
Interest Operators Find “interesting” pieces of the image

tarix  17.11.2018  ölçüsü  2,52 Mb.   #80063 

Find “interesting” pieces of the image  e.g. corners, salient regions
 Focus attention of algorithms
 Speed up computation
Many possible uses in matching/recognition  Search
 Object recognition
 Image alignment & stitching
 Stereo
 Tracking
 …
Interest points
Local invariant photometric descriptors
History  Matching 1. Matching based on correlation alone e.g. line segments Not very discriminating (why?) Solution : matching with interest points & correlation [ A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry, Z. Zhang, R. Deriche, O. Faugeras and Q. Luong, Artificial Intelligence 1995 ]
Approach Extraction of interest points with the Harris detector Comparison of points with crosscorrelation Verification with the fundamental matrix
Harris detector
Harris detector
Harris detector
Crosscorrelation matching
Global constraints
Summary of the approach Very good results in the presence of occlusion and clutter  local information
 discriminant greyvalue information
 robust estimation of the global relation between images
 works well for limited view point changes
Solution for more general view point changes  wide baseline matching (different viewpoint, scale and rotation)
 local invariant descriptors based on greyvalue information
Schmid & Mohr 1997, Lowe 1999, Baumberg 2000, Tuytelaars & Van Gool 2000, Mikolajczyk & Schmid 2001, Brown & Lowe 2002, Matas et. al. 2002, Schaffalitzky & Zisserman 2002
Approach 1) Extraction of interest points (characteristic locations) 2) Computation of local descriptors (rotational invariants) 3) Determining correspondences 4) Selection of similar images
Harris detector
Autocorrelation
Background: Moravec Corner Detector
Shortcomings of Moravec Operator Only tries 4 shifts. We’d like to consider “all” shifts. Uses a discrete rectangular window. We’d like to use a smooth circular (or later elliptical) window. Uses a simple min function. We’d like to characterize variation with respect to direction.
Harris detector
Harris detector
Harris detector
Harris detection Autocorrelation matrix  captures the structure of the local neighborhood
 measure based on eigenvalues of M
 2 strong eigenvalues => interest point
 1 strong eigenvalue => contour
 0 eigenvalue => uniform region
Interest point detection
Some Details from the Harris Paper Corner strength R = Det(M) – k Tr(M)2 Let and be the two eigenvalues Tr(M) = + Det(M) = R is positive for corners,  for edges, and small for flat regions Select corner pixels that are 8way local maxima
Determining correspondences
Distance Measures We can use the sumsquare difference of the values of the pixels in a square neighborhood about the points being compared.
Some Matching Results
Summary of the approach Basic feature matching = Harris Corners & Correlation Very good results in the presence of occlusion and clutter  local information
 discriminant greyvalue information
 invariance to image rotation and illumination
Not invariance to scale and affine changes Solution for more general view point changes
Rotation/Scale Invariance
Rotation/Scale Invariance
Rotation/Scale Invariance
Rotation/Scale Invariance
Rotation/Scale Invariance
Rotation/Scale Invariance
Rotation/Scale Invariance
Rotation/Scale Invariance
Rotation/Scale Invariance
Invariant Features Local image descriptors that are invariant (unchanged) under image transformations
Canonical Frames
Canonical Frames
MultiScale Oriented Patches
MultiScale Oriented Patches Sample scaled, oriented patch
MultiScale Oriented Patches Sample scaled, oriented patch  8x8 patch, sampled at 5 x scale
MultiScale Oriented Patches Sample scaled, oriented patch  8x8 patch, sampled at 5 x scale
Bias/gain normalised
Matching Interest Points: Summary Harris corners / correlation  Extract and match repeatable image features
 Robust to clutter and occlusion
 BUT not invariant to scale and rotation
MultiScale Oriented Patches  Corners detected at multiple scales
 Descriptors oriented using local gradient
 Also, sample a blurred image patch
 Invariant to scale and rotation
Dostları ilə paylaş: 

