Results 1  10
of
303
Distinctive Image Features from ScaleInvariant Keypoints
, 2003
"... This paper presents a method for extracting distinctive invariant features from images, which can be used to perform reliable matching between different images of an object or scene. The features are invariant to image scale and rotation, and are shown to provide robust matching across a a substa ..."
Abstract

Cited by 5169 (20 self)
 Add to MetaCart
This paper presents a method for extracting distinctive invariant features from images, which can be used to perform reliable matching between different images of an object or scene. The features are invariant to image scale and rotation, and are shown to provide robust matching across a a substantial range of affine distortion, addition of noise, change in 3D viewpoint, and change in illumination. The features are highly distinctive, in the sense that a single feature can be correctly matched with high probability against a large database of features from many images. This paper also describes an approach to using these features for object recognition. The recognition proceeds by matching individual features to a database of features from known objects using a fast nearestneighbor algorithm, followed by a Hough transform to identify clusters belonging to a single object, and finally performing verification through leastsquares solution for consistent pose parameters. This approach to recognition can robustly identify objects among clutter and occlusion while achieving near realtime performance.
Scalebased description and recognition of planar curves and twodimensional shapes
, 1986
"... The problem of finding a description, at varying levels of detail, for planar curves and matching two such descriptions is posed and solved in this paper. A number of necessary criteria are imposed on any candidate solution method. Pathbased Gaussian smoothing techniques are applied to the curve to ..."
Abstract

Cited by 167 (1 self)
 Add to MetaCart
The problem of finding a description, at varying levels of detail, for planar curves and matching two such descriptions is posed and solved in this paper. A number of necessary criteria are imposed on any candidate solution method. Pathbased Gaussian smoothing techniques are applied to the curve to find zeros of curvature at varying levels of detail. The result is the "generalized scale space " image of a planar curve which is invariant under rotation, uniform scaling and translation of the curve. These properties make the scale space image suitable for matching. The matching algorithm is a modification of the uniform cost algorithm and finds the lowest cost match of contours in the scale space images. It is argued that this is preferable to matching in a socalled stable scale of the curve because no such scale may exist for a given curve. This technique is applied to register a Landsat satellite image of the Strait of Georgia, B.C. (manually corrected for skew) to a map containing the shorelines of an overlapping area.
Multidimensional indexing for recognizing visual shapes
 PAMI
, 1994
"... AbstractThis paper introduces an analytical framework for studying some properties of model acquisition and recognition techniques based on indexing. The goal is to demonstrate that several problems previously associated with the approach can be attributed to the low dimensionality of invariants us ..."
Abstract

Cited by 78 (0 self)
 Add to MetaCart
AbstractThis paper introduces an analytical framework for studying some properties of model acquisition and recognition techniques based on indexing. The goal is to demonstrate that several problems previously associated with the approach can be attributed to the low dimensionality of invariants used. These include limited index selectivity, excessive accumulation of votes in the lookup table buckets, and excessive sensitivity to quantization parameters. Theoretical results demonstrate that using highdimensional, highly descriptive global invariants produces better results in terms of accuracy, false positive suppression, and computation time. A practical example of highdimensional global invariants is introduced and used to implement a 2D shape acquisitionhecognition system. The acquisitiodrecognition system is based on a twostep table lookup mechanism. First, local curve descriptors are obtained by correlating image contour information at short range. Then, sevendimensional global invariants are computed by correlating triplets of local curve descriptors at longer range. This experimental system is meant to illustrate the behavior of a highdimensional indexing scheme. Indeed, its performance shows good agreement with the analytical model with respect to database size, fault tolerance, and recognition speed. Model acquisition time is linear to cubic in the number of object features. Object recognition time is constant to linear in the number of models in the database and linear to cubic in the number of features in the image. The system has been tested extensively, with more than 250 arbitrary shapes in the database. Unsupervised shape and subpart acquisition is demonstrated. I.
Global Localization using Distinctive Visual Features
, 2002
"... We have previously developed a mobile robot system which uses scale invariant visual landmarks to localize and simultaneously build a 3D map of the environment In this paper, we look at global localization, also known as the kidnapped robot problem, where the robot localizes itself globally, without ..."
Abstract

Cited by 61 (1 self)
 Add to MetaCart
We have previously developed a mobile robot system which uses scale invariant visual landmarks to localize and simultaneously build a 3D map of the environment In this paper, we look at global localization, also known as the kidnapped robot problem, where the robot localizes itself globally, without any prior location estimate. This is achieved by matching distinctive landmarks in the current frame to a database map. A Hough Transform approach and a RANSAC approach for global localization are compared, showing that RANSAC is much more cjficicnt. Moreover, robust global localization can be achieved by matching a small submap of the local region built from multiple frames.
Statistical Approaches to FeatureBased Object Recognition
, 1997
"... . This paper examines statistical approaches to modelbased object recognition. Evidence is presented indicating that, in some domains, normal (Gaussian) distributions are more accurate than uniform distributions for modeling feature fluctuations. This motivates the development of new maximumlikeli ..."
Abstract

