COMPARISON OF IMAGE FEATURE DETECTORS AND EVALUATION OF THEIR STATISTICAL CHARACTERISTICS

2021 ◽  
Keyword(s):  
Image Feature ◽  
Statistical Characteristics ◽  
Feature Detectors

Equi-affine differential invariants for invariant feature point detection

2019 ◽  
Vol 31 (2) ◽  
pp. 277-296
Author(s):  
STANLEY L. TUZNIK ◽  
PETER J. OLVER ◽  
ALLEN TANNENBAUM
Keyword(s):  
Feature Point ◽  
Image Feature ◽  
Differential Invariants ◽  
Feature Points ◽  
Affine Invariant ◽  
Moving Frames ◽  
Feature Detectors ◽  
Point Detection ◽  
Point Detector ◽  
Method Of Moving Frames

Image feature points are detected as pixels which locally maximise a detector function, two commonly used examples of which are the (Euclidean) image gradient and the Harris–Stephens corner detector. A major limitation of these feature detectors is that they are only Euclidean-invariant. In this work, we demonstrate the application of a 2D equi-affine-invariant image feature point detector based on differential invariants as derived through the equivariant method of moving frames. The fundamental equi-affine differential invariants for 3D image volumes are also computed.

scholarly journals Performance comparison of image feature detectors utilizing a large number of scenes

2016 ◽  
Vol 25 (1) ◽  
pp. 010501 ◽  
Author(s):  
Bruno Ferrarini ◽  
Shoaib Ehsan ◽  
Naveed Ur Rehman ◽  
Klaus D. McDonald-Maier
Keyword(s):  
Performance Comparison ◽  
Image Feature ◽  
Feature Detectors

scholarly journals IMPACT ASSESSMENT OF IMAGE FEATURE EXTRACTORS ON THE PERFORMANCE OF SLAM SYSTEMS

2015 ◽  
Vol 2 (2) ◽  
pp. 45-50 ◽  
Author(s):  
Taihú Pire ◽  
Thomas Fischer ◽  
Jan Faigl
Keyword(s):  
Ground Truth ◽  
Mapping Method ◽  
Image Feature ◽  
Feature Descriptor ◽  
Visual Slam ◽  
Feature Detector ◽  
Trade Off ◽  
Feature Detectors ◽  
Localization Precision ◽  
Ground Truth Information

This work evaluates an impact of image feature extractors on the performance of a visual SLAM method in terms of pose accuracy and computational requirements. In particular, the S-PTAM (Stereo Parallel Tracking and Mapping) method is considered as the visual SLAM framework for which both the feature detector and feature descriptor are parametrized. The evaluation was performed with a standard dataset with ground-truth information and six feature detectors and four descriptors. The presented results indicate that the combination of the GFTT detector and the BRIEF descriptor provides the best trade-off between the localization precision and computational requirements among the evaluated combinations of the detectors and descriptors.

scholarly journals Performance Characterization of Image Feature Detectors in Relation to the Scene Content Utilizing a Large Image Database

IEEE Access ◽  
2018 ◽  
Vol 6 ◽  
pp. 8564-8573 ◽  
Author(s):  
Bruno Ferrarini ◽  
Shoaib Ehsan ◽  
Ales Leonardis ◽  
Naveed Ur Rehman ◽  
Klaus D. McDonald-Maier
Keyword(s):  
Image Database ◽  
Image Feature ◽  
Performance Characterization ◽  
Feature Detectors ◽  
Scene Content
Sign in / Sign up

Export Citation Format

Share Document