Pub Date : 1998-01-04DOI: 10.1109/ICCV.1998.710720
D. Marimont, Y. Rubner
We devise a statistical framework for edge detection by performing a statistical analysis of zero crossings of the second derivative of an image. This analysis enables us to estimate at each pixel of an image the probability that an edge passes through the pixel. We present a statistical analysis of the the Lindeberg operators that we use to compute image derivatives. We also introduce a confidence probability that tells us how reliable the edge probability is, given the image's noise level and the operator's scale. Combining the edge and confidence probabilities leads to a probabilistic scale selection algorithm. We present the results of experiments on natural images.
{"title":"A probabilistic framework for edge detection and scale selection","authors":"D. Marimont, Y. Rubner","doi":"10.1109/ICCV.1998.710720","DOIUrl":"https://doi.org/10.1109/ICCV.1998.710720","url":null,"abstract":"We devise a statistical framework for edge detection by performing a statistical analysis of zero crossings of the second derivative of an image. This analysis enables us to estimate at each pixel of an image the probability that an edge passes through the pixel. We present a statistical analysis of the the Lindeberg operators that we use to compute image derivatives. We also introduce a confidence probability that tells us how reliable the edge probability is, given the image's noise level and the operator's scale. Combining the edge and confidence probabilities leads to a probabilistic scale selection algorithm. We present the results of experiments on natural images.","PeriodicalId":270671,"journal":{"name":"Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116871405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1998-01-04DOI: 10.1109/ICCV.1998.710860
S. Sclaroff, J. Isidoro
A new region-based approach to nonrigid motion tracking is described. Shape is defined in terms of a deformable triangular mesh that captures object shape plus a color texture map that captures object appearance. Photometric variations are also modeled. Nonrigid shape registration and motion tracking are achieved by posing the problem as an energy-based, robust minimization procedure. The approach provides robustness to occlusions, wrinkles, shadows, and specular highlights. The formulation is tailored to rake advantage of texture mapping hardware available in many workstations, PCs, and game consoles. This enables nonrigid tracking at speeds approaching video rate.
{"title":"Active blobs","authors":"S. Sclaroff, J. Isidoro","doi":"10.1109/ICCV.1998.710860","DOIUrl":"https://doi.org/10.1109/ICCV.1998.710860","url":null,"abstract":"A new region-based approach to nonrigid motion tracking is described. Shape is defined in terms of a deformable triangular mesh that captures object shape plus a color texture map that captures object appearance. Photometric variations are also modeled. Nonrigid shape registration and motion tracking are achieved by posing the problem as an energy-based, robust minimization procedure. The approach provides robustness to occlusions, wrinkles, shadows, and specular highlights. The formulation is tailored to rake advantage of texture mapping hardware available in many workstations, PCs, and game consoles. This enables nonrigid tracking at speeds approaching video rate.","PeriodicalId":270671,"journal":{"name":"Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121464979","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1998-01-04DOI: 10.1109/ICCV.1998.710718
P. Liang
A novel local scale controlled piecewise linear diffusion for selective smoothing and edge detection is presented. The diffusion stops at the place and time determined by the minimum reliable local scale and a spatial variant, anisotropic local noise estimate. It shows anisotropic, nonlinear diffusion equation using diffusion coefficients/tensors that continuously depend on the gradient is not necessary to achieve sharp, distorted, stable edge detection across many scales. The new diffusion is anisotropic and asymmetric only at places it needs to be, i.e., at significant edges. It not only does not diffuse across significant edges, but also enhances edges. It advances geometry-driven diffusion because it is a piecewise linear model rather than a full nonlinear model, thus it is simple to implement and analyze, and avoids the difficulties and problems associated with nonlinear diffusion. It advances local scale control by introducing spatial variant, anisotropic local noise estimation, and local stopping of diffusion. The original local scale control was based on the unrealistic assumption of uniformly distributed noise independent of the image signal. The local noise estimate significantly improves local scale control.
