Slides (PPT)

Report
BRIEF: Binary Robust Independent
Elementary Features
Michael Calonder, Vincent Lepetit, Christoph
Strecha, and Pascal Fua
CVLab, EPFL, Lausanne, Switzerland
Contributions
• Pros:
• Compact, easy-computed, highly discriminative
• Fast matching using Hamming distance
• Good recognition performance
• Cons:
• More sensitive to image distortions and
transformations, in particular to in-plane rotation
and scale change
Related work
• Descriptors: SIFT, SURF, DAISY, etc
• Descriptor + Dimension Reduction (e.g.
PCA, LDA, etc)
• Quantization
• Hashing (e.g. Locality Sensitive Hashing)
Method
• Binary test
• BRIEF descriptor
• For each S*S patch
1. Smooth it
2. Pick pixels using pre-defined binary tests
Smoothing kernels
• De-noising
• Gaussian kernels
Spatial arrangement of the
binary tests
1. (X,Y)~i.i.d. Uniform
2. (X,Y)~i.i.d. Gaussian
3. X~i.i.d. Gaussian
, Y~i.i.d. Gaussian
4. Randomly sampled from discrete locations
of a coarse polar grid introducing a spatial
quantization.
5.
and takes all possible values
on a coarse polar grid containing points
Distance Distributions
Experiments
BRISK: Binary Robust Invariant
Scalable Keypoints
Stefan Leutenegger, Margarita Chli and
Roland Y. Siegwart
Autonomous Systems Lab, ETH Zurich
Contributions
• Combination of SIFT-like scale-space
keypoint detection and BREIF-like descriptor
• Scale and rotation invariant
Method
• Scale-space
keypoint
detection
• Sampling
pattern
• Local gradient
• All sampling-point pairs
• Short-distance pairings S and long-distance
pairings L
• Overall characteristic pattern direction
• Descriptor
• Rotation- and scale-normalization
• BRIEF-like
• Matching: Hamming distance
Experiments

similar documents