Results 1 - 10
of
215
BRIEF: Binary robust independent elementary features
, 2010
"... We propose to use binary strings as an efficient feature point descriptor, which we call BRIEF. We show that it is highly discriminative even when using relatively few bits and can be computed using simple intensity difference tests. Furthermore, the descriptor similarity can be evaluated using the ..."
Abstract
-
Cited by 208 (5 self)
- Add to MetaCart
(Show Context)
We propose to use binary strings as an efficient feature point descriptor, which we call BRIEF. We show that it is highly discriminative even when using relatively few bits and can be computed using simple intensity difference tests. Furthermore, the descriptor similarity can be evaluated using the Hamming distance, which is very efficient to compute, instead of the L2 norm as is usually done. As a result, BRIEF is very fast both to build and to match. We compare it against SURF and U-SURF on standard benchmarks and show that it yields a similar or better recognition performance, while running in a fraction of the time required by either.
Learning Local Image Descriptors
- Proc. IEEE Conf. Computer Vision and Pattern Recognition
, 2007
"... Abstract—In this paper, we explore methods for learning local image descriptors from training data. We describe a set of building blocks for constructing descriptors which can be combined together and jointly optimized so as to minimize the error of a nearest-neighbor classifier. We consider both li ..."
Abstract
-
Cited by 174 (2 self)
- Add to MetaCart
(Show Context)
Abstract—In this paper, we explore methods for learning local image descriptors from training data. We describe a set of building blocks for constructing descriptors which can be combined together and jointly optimized so as to minimize the error of a nearest-neighbor classifier. We consider both linear and nonlinear transforms with dimensionality reduction, and make use of discriminant learning techniques such as Linear Discriminant Analysis (LDA) and Powell minimization to solve for the parameters. Using these techniques, we obtain descriptors that exceed state-of-the-art performance with low dimensionality. In addition to new experiments and recommendations for descriptor learning, we are also making available a new and realistic ground truth data set based on multiview stereo data. Index Terms—Image descriptors, local features, discriminative learning, SIFT. Ç 1
Robust Object Tracking with Online Multiple Instance Learning
, 2011
"... In this paper, we address the problem of tracking an object in a video given its location in the first frame and no other information. Recently, a class of tracking techniques called “tracking by detection ” has been shown to give promising results at real-time speeds. These methods train a discrim ..."
Abstract
-
Cited by 140 (7 self)
- Add to MetaCart
In this paper, we address the problem of tracking an object in a video given its location in the first frame and no other information. Recently, a class of tracking techniques called “tracking by detection ” has been shown to give promising results at real-time speeds. These methods train a discriminative classifier in an online manner to separate the object from the background. This classifier bootstraps itself by using the current tracker state to extract positive and negative examples from the current frame. Slight inaccuracies in the tracker can therefore lead to incorrectly labeled training examples, which degrade the classifier and can cause drift. In this paper, we show that using Multiple Instance Learning (MIL) instead of traditional supervised learning avoids these problems and can therefore lead to a more robust tracker with fewer parameter tweaks. We propose a novel online MIL algorithm for object tracking that achieves superior results with real-time performance. We present thorough experimental results (both qualitative and quantitative) on a number of challenging video clips.
Fast keypoint recognition in ten lines of code
- In Proc. IEEE Conference on Computing Vision and Pattern Recognition
, 2007
"... While feature point recognition is a key component of modern approaches to object detection, existing approaches require computationally expensive patch preprocessing to handle perspective distortion. In this paper, we show that formulating the problem in a Naive Bayesian classification framework ma ..."
Abstract
-
Cited by 127 (7 self)
- Add to MetaCart
(Show Context)
While feature point recognition is a key component of modern approaches to object detection, existing approaches require computationally expensive patch preprocessing to handle perspective distortion. In this paper, we show that formulating the problem in a Naive Bayesian classification framework makes such preprocessing unnecessary and produces an algorithm that is simple, efficient, and robust. Furthermore, it scales well to handle large number of classes. To recognize the patches surrounding keypoints, our classifier uses hundreds of simple binary features and models class posterior probabilities. We make the problem computationally tractable by assuming independence between arbitrary sets of features. Even though this is not strictly true, we demonstrate that our classifier nevertheless performs remarkably well on image datasets containing very significant perspective changes. 1.
