This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene. The features are invariant to image scale and rotation, and are shown to provide robust matching across a a substantial range of affine distortion, change in 3D viewpoint, addition of noise, and change in illumination.
|
1435
|
A.: Multiple View Geometry in Computer Vision, 2nd edn
– Hartley, Zisserman
- 2004
|
|
864
|
A combined corner and edge detector
– Harris, Stephens
- 1988
|
|
576
|
Object Recognition from Local Scale-invariant Features
– Lowe
- 1999
|
|
494
|
The structure of images
– Koenderink
- 1984
|
|
444
|
A.: An optimal algorithm for approximate nearest neighbor searching
– ARYA, MOUNT, et al.
- 1994
|
|
415
|
An algorithm for finding best matches in logarithmic expected time
– Friedman, Bentley, et al.
- 1977
|
|
402
|
Scale-space filtering
– Witkin
- 1983
|
|
374
|
Scale and affine invariant interest point detectors
– Mikolajczyk, Schmid
|
|
337
|
Generalizing the Hough transform to detect arbitrary shapes
– Ballard
- 1981
|
|
288
|
Object Recognition by Computer: The Role of Geometric Constraints
– Grimson
- 1991
|
|
275
|
Local Grayvalue Invariants for Image Retrieval
– Schmid, Mohr
- 1997
|
|
230
|
A method and means for recognizing complex patterns
– Hough
- 1962
|
|
212
|
Fitting parameterized three-dimensional models to images
– Lowe
- 1991
|
|
206
|
T.: Robust wide baseline stereo from maximally stable extremal regions. BMVC
– Matas, Chum, et al.
- 2002
|
|
183
|
Color constant color indexing
– Funt, Finlayson
- 1995
|
|
181
|
O.: The fundamental matrix: Theory, algorithms, and stability analysis
– Luong, Faugeras
- 1996
|
|
160
|
Unsupervised learning of models for recognition
– Weber, Welling, et al.
- 2000
|
|
150
|
Reliable feature matching across widely separated views
– Baumberg
- 2000
|
|
148
|
Recognition without correspondence using multidimensional receptive field histograms
– Schiele, Crowley
- 2000
|
|
104
|
Detecting salient blob-like image structures and their scales with a scale-space primal sketch: A method for focus of attention
– Lindeberg
- 1993
|
|
95
|
Motion Segmentation and Outlier Detection
– Torr
- 1995
|
|
93
|
Multi-View Matching for Unordered Image Sets, or How Do I Organize My Holiday Snaps
– Schaffalitzky, Zisserman
- 2002
|
|
83
|
Shape indexing using approximate nearest-neighbour search
– Beis, Lowe
- 1997
|
|
66
|
Scale-Space Theory: A Basic Tool for Analysing Structures at Different Scales
– Lindeberg
- 1994
|
|
55
|
Approximate nearest neighbor queries in fixed dimensions
– Arya, Mount
- 1993
|
|
53
|
Vision-based mobile robot localization and mapping using scale-invariant features
– Se, Lowe, et al.
- 2001
|
|
51
|
A representation for shape based on peaks and ridges in the difference of lowpass transform
– Crowley, Parker
- 1984
|
|
46
|
Invariant Features from Interest Point Groups
– Brown, Lowe
- 2002
|
|
40
|
Local feature view clustering for 3D object recognition
– Lowe
- 2001
|
|
33
|
View-based object recognition using saliency maps
– Shokoufandeh, Marsic, et al.
- 1999
|
|
32
|
Global localization using distinctive visual features
– Se, Lowe, et al.
- 2002
|
|
29
|
Geometry from visual motion
– Harris
- 1992
|
|
29
|
Large-scale tests of a keyed, appearance-based 3-D object recognition system. Vision Research
– Nelson, Selinger
- 1998
|
|
28
|
Shape recognition with edge-based features
– Mikolajczyk, Zisserman, et al.
- 2003
|
|
26
|
Probabilistic models of appearance for 3-D object recognition
– Pope, Lowe
- 2000
|
|
26
|
Gool. Wide baseline stereo based on local, affinely invariant regions
– Tuytelaars, Van
- 2000
|
|
22
|
Recognition using region correspondences
– Basri, Jacobs
- 1997
|
|
20
|
Phase-based local features
– Carneiro, Jepson
- 2002
|
|
19
|
Detection of local features invariant to affine transformations
– Mikolajczyk
- 2002
|
|
15
|
Rover visual obstacle avoidance
– Moravec
- 1981
|
|
13
|
Cloth motion capture
– Pritchard, Heidrich
- 2003
|
|
11
|
Complex cells and object recognition,” Unpublished Manuscript, preprint at http://www.ai.mit.edu/ edelman/mirror/nips97.ps.Z
– Edelman, Intrator, et al.
|