Book ChapterDOI
CenSurE: Center Surround Extremas for Realtime Feature Detection and Matching
Motilal Agrawal,Kurt Konolige,Morten Rufus Blas +2 more
- pp 102-115
Reads0
Chats0
TLDR
A suite of scale-invariant center-surround detectors (CenSurE) that outperform the other detectors, yet have better computational characteristics than other scale-space detectors, and are capable of real-time implementation are introduced.Abstract:
We explore the suitability of different feature detectors for the task of image registration, and in particular for visual odometry, using two criteria: stability (persistence across viewpoint change) and accuracy (consistent localization across viewpoint change). In addition to the now-standard SIFT, SURF, FAST, and Harris detectors, we introduce a suite of scale-invariant center-surround detectors (CenSurE) that outperform the other detectors, yet have better computational characteristics than other scale-space detectors, and are capable of real-time implementation.read more
Citations
More filters
Proceedings ArticleDOI
Stockwell transform based face recognition: A robust and an accurate approach
B. H. Shekar,D. S. Rajesh +1 more
TL;DR: This work has designed a local and a global descriptor based on the Stockwell transform, which possesses a better time frequency resolution than the Gabor transform (the short term Fourier transform with a Gaussian window) time frequency distribution.
Journal ArticleDOI
An extension to the brightness clustering transform and locally contrasting keypoints
Jaime Lomeli-R.,Mark S. Nixon +1 more
TL;DR: An extension of the Brightness Clustering Transform that detects larger structures maintaining timing and repeatability is presented, called the BCT-S, which is amongst the fastest affine-covariant feature detectors.
Dissertation
Exploring visual content in social networks
TL;DR: This project was to develop and implement strategies to extract meaningful clusters from images shared in social media websites, more specifically on Twitter, using only features extracted from the images’ content and not any associated tag or text, and indicates that the Bag-of-Features model works well for simple object and scene datasets.
Proceedings ArticleDOI
Local binary feature based on census transform for mobile robot
TL;DR: A very simple descriptor for local image feature that is detected by DOB (Difference of Boxes) proposed in CenSurE has strength for some image changes, furthermore it has a high robustness for illumination change.
References
More filters
Journal ArticleDOI
Distinctive Image Features from Scale-Invariant Keypoints
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Journal ArticleDOI
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography
TL;DR: New results are derived on the minimum number of landmarks needed to obtain a solution, and algorithms are presented for computing these minimum-landmark solutions in closed form that provide the basis for an automatic system that can solve the Location Determination Problem under difficult viewing.
Proceedings ArticleDOI
A Combined Corner and Edge Detector
Chris Harris,Mike Stephens +1 more
TL;DR: The problem the authors are addressing in Alvey Project MMI149 is that of using computer vision to understand the unconstrained 3D world, in which the viewed scenes will in general contain too wide a diversity of objects for topdown recognition techniques to work.
Book ChapterDOI
SURF: speeded up robust features
TL;DR: A novel scale- and rotation-invariant interest point detector and descriptor, coined SURF (Speeded Up Robust Features), which approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster.
Proceedings ArticleDOI
Robust real-time face detection
Paul A. Viola,Michael Jones +1 more
TL;DR: A new image representation called the “Integral Image” is introduced which allows the features used by the detector to be computed very quickly and a method for combining classifiers in a “cascade” which allows background regions of the image to be quickly discarded while spending more computation on promising face-like regions.