Computer vision; Convolution; Geometry; Image analysis; Intelligent robots; Layout; Robot vision systems; Simultaneous localization and mapping; USA Councils
• ISBN: 9781424409112; 142440911X
• ISSN: 2153-0858
• DOI: 10.1109/IROS.2007.4399266

Numerous scale-invariant feature matching algorithms using scale-space analysis have been proposed for use with perspective cameras, where scale-space is defined as convolution with a Gaussian. The contribution of this work is a method suitable for use with wide angle cameras. Given an input image, we map it to the unit sphere and obtain scale-space images by convolution with the solution of the spherical diffusion equation on the sphere which we implement in the spherical Fourier domain. Using such an approach, the scale-space response of a point in space is independent of its position on the image plane for a camera subject to pure rotation. Scale-invariant features are then found as local extrema in scale-space. Given this set of scale-invariant features, we then generate feature descriptors by considering a circular support region defined on the sphere whose size is selected relative to the feature scale. We compare our method to a naive implementation of SIFT where the image is treated as perspective, where our results show an improvement in matching performance.