AlexandreAlahi

Contents

Home
Research Projects
Publications
Teaching
Data set
Source Code
CV
Media Coverage


Research fields

Computer Vision
Signal Processing
Machine learning
Robotics
Computational Neuroscience


Research Interests

Sparse approximation
Compressed-sensing
Inverse problems
Real-time vision
Bio-inspired vision
Large-scale vision
Big Visual data

 

FREAK: Fast Retina Keypoint
(CVPR 2012 Open Source Award Winner)

- What is the problem?

A large number of vision applications rely on matching keypoints across images. The last decade featured an arms-race towards faster and more robust keypoints and association algorithms: SIFT, SURF, and more recently BRISK to name a few. These days, the deployment of vision algorithms on smart phones and embedded devices with low memory and computation complexity has even upped the ante: we need to make descriptors faster to compute, more compact while remaining robust to scale, rotation and noise.

- What is our solution?

We propose a novel keypoint descriptor inspired by the human visual system and more precisely the retina, coined Fast Retina Keypoint (FREAK). A cascade of binary strings is computed by efficiently comparing image intensities over a retinal sampling pattern.

- Why is our solution proposed?

Our experiments show that FREAKs are in general faster to compute with lower memory load and also more robust than SIFT, SURF or BRISK. They are thus competitive alternatives to existing keypoints in particular for embedded applications.

Software:

Download: FREAK C/C++ source
License: BSD
Dependency: OpenCV
Related publication: A. Alahi, R. Ortiz, and P. Vandergheynst. FREAK: Fast Retina Keypoint. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012 Open Source Award Winner.Details | Full Text ]

Note: There is also a SIMD optimized (SSE2, SSE3...) implemention if your CPU supports it.

Some examples:

    FREAKY OBJECT DETECTION

    FREAKY PEDESTRIAN MATCHING

 
   
 
top

© alahi {at} stanford.edu
updated: January 2015

Follow me on

Alahi on ScholarAlahi on LinkedinAlahi on Twitter

 

Schools Studied


Stanford


Ecole Polytechnique Fédérale de Lausanne


Labs Worked

Vision lab at Stanford

LTS2

Transpor


Companies Worked

VisioSafe