{"title":"Local scale controlled anisotropic diffusion with local noise estimate for image smoothing and edge detection","authors":"P. Liang","doi":"10.1109/ICCV.1998.710718","DOIUrl":"https://doi.org/10.1109/ICCV.1998.710718","url":null,"abstract":"A novel local scale controlled piecewise linear diffusion for selective smoothing and edge detection is presented. The diffusion stops at the place and time determined by the minimum reliable local scale and a spatial variant, anisotropic local noise estimate. It shows anisotropic, nonlinear diffusion equation using diffusion coefficients/tensors that continuously depend on the gradient is not necessary to achieve sharp, distorted, stable edge detection across many scales. The new diffusion is anisotropic and asymmetric only at places it needs to be, i.e., at significant edges. It not only does not diffuse across significant edges, but also enhances edges. It advances geometry-driven diffusion because it is a piecewise linear model rather than a full nonlinear model, thus it is simple to implement and analyze, and avoids the difficulties and problems associated with nonlinear diffusion. It advances local scale control by introducing spatial variant, anisotropic local noise estimation, and local stopping of diffusion. The original local scale control was based on the unrealistic assumption of uniformly distributed noise independent of the image signal. The local noise estimate significantly improves local scale control.","PeriodicalId":270671,"journal":{"name":"Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122519440","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1998-01-04DOI: 10.1109/ICCV.1998.710752
M. Jolly, C. Liang, Alok Gupta
We propose a novel solution to the problem of motion compensation of coronary angiographs. As the heart is beating, it is difficult for the physician to observe closely a particular point (e.g. stenosis) on the artery tree. We propose, to rigidly compensate the sequence so that the area around the point of interest appears stable. This is a difficult problem because the arteries deform in a non-rigid manner and only their 2D X-ray projection is observed. Also, the lack of features around the selected point makes the matching subject to the aperture problem. The algorithm automatically extracts a section of the artery of interest, models it as a polyline, and tracks it. The problem is formulated as an energy minimization problem which is solved using a shortest path in a graph algorithm. The motion compensated sequence can be obtained by translating every pixel so that the point of interest remains stable. We have applied this algorithm to many examples in two sets of angiography data and have obtained excellent results.
{"title":"Optimal polyline tracking for artery motion compensation in coronary angiography","authors":"M. Jolly, C. Liang, Alok Gupta","doi":"10.1109/ICCV.1998.710752","DOIUrl":"https://doi.org/10.1109/ICCV.1998.710752","url":null,"abstract":"We propose a novel solution to the problem of motion compensation of coronary angiographs. As the heart is beating, it is difficult for the physician to observe closely a particular point (e.g. stenosis) on the artery tree. We propose, to rigidly compensate the sequence so that the area around the point of interest appears stable. This is a difficult problem because the arteries deform in a non-rigid manner and only their 2D X-ray projection is observed. Also, the lack of features around the selected point makes the matching subject to the aperture problem. The algorithm automatically extracts a section of the artery of interest, models it as a polyline, and tracks it. The problem is formulated as an energy minimization problem which is solved using a shortest path in a graph algorithm. The motion compensated sequence can be obtained by translating every pixel so that the point of interest remains stable. We have applied this algorithm to many examples in two sets of angiography data and have obtained excellent results.","PeriodicalId":270671,"journal":{"name":"Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126152374","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1998-01-04DOI: 10.1109/ICCV.1998.710785
A. Rajagopalan, K. S. Kumar, J. Karlekar, R. Manivasakan, M. Patil, U. Desai, P. G. Poonacha, S. Chaudhuri
Two new schemes are presented for finding human faces in a photograph. The first scheme approximates the unknown distributions of the face and the face-like manifolds wing higher order statistics (HOS). An HOS-based data clustering algorithm is also proposed. In the second scheme, the face to non-face and non-face to face transitions are learnt using a hidden Markov model (HMM). The HMM parameters are estimated corresponding to a given photograph and the faces are located by examining the optimal state sequence of the HMM. Experimental results are presented on the performance of both the schemes.
