Download presentation
Presentation is loading. Please wait.
Published byMervin Tyler Modified over 9 years ago
1
776 Computer Vision Jan-Michael Frahm, Enrique Dunn Spring 2013
2
SIFT-detector Problem: want to detect features at different scales (sizes) and with different orientations!
3
SIFT-detector Scale and image-plane-rotation invariant feature descriptor [Lowe 2004] - Image content is transformed into local feature coordinates that are invariant to translation, rotation, scale, and other imaging parameters
4
SIFT-detector Scale = 2.5 Rotation = 45 0 Empirically found to perform very good [Mikolajczyk 2003]
5
Difference of Gaussian for Scale invariance Difference-of-Gaussian with constant ratio of scales is a close approximation to Lindeberg’s scale-normalized Laplacian [Lindeberg 1998] Gaussian Difference of Gaussian
6
Difference of Gaussian for Scale invariance Difference-of-Gaussian with constant ratio of scales is a close approximation to Lindeberg’s scale-normalized Laplacian [Lindeberg 1998]
7
Key point localization Detect maxima and minima of difference-of-Gaussian in scale space Fit a quadratic to surrounding values for sub-pixel and sub- scale interpolation (Brown & Lowe, 2002) Taylor expansion around point: Offset of extremum (use finite differences for derivatives):
8
Orientation normalization Histogram of local gradient directions computed at selected scale Assign principal orientation at peak of smoothed histogram Each key specifies stable 2D coordinates (x, y, scale, orientation)
9
Example of keypoint detection Threshold on value at DOG peak and on ratio of principle curvatures (Harris approach) (a) 233x189 image (b) 832 DOG extrema (c) 729 left after peak value threshold (d) 536 left after testing ratio of principle curvatures courtesy Lowe XX
10
SIFT vector formation SIFT vector formation Thresholded image gradients are sampled over 16x16 array of locations in scale space Create array of orientation histograms 8 orientations x 4x4 histogram array = 128 dimensions © Lowe example 2x2 histogram array
11
Sift feature detector
12
Goal 12 Image Patch [0, 0, 1, 0, 1, 1, 0, 1, …] Binary Descriptor slide: J. Heinly
13
BRIEF Binary Robust Independent Elementary Features Calonder et al. ECCV 2010 slide: J. Heinly
14
Feature Description 14 slide: J. Heinly
15
BRIEF: Method 15 Descriptor: 011 0 10… slide: J. Heinly
16
BRIEF: Sampling 16 Endpoints from 2D Gaussian slide: J. Heinly
17
BRIEF: Descriptor 17 slide: J. Heinly
18
BRIEF: Descriptor 128, 256, or 512 bits o 16, 32, or 64 bytes Hamming distance matching 18 slide: J. Heinly
19
BRIEF: Summary Pros o Highly efficient Cons o No scale invariance o No rotation invariance o Sensitive to noise 19 slide: J. Heinly
20
ORB An Efficient Alternative to SIFT or SURF Rublee et at. ICCV 2011 slide: J. Heinly
21
Limitations of BRIEF No rotation invariance 21 slide: J. Heinly
22
ORB: Method 22 Feature Directio n Descriptor: 011 0 10… slide: J. Heinly
23
ORB: Gradient Alignment 23 Gradient Direction slide: J. Heinly
24
ORB: Rotation Invariance 24 Intensity Centroid Feature Direction slide: J. Heinly
25
ORB: Descriptor 25 Low Endpoint Correlation High Candidate ArrangementLearned Arrangement slide: J. Heinly
26
ORB: Summary Pros o Efficient o Rotation invariance Cons o No scale invariance o Sensitive to noise 26 slide: J. Heinly
27
BRISK Binary Robust Invariant Scalable Keypoints Leutenegger et al. ICCV 2011 slide: J. Heinly
28
Limitations of BRIEF No rotation invariance No scale invariance Sensitive to noise 28 slide: J. Heinly
29
BRISK: Method 29 Descriptor: 011 0 10… slide: J. Heinly
30
BRISK: Rotation Invariance 30 Long-distance comparisons Gradient direction slide: J. Heinly
31
BRISK: Scale Invariance 31 Find maximum response slide: J. Heinly
32
BRISK: Descriptor 32 Centers: BLUE Gaussian: RED 2D Gaussian around each feature Robust to noise slide: J. Heinly
33
BRISK: Descriptor 33 Centers: BLUE Gaussian: RED 512 Comparisons 64 bytes Avoid short- distance comparisons slide: J. Heinly
34
BRISK: Summary Pros o Efficient o Rotation invariance o Scale invariance o Robust to noise 34 slide: J. Heinly
35
Summary 35 BRIEF BRISK ORB Efficient Rotation Efficient Rotation Scale Noise slide: J. Heinly
36
Results: BRIEF 36 Increased Difficulty No Rotation Dimensionali ty Reduction Recognition Rate % slide: J. Heinly
37
Results: BRIEF 37 Increased Difficulty Recognition Rate % slide: J. Heinly
38
Results: ORB 38 Percentage of Inliers Angle of Rotation ORB slide: J. Heinly
39
Results: BRISK 39 slide: J. Heinly
40
Results: BRISK 40 slide: J. Heinly
41
Results Many more tests… 41 Key Observation: Results are comparable to traditional feature descriptors. slide: J. Heinly
42
Efficiency 42 SURFSIFTBRIEFORBBRISK 1.019.00.0270.0700.087 37.214.211.5 Normalized Time Speedup slide: J. Heinly
43
Summary 43 BRIEF BRISK ORB Efficient Binary Descriptors slide: J. Heinly
44
Future Work Improved robustness o Rotation o Scale o Noise Coupling with detector 44 slide: J. Heinly
45
BRIEFBRISKORB slide: J. Heinly
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.