Results 1  10
of
11
Recognition Using Region Correspondences
 International Journal of Computer Vision
, 1995
"... A central problem in object recognition is to determine the transformation that relates the model to the image, given some partial correspondence between the two. This is useful in determining whether an object is present in an image, and if so, determining where the object is. We present a novel me ..."
Abstract

Cited by 38 (7 self)
 Add to MetaCart
(Show Context)
A central problem in object recognition is to determine the transformation that relates the model to the image, given some partial correspondence between the two. This is useful in determining whether an object is present in an image, and if so, determining where the object is. We present a novel method of solving this problem that uses region information. In our approach the model is divided into volumes, and the image is divided into regions. Given a match between subsets of volumes and regions (without any explicit correspondence between different pieces of the regions) the alignment transformation is computed. The method applies to planar objects under similarity, affine, and projective transformations and to projections of 3D objects undergoing affine and projective transformations. 1 Introduction A fundamental problem in recognition is pose estimation. Given a correspondence between some portions of an object model and some portions of an image, determine the transformation th...
Probabilistic Affine Invariants for Recognition
 In Proc. IEEE Comput. Soc. Conf. Comput. Vision and Pattern Recogn
, 1998
"... Under a weak perspective camera model, the image plane coordinates in different views of a planar object are related by an affine transformation. Because of this property, researchers have attempted to use affine invariants for recognition. However, there are two problems with this approach: (1) obj ..."
Abstract

Cited by 34 (5 self)
 Add to MetaCart
Under a weak perspective camera model, the image plane coordinates in different views of a planar object are related by an affine transformation. Because of this property, researchers have attempted to use affine invariants for recognition. However, there are two problems with this approach: (1) objects or object classes with inherent variability cannot be adequately treated using invariants; and (2) in practice the calculated affine invariants can be quite sensitive to errors in the image plane measurements. In this paper we use probability distributions to address both of these difficulties. Under the assumption that the feature positions of a planar object can be modeled using a jointly Gaussian density, we have derived the joint density over the corresponding set of affine coordinates. Even when the assumptions of a planar object and a weak perspective camera model do not strictly hold, the results are useful because deviations from the ideal can be treated as deformability in the ...
Efficient Pose Clustering Using a Randomized Algorithm
, 1997
"... . Pose clustering is a method to perform object recognition by determining hypothetical object poses and finding clusters of the poses in the space of legal object positions. An object that appears in an image will yield a large cluster of such poses close to the correct position of the object. If t ..."
Abstract

Cited by 31 (7 self)
 Add to MetaCart
. Pose clustering is a method to perform object recognition by determining hypothetical object poses and finding clusters of the poses in the space of legal object positions. An object that appears in an image will yield a large cluster of such poses close to the correct position of the object. If there are m model features and n image features, then there are O(m 3 n 3 ) hypothetical poses that can be determined from minimal information for the case of recognition of threedimensional objects from feature points in twodimensional images. Rather than clustering all of these poses, we show that pose clustering can have equivalent performance for this case when examining only O(mn) poses, due to correlation between the poses, if we are given two correct matches between model features and image features. Since we do not usually know two correct matches in advance, this property is used with randomization to decompose the pose clustering problem into O(n 2 ) problems, each of which...
Solution of the Simultaneous Pose and Correspondence Problem Using Gaussian Error Model
 COMPUTER VISION AND IMAGE UNDERSTANDING
, 1999
"... ..."
Probabilistic 3D Object Recognition
 In International Conf. on Computer Vision
, 1995
"... : A probabilistic 3D object recognition algorithm is presented. In order to guide the recognition process the probability that match hypotheses between image features and model features are correct is computed. A model is developed which uses the probabilistic peaking effect of measured angles and r ..."
Abstract

Cited by 18 (0 self)
 Add to MetaCart
: A probabilistic 3D object recognition algorithm is presented. In order to guide the recognition process the probability that match hypotheses between image features and model features are correct is computed. A model is developed which uses the probabilistic peaking effect of measured angles and ratios of lengths by tracing isoangle and isoratio curves on the viewing sphere. The model also accounts for various types of uncertainty in the input such as incomplete and inexact edge detection. For each match hypothesis the pose of the object and the pose uncertainty which is due to the uncertainty in vertex position are recovered. This is used to find sets of hypotheses which reinforce each other by matching features of the same object with compatible uncertainty regions. A probabilistic expression is used to rank these hypothesis sets. The hypothesis sets with the highest rank are output. The algorithm has been fully implemented, and tested on real images. 1 Introduction One of the ...
A General Method for Geometric Feature Matching and Model Extraction
 International Journal of Computer Vision
, 2001
"... Popular algorithms for feature matching and model extraction fall into two broad categories, generateandtest and Hough transform variations. However, both methods suffer from problems in practical implementations. Generateandtest methods are sensitive to noise in the data. They often fail when t ..."
Abstract