Fast Keypoint Recognition using Random Ferns. PAMI, 2009. Accepted for Publication
"... While feature point recognition is a key component of modern approaches to object detection, existing approaches require computationally expensive patch preprocessing to handle perspective distortion. In this paper, we show that formulating the problem in a Naive Bayesian classification framework ma ..."
Abstract
-
Cited by 113 (8 self)
- Add to MetaCart
(Show Context)
While feature point recognition is a key component of modern approaches to object detection, existing approaches require computationally expensive patch preprocessing to handle perspective distortion. In this paper, we show that formulating the problem in a Naive Bayesian classification framework makes such preprocessing unnecessary and produces an algorithm that is simple, efficient, and robust. Furthermore, it scales well as number of classes grows. To recognize the patches surrounding keypoints, our classifier uses hundreds of simple binary features and models class posterior probabilities. We make the problem computationally tractable by assuming independence betweenarbitrarysetsoffeatures.Eventhoughthisisnotstrictlytrue,wedemonstratethatourclassifier nevertheless performs remarkably well on image datasets containing very significant perspective changes. Index Terms Image processing and computer vision, object recognition, tracking, image registration, feature matching, naive bayesian 1 I.
R.: Optimised KD-trees for fast image descriptor matching
- In CVPR, IEEE Computer Society
, 2008
"... In this paper, we look at improving the KD-tree for a specific usage: indexing a large number of SIFT and other types of image descriptors. We have extended priority search, to priority search among multiple trees. By creating multiple KD-trees from the same data set and simultaneously searching amo ..."
Abstract
-
Cited by 94 (0 self)
- Add to MetaCart
(Show Context)
In this paper, we look at improving the KD-tree for a specific usage: indexing a large number of SIFT and other types of image descriptors. We have extended priority search, to priority search among multiple trees. By creating multiple KD-trees from the same data set and simultaneously searching among these trees, we have improved the KD-tree’s search performance significantly. We have also exploited the structure in SIFT descriptors (or structure in any data set) to reduce the time spent in backtracking. By using Principal Component Analysis to align the principal axes of the data with the coordinate axes, we have further increased the KD-tree’s search performance. 1.
Viewpoint-independent object class detection using 3d feature maps
- in In proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
, 2008
"... This paper presents a 3D approach to multi-view object class detection. Most existing approaches recognize object classes for a particular viewpoint or combine classifiers for a few discrete views. We propose instead to build 3D representations of object classes which allow to handle viewpoint chang ..."
Abstract
-
Cited by 93 (3 self)
- Add to MetaCart
(Show Context)
This paper presents a 3D approach to multi-view object class detection. Most existing approaches recognize object classes for a particular viewpoint or combine classifiers for a few discrete views. We propose instead to build 3D representations of object classes which allow to handle viewpoint changes and intra-class variability. Our approach extracts a set of pose and class discriminant features from synthetic 3D object models using a filtering procedure, evaluates their suitability for matching to real image data and represents them by their appearance and 3D position. We term these representations 3D Feature Maps. For recognizing an object class in an image we match the synthetic descriptors to the real ones in a 3D voting scheme. Geometric coherence is reinforced by means of a robust pose estimation which yields a 3D bounding box in addition to the 2D localization. The precision of the 3D pose estimation is evaluated on a set of images of a calibrated scene. The 2D localization is evaluated on the PASCAL 2006 dataset for motorbikes and cars, showing that its performance can compete with state-of-the-art 2D object detectors. 1.
I.: Real-Time SLAM Relocalisation, In:
- 11th IEEE International Conference on Computer Vision
, 2007
"... ..."
(Show Context)
