Abstract
We propose a novel and fast multiscale feature detection and description approach that exploits the benefits of nonlinear scale spaces. Previous attempts to detect and describe features in nonlinear scale spaces such as KAZE [1] and BFSIFT [6] are highly time consuming due to the computational burden of creating the nonlinear scale space. In this paper we propose to use recent numerical schemes called Fast Explicit Diffusion (FED) [3, 4] embedded in a pyramidal framework to dramatically speed-up feature detection in nonlinear scale spaces. In addition, we introduce a Modified-Local Difference Binary (M-LDB) descriptor that is highly efficient, exploits gradient information from the nonlinear scale space, is scale and rotation invariant and has low storage requirements. Our features are called Accelerated-KAZE (A-KAZE) due to the dramatic speed-up introduced by FED schemes embedded in a pyramidal framework.
Keywords
Nonlinear systemScale spaceExploitComputer scienceScale (ratio)DiffusionInvariant (physics)AlgorithmBinary numberFeature (linguistics)Artificial intelligenceTheoretical computer scienceMathematicsImage processingImage (mathematics)Physics
Affiliated Institutions
Related Publications
Natural Feature Detection on Mobile Phones with 3D FAST
In this paper, we present a novel feature detection approach designed for mobile devices, showing optimized solutions for both detection and description. It is based on FAST (Fe...
ORB: An efficient alternative to SIFT or SURF
Feature matching is at the base of many computer vision problems, such as object recognition or structure from motion. Current methods rely on costly descriptors for detection a...
Image Transformation Based on Learning Dictionaries across Image Spaces
In this paper, we propose a framework of transforming images from a source image space to a target image space, based on learning coupled dictionaries from a training set of pai...
Multi-Image Matching Using Multi-Scale Oriented Patches
This paper describes a novel multi-view matching framework based on a new type of invariant feature. Our features are located at Harris corners in discrete scale-space and orien...
Modeling scenes with local descriptors and latent aspects
We present a new approach to model visual scenes in image collections, based on local invariant features and probabilistic latent space models. Our formulation provides answers ...
Publication Info
- Year
- 2013
- Type
- article
- Pages
- 13.1-13.11
- Citations
- 1129
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
1129
OpenAlex
179
Influential
616
CrossRef
Cite This
Pablo F. Alcantarilla,
J. Nuevo,
Adrien Bartoli
(2013).
Fast Explicit Diffusion for Accelerated Features in Nonlinear Scale Spaces.
Procedings of the British Machine Vision Conference 2013
, 13.1-13.11.
https://doi.org/10.5244/c.27.13
Identifiers
- DOI
- 10.5244/c.27.13