Abstract

This paper describes a novel multi-view matching framework based on a new type of invariant feature. Our features are located at Harris corners in discrete scale-space and oriented using a blurred local gradient. This defines a rotationally invariant frame in which we sample a feature descriptor, which consists of an 8 × 8 patch of bias/gain normalised intensity values. The density of features in the image is controlled using a novel adaptive non-maximal suppression algorithm, which gives a better spatial distribution of features than previous approaches. Matching is achieved using a fast nearest neighbour algorithm that indexes features based on their low frequency Haar wavelet coefficients. We also introduce a novel outlier rejection procedure that verifies a pairwise feature match based on a background distribution of incorrect feature matches. Feature matches are refined using RANSAC and used in an automatic 2D panorama stitcher that has been extensively tested on hundreds of sample inputs. 1

Citations

3104	Distinctive Image Features from Scale-Invariant Keypoints - Lowe - 2004
1481	An Iterative Image Registration Technique with an Application to Stereo Vision - Lucas, Kanade - 1981
774	A performance evaluation of local descriptors - Mikolajczyk, Schmid - 2003
523	Hierarchical Model-Based Motion Estimation - BERGEN, ANANDAN, et al. - 1992
424	Robust wide baseline stereo from maximally stable extremal regions - Matas, Chum, et al. - 2002
367	Local gray-value invariants for image retrieval - Schmid, Mohr - 1997
224	Evaluation of interest point detectors - Schmid, Mohr, et al.
185	Reliable feature matching across widely separated views - Baumberg - 2000
146	Multiview matching for unordered image sets, or ”how do i organize my holiday snaps - Schaffalitzky, Zisserman - 2002
139	Recognising panoramas - Brown, Lowe
130	Gool, L.,” wide Baseline Stereo Matching Based - Tuytelaars, Van - 2000
99	Transformation invariance in pattern recognition-tangent distance and tangent propogation - Simard, Cun, et al. - 1998
72	Invariant features from interest points groups - Brown, Lowe - 2002
32	Geometry from visual motion - Harris - 1992
13	feature-based correspondence algorithm for image matching - Förstner, BA - 1986
7	Multi-scale local phase-based features - Carneiro, Jepson - 2003