Cited by 61 (1 self)
 Add to MetaCart
. This paper examines statistical approaches to modelbased object recognition. Evidence is presented indicating that, in some domains, normal (Gaussian) distributions are more accurate than uniform distributions for modeling feature fluctuations. This motivates the development of new maximumlikelihood and MAP recognition formulations which are based on normal feature models. These formulations lead to an expression for the posterior probability of the pose and correspondences given an image. Several avenues are explored for specifying a recognition hypothesis. In the first approach, correspondences are included as a part of the hypotheses. Search for solutions may be ordered as a combinatorial search in correspondence space, or as a search over pose space, where the same criterion can equivalently be viewed as a robust variant of chamfer matching. In the second approach, correspondences are not viewed as being a part of the hypotheses. This leads to a criterion that is a smooth funct...
A Tensor Framework for Multidimensional Signal Processing
 Linkoping University, Sweden
, 1994
"... ii About the cover The figure on the cover shows a visualization of a symmetric tensor in three dimensions, G = λ1ê1ê T 1 + λ2ê2ê T 2 + λ3ê3ê T 3 The object in the figure is the sum of a spear, a plate and a sphere. The spear describes the principal direction of the tensor λ1ê1ê T 1, where the lengt ..."
Abstract

Cited by 56 (8 self)
 Add to MetaCart
ii About the cover The figure on the cover shows a visualization of a symmetric tensor in three dimensions, G = λ1ê1ê T 1 + λ2ê2ê T 2 + λ3ê3ê T 3 The object in the figure is the sum of a spear, a plate and a sphere. The spear describes the principal direction of the tensor λ1ê1ê T 1, where the length is proportional to the largest eigenvalue, λ1. The plate describes the plane spanned by the eigenvectors corresponding to the two largest eigenvalues, λ2(ê1ê T 1 + ê2ê T 2). The sphere, with a radius proportional to the smallest eigenvalue, shows how isotropic the tensor is, λ3(ê1ê T 1 + ê2ê T 2 + ê3ê T 3). The visualization is done using AVS [WWW94]. I am very grateful to Johan Wiklund for implementing the tensor viewer module used. This thesis deals with filtering of multidimensional signals. A large part of the thesis is devoted to a novel filtering method termed “Normalized convolution”. The method performs local expansion of a signal in a chosen filter basis which
A Robust Method for Road Sign Detection and Recognition
, 1996
"... This paper describes a method for detecting and recognizing road signs in graylevel and color images acquired by a single camera mounted on a moving vehicle. The method works in three stages. First, the search for the road sign is reduced to a suitable region of the image by using some a priori kno ..."
Abstract

Cited by 54 (0 self)
 Add to MetaCart
This paper describes a method for detecting and recognizing road signs in graylevel and color images acquired by a single camera mounted on a moving vehicle. The method works in three stages. First, the search for the road sign is reduced to a suitable region of the image by using some a priori knowledge on the scene or color clues (when available) . Secondly, a geometrical analysis of the edges extracted from the image is carried out, which generates candidates to be circular and triangular signs. Thirdly, a recognition stage tests by crosscorrelation techniques each candidate which, if validated, is classified according to the database of signs. An extensive experimentation has shown that the method is robust against lowlevel noise corrupting edge detection and contour following, and works for images of cluttered urban streets as well as country roads and highways. A further improvement on the detection and recognition scheme has been obtained by means of temporal integration b...
The Combinatorics of Object Recognition in Cluttered Environments using Constrained Search
, 1988
"... The problem of recognizing rigid objects from noisy sensory data has been successfully attacked in previous work by using a constrained search approach. Empirical investigations have shown the method to be very effective when recognizing and localizing isolated objects, but less effective when deali ..."
Abstract

Cited by 53 (2 self)
 Add to MetaCart
The problem of recognizing rigid objects from noisy sensory data has been successfully attacked in previous work by using a constrained search approach. Empirical investigations have shown the method to be very effective when recognizing and localizing isolated objects, but less effective when dealing with occluded objects where much of the sensory data arises from objects other than the one of interest. When clustering techniques such as the Hough transform are used to isolate likely subspaces of the search space, empiricial performance in cluttered scenes improves considerably. In this note, we establish formal bounds on the combinatories of this approach. Under some simple assumptions, we show that the expected complexity of recognizing isolated objects is quadratic in the number of model and sensory fragments, but that the expected complexity of recognizing objects in cluttered environments is exponential in the size of the correct interpretation. We also provide formal bounds on the efficacy of using the Hough transform to preselect likely subspaces, showing that problem remains exponential, but that in practical terms, the size of the problem is significantly decreased.