Cited by 13 (1 self)
 Add to MetaCart
Popular algorithms for feature matching and model extraction fall into two broad categories, generateandtest and Hough transform variations. However, both methods suffer from problems in practical implementations. Generateandtest methods are sensitive to noise in the data. They often fail when the generated model fit is poor due to error in the selected features. Hough transform variations are somewhat less sensitive the noise, but implementations for complex problems suffer from large time and space requirements and the detection of false positives. This paper describes a general method for solving problems where a model is extracted from or fit to data that draws benefits from both generateandtest methods and those based on the Hough transform, yielding a method superior to both. An important component of the method is the subdivision of the problem into many subproblems. This allows efficient generateandtest techniques to be used, including the use of randomization to limit the number of subproblems that must be examined. Each subproblem is solved using pose space analysis techniques similar to the Hough transform, which lowers the sensitivity of the method to noise. This strategy is easy to implement and results in practical algorithms that are efficient and robust. We apply this method to object recognition, geometric primitive extraction, robust regression, and motion segmentation. 1
Features and classification methods to locate deciduous trees
 in images,” Computer Vision and Image Understanding
, 1999
"... We compare features and classification methods to locate deciduous trees in images. From this comparison we conclude that a backpropagation neural network achieves better classification results than the other classifiers we tested. Our analysis of the relevance of 51 features from seven feature extr ..."
Abstract

Cited by 11 (0 self)
 Add to MetaCart
(Show Context)
We compare features and classification methods to locate deciduous trees in images. From this comparison we conclude that a backpropagation neural network achieves better classification results than the other classifiers we tested. Our analysis of the relevance of 51 features from seven feature extraction methods based on the graylevel cooccurrence matrix, Gabor filters, fractal dimension, steerable filters, the Fourier transform, entropy, and color shows that each feature contributes important information. We show how we obtain a 13feature subset that significantly reduces the feature extraction time while retaining most of the complete feature set’s power and robustness. The best subsets of features were found to be combinations of features of each of the extraction methods. Methods for classification and feature relevance determination that are based on the covariance or correlation matrix of the features (such as eigenanalyses or linear or quadratic classifiers) generally cannot be used, since even small sets of features are usually highly linearly redundant, rendering their covariance or correlation matrices too singular to be invertible. We argue that representing deciduous trees and many other objects by rich image descriptions can significantly aid their classification. We make no assumptions about the shape, location, viewpoint, viewing distance, lighting conditions, and camera parameters, and we only expect scanning methods and compression schemes to retain a “reasonable ” image quality. c ○ 1999 Academic Press 1.
3D to 2D Recognition with Regions
 IEEE Conference on Computer Vision and Pattern Recognition
, 1997
"... This paper presents a novel approach to partsbased object recognition in the presence of occlusion. We focus on the problem of determining the pose of a 3D object from a single 2D image when convex parts of the object have been matched to corresponding regions in the image. We consider three t ..."
Abstract

Cited by 3 (0 self)
 Add to MetaCart
(Show Context)
This paper presents a novel approach to partsbased object recognition in the presence of occlusion. We focus on the problem of determining the pose of a 3D object from a single 2D image when convex parts of the object have been matched to corresponding regions in the image. We consider three types of occlusions: selfocclusion, occlusions whose locus is identified in the image, and completely arbitrary occlusions. We derive efficient algorithms for the first two cases, and characterize their performance. For the last case, we prove that the problem of finding valid poses is computationally hard, but provide an efficient, approximate algorithm. This work generalizes our previous work on regionbased object recognition, which focused on the case of planar models. A preliminary version of this paper has appeared in [29] A brief overview of these and related results has appeared in [8] y This research was supported by the Unites StatesIsrael Binational Science Foundation, Gr...
3D Matching using Statistically Significant Groupings
 American Behavioral Scientist
, 1996
"... Vision programming is defined as the task of constructing explicit object models to be used in object recognition. These object models specify the features to be used in recognizing the object as well as the exact order in which they have to be used. For 3D recognition, in the absence of grouping in ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
Vision programming is defined as the task of constructing explicit object models to be used in object recognition. These object models specify the features to be used in recognizing the object as well as the exact order in which they have to be used. For 3D recognition, in the absence of grouping information, the number of bases (model feature/image feature correspondences) that must be examined before a match is found is prohibitively large. By exploiting the relationships between features, we can avoid having to consider a potentially large number of bases. The automatic programming framework [5] helps us in ordering model features based on their utilities such as detectability and error rate that are derived from training data. Examining model features in the order specified by this framework leads to minimal numbers of bases being considered before a match is found. In this article, we describe a vision programming approach to matching 3D models to 2D images. Our system considers feature clusters instead of individual features...
c ○ 1997 Kluwer Academic Publishers. Manufactured in The Netherlands. Recognition Using Region Correspondences
, 1995
"... Abstract. Recognition systems attempt to recover information about the identity of observed objects and their location in the environment. A fundamental problem in recognition is pose estimation. This is the problem of using a correspondence between some portions of an object model and some portions ..."
Abstract
 Add to MetaCart
(Show Context)
Abstract. Recognition systems attempt to recover information about the identity of observed objects and their location in the environment. A fundamental problem in recognition is pose estimation. This is the problem of using a correspondence between some portions of an object model and some portions of an image to determine whether the image contains an instance of the object, and, in case it does, to determine the transformation that relates the model to the image. The current approaches to this problem are divided into methods that use “global ” properties of the object (e.g., centroid and moments of inertia) and methods that use “local ” properties of the object (e.g., corners and line segments). Global properties are sensitive to occlusion and, specifically, to self occlusion. Local properties are difficult to locate reliably, and their matching involves intensive computation. We present a novel method for recognition that uses region information. In our approach the model and the image are divided into regions. Given a match between subsets of regions (without any explicit correspondence between different pieces of the regions) the alignment transformation is computed. The method applies to planar objects under similarity, affine, and projective transformations and to projections of 3D objects undergoing affine and projective transformations. The new approach combines many of the advantages of the previous two approaches, while avoiding some of their pitfalls. Like the global methods, our approach makes use of region information that reflects the true shape of the object. But like local methods, our approach can handle occlusion.