{"title":"Finding faces in photographs","authors":"A. Rajagopalan, K. S. Kumar, J. Karlekar, R. Manivasakan, M. Patil, U. Desai, P. G. Poonacha, S. Chaudhuri","doi":"10.1109/ICCV.1998.710785","DOIUrl":"https://doi.org/10.1109/ICCV.1998.710785","url":null,"abstract":"Two new schemes are presented for finding human faces in a photograph. The first scheme approximates the unknown distributions of the face and the face-like manifolds wing higher order statistics (HOS). An HOS-based data clustering algorithm is also proposed. In the second scheme, the face to non-face and non-face to face transitions are learnt using a hidden Markov model (HMM). The HMM parameters are estimated corresponding to a given photograph and the faces are located by examining the optimal state sequence of the HMM. Experimental results are presented on the performance of both the schemes.","PeriodicalId":270671,"journal":{"name":"Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125170626","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1998-01-04DOI: 10.1109/ICCV.1998.710782
I. Rigoutsos
We derive and discuss a set of parametric equations which, when given a convex 2D feature domain, K, will generate affine invariants with the property that the invariants' values are uniformly distributed in the region [0,1]/spl times/[0,1]. Definition of the shape of the convex domain K allows computation of the parameters' values and thus the proposed scheme can be tuned to a specific feature domain. The features of all recognizable objects (models) are assumed to be two-dimensional points and uniformly distributed over K. The scheme leads to improved discrimination power, improved computational-load and storage-load balancing and can also be used to determine and identify biases in the database of recognizable models (over-represented constructs of object points). Obvious enhancements produce rigid-transformation and similarity-transformation invariants with the same good distribution properties, making this approach generally applicable. An extension to the case of affine invariants for feature points in three-dimensional space, with the invariants now being uniformly distributed in the region [0,1]/spl times/[0,1]/spl times/[0,1], has also been carried out and is discussed briefly. We present results for several 2D convex domains using both synthetic data and real databases.
{"title":"2D-affine invariants that distribute uniformly and can be tuned to any convex feature domain","authors":"I. Rigoutsos","doi":"10.1109/ICCV.1998.710782","DOIUrl":"https://doi.org/10.1109/ICCV.1998.710782","url":null,"abstract":"We derive and discuss a set of parametric equations which, when given a convex 2D feature domain, K, will generate affine invariants with the property that the invariants' values are uniformly distributed in the region [0,1]/spl times/[0,1]. Definition of the shape of the convex domain K allows computation of the parameters' values and thus the proposed scheme can be tuned to a specific feature domain. The features of all recognizable objects (models) are assumed to be two-dimensional points and uniformly distributed over K. The scheme leads to improved discrimination power, improved computational-load and storage-load balancing and can also be used to determine and identify biases in the database of recognizable models (over-represented constructs of object points). Obvious enhancements produce rigid-transformation and similarity-transformation invariants with the same good distribution properties, making this approach generally applicable. An extension to the case of affine invariants for feature points in three-dimensional space, with the invariants now being uniformly distributed in the region [0,1]/spl times/[0,1]/spl times/[0,1], has also been carried out and is discussed briefly. We present results for several 2D convex domains using both synthetic data and real databases.","PeriodicalId":270671,"journal":{"name":"Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127048011","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1998-01-04DOI: 10.1109/ICCV.1998.710712
Margrit Betke, N. Makris
Following the theory of statistical estimation, the problem of recognizing objects imaged in complex real-world scenes is examined from a parametric perspective. A scalar measure of an object's complexity, which is invariant under affine transformation and changes in image noise level, is extracted from the object's Fisher information. The volume of Fisher information is shown to provide an overall statistical measure of the object's recognizability in a particular image, while the complexity provides an intrinsically physical measure that characterizes the object in any image. An information-conserving method is then developed for recognizing an object imaged in a complex scene. Here the term information-conserving means that the method uses all the measured data pertinent to the object's recognizability, attains the theoretical lower bound on estimation error for any unbiased estimate, and therefore is statistically optimal. This method is then successfully applied to finding objects imaged in thousands of complex real-world scenes.
{"title":"Information-conserving object recognition","authors":"Margrit Betke, N. Makris","doi":"10.1109/ICCV.1998.710712","DOIUrl":"https://doi.org/10.1109/ICCV.1998.710712","url":null,"abstract":"Following the theory of statistical estimation, the problem of recognizing objects imaged in complex real-world scenes is examined from a parametric perspective. A scalar measure of an object's complexity, which is invariant under affine transformation and changes in image noise level, is extracted from the object's Fisher information. The volume of Fisher information is shown to provide an overall statistical measure of the object's recognizability in a particular image, while the complexity provides an intrinsically physical measure that characterizes the object in any image. An information-conserving method is then developed for recognizing an object imaged in a complex scene. Here the term information-conserving means that the method uses all the measured data pertinent to the object's recognizability, attains the theoretical lower bound on estimation error for any unbiased estimate, and therefore is statistically optimal. This method is then successfully applied to finding objects imaged in thousands of complex real-world scenes.","PeriodicalId":270671,"journal":{"name":"Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130392441","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1998-01-04DOI: 10.1109/ICCV.1998.710749
I. Cohen, I. Herlin
This paper is concerned with the problem of tracking clouds structures like vortices in meteorological images. For this purpose we characterize the deformation between two successive occurrences, by matching their two boundary curves. Our approach is based on the computation of the set of paths connecting the two curves to be matched. It minimizes a cost function which measures the local similarity of the two curves. These matching paths are obtained as geodesic curves on this cost surface. Moreover our method allows to consider complex curves of arbitrary topology since these curves are represented through an implicit function rather than through a parameterization. Experimental results are given to illustrate the properties of the method in processing synthetic and then meteorologic remotely-sensed data.
