Presentation is loading. Please wait.

Presentation is loading. Please wait.

BRIEF: Binary Robust Independent Elementary Features

Similar presentations


Presentation on theme: "BRIEF: Binary Robust Independent Elementary Features"— Presentation transcript:

1 BRIEF: Binary Robust Independent Elementary Features
Michael Calonder, Vincent Lepetit, Christoph Strecha, and Pascal Fua CVLab, EPFL, Lausanne, Switzerland

2 Contributions Pros: Cons:
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

3 Related work Descriptors: SIFT, SURF, DAISY, etc
Descriptor + Dimension Reduction (e.g. PCA, LDA, etc) Quantization Hashing (e.g. Locality Sensitive Hashing)

4 Method Binary test BRIEF descriptor For each S*S patch Smooth it
Pick pixels using pre-defined binary tests

5 Smoothing kernels De-noising Gaussian kernels

6 Spatial arrangement of the binary tests
(X,Y)~i.i.d. Uniform (X,Y)~i.i.d. Gaussian X~i.i.d. Gaussian , Y~i.i.d. Gaussian Randomly sampled from discrete locations of a coarse polar grid introducing a spatial quantization. and takes all possible values on a coarse polar grid containing points

7

8

9 Distance Distributions

10 Experiments

11 BRISK: Binary Robust Invariant Scalable Keypoints
Stefan Leutenegger, Margarita Chli and Roland Y. Siegwart Autonomous Systems Lab, ETH Zurich

12 Contributions Combination of SIFT-like scale-space keypoint detection and BREIF-like descriptor Scale and rotation invariant

13 Method Scale-space keypoint detection

14 Sampling pattern

15 Local gradient All sampling-point pairs Short-distance pairings S and long-distance pairings L

16 Overall characteristic pattern direction
Descriptor Rotation- and scale-normalization BRIEF-like Matching: Hamming distance

17 Experiments

18

19


Download ppt "BRIEF: Binary Robust Independent Elementary Features"

Similar presentations


Ads by Google