In the Saddle: Chasing Fast and Repeatable Features

08/24/2016
by   Javier Aldana-Iuit, et al.
0

A novel similarity-covariant feature detector that extracts points whose neighbourhoods, when treated as a 3D intensity surface, have a saddle-like intensity profile. The saddle condition is verified efficiently by intensity comparisons on two concentric rings that must have exactly two dark-to-bright and two bright-to-dark transitions satisfying certain geometric constraints. Experiments show that the Saddle features are general, evenly spread and appearing in high density in a range of images. The Saddle detector is among the fastest proposed. In comparison with detector with similar speed, the Saddle features show superior matching performance on number of challenging datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 6

research
03/14/2016

RISAS: A Novel Rotation, Illumination, Scale Invariant Appearance and Shape Feature

This paper presents a novel appearance and shape feature, RISAS, which i...
research
09/15/2019

Performance Evaluation of Learned 3D Features

Matching surfaces is a challenging 3D Computer Vision problem typically ...
research
11/17/2021

Nonlinear Intensity Sonar Image Matching based on Deep Convolution Features

In the field of deep-sea exploration, sonar is presently the only effici...
research
05/30/2019

Retrieving fields from proton radiography without source profiles

Proton radiography is a technique in high energy density science to diag...
research
08/17/2011

Hamiltonian Streamline Guided Feature Extraction with Applications to Face Detection

We propose a new feature extraction method based on two dynamical system...
research
08/30/2018

Bayesian Outdoor Defect Detection

We introduce a Bayesian defect detector to facilitate the defect detecti...

Please sign up or login with your details

Forgot password? Click here to reset