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
Dissertation
Multi-sources fusion based vehicle localization in urban environments under a loosely coupled probabilistic framework
TL;DR: La information GPS est indisponible pendant une longue periode, the trajectoire estimee par uniquement les approches relatives tend `a diverger, en raison de l’accumulation of the position du vehicule en tout temps.
Dissertation
Vision based detection and tracking in dynamic environments with minimal supervision
TL;DR: A framework for associating detections across frames is presented that exploits spatial and temporal constraints, enabling life-long improvement through self-supervised learning.
Journal ArticleDOI
Learning second-order statistics for place recognition based on robust covariance estimation of CNN features
TL;DR: High-order statistics are introduced into place recognition by developing a novel adaptively normalized covariance pooling method for learning place representations in an end-to-end manner that provides robust covariance matrix estimation of high-dimensional and small-size deep features by adaptive covariance normalization (AdaCN).
Proceedings ArticleDOI
GPU-Based Computation of the Integral Image
TL;DR: In this paper, an intuitive parallel method based on the binary tree is introduced to compute the integral image in the regular region of the grey-level image, which can be used to quickly complete common pixel-level operations.
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.