{"title":"Tracking meteorological structures through curves matching using geodesic paths","authors":"I. Cohen, I. Herlin","doi":"10.1109/ICCV.1998.710749","DOIUrl":"https://doi.org/10.1109/ICCV.1998.710749","url":null,"abstract":"This paper is concerned with the problem of tracking clouds structures like vortices in meteorological images. For this purpose we characterize the deformation between two successive occurrences, by matching their two boundary curves. Our approach is based on the computation of the set of paths connecting the two curves to be matched. It minimizes a cost function which measures the local similarity of the two curves. These matching paths are obtained as geodesic curves on this cost surface. Moreover our method allows to consider complex curves of arbitrary topology since these curves are represented through an implicit function rather than through a parameterization. Experimental results are given to illustrate the properties of the method in processing synthetic and then meteorologic remotely-sensed data.","PeriodicalId":270671,"journal":{"name":"Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271)","volume":"331 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134364781","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1998-01-04DOI: 10.1109/ICCV.1998.710728
Gilles Simon, M. Berger
A model registration system capable of tracking an object, the model of which is known, in an image sequence is presented. It integrates tracking, pose determination and updating of the visible features. The heart of our system is the pose computation method, which handles various features (points, lines and free-form curves) in a very robust way and is able to give a correct estimate of the pose even when tracking errors occur. The reliability of the system is shown on an augmented reality project.
{"title":"A two-stage robust statistical method for temporal registration from features of various type","authors":"Gilles Simon, M. Berger","doi":"10.1109/ICCV.1998.710728","DOIUrl":"https://doi.org/10.1109/ICCV.1998.710728","url":null,"abstract":"A model registration system capable of tracking an object, the model of which is known, in an image sequence is presented. It integrates tracking, pose determination and updating of the visible features. The heart of our system is the pose computation method, which handles various features (points, lines and free-form curves) in a very robust way and is able to give a correct estimate of the pose even when tracking errors occur. The reliability of the system is shown on an augmented reality project.","PeriodicalId":270671,"journal":{"name":"Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271)","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132557961","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1998-01-04DOI: 10.1109/ICCV.1998.710825
Colin Davidson, A. Blake
This paper describes an efficient method to calculate, from an image of an object, configurations of a two-fingered robot gripper that form a "cage" to contain that object. Closing the fingers on the object from these configurations is guaranteed to reach a given desired grasp. This builds on the visual grasping theory of A. Blake et al. (1993), which describes how to find optimal grasps. It extends the results of E. Rimon and A. Blake (1996) which show how to construct such cages, in two ways. First, a more efficient algorithm for computing the cage is described. Second, a further development deals with occlusion by solving the caging problem within a restricted image window. The new methods greatly reduce the complexity of the visual caging problem, making it feasible in a real time computer vision system.
{"title":"Error-tolerant visual planning of planar grasp","authors":"Colin Davidson, A. Blake","doi":"10.1109/ICCV.1998.710825","DOIUrl":"https://doi.org/10.1109/ICCV.1998.710825","url":null,"abstract":"This paper describes an efficient method to calculate, from an image of an object, configurations of a two-fingered robot gripper that form a \"cage\" to contain that object. Closing the fingers on the object from these configurations is guaranteed to reach a given desired grasp. This builds on the visual grasping theory of A. Blake et al. (1993), which describes how to find optimal grasps. It extends the results of E. Rimon and A. Blake (1996) which show how to construct such cages, in two ways. First, a more efficient algorithm for computing the cage is described. Second, a further development deals with occlusion by solving the caging problem within a restricted image window. The new methods greatly reduce the complexity of the visual caging problem, making it feasible in a real time computer vision system.","PeriodicalId":270671,"journal":{"name":"Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271)","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131633291","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：