Pub Date : 1999-06-23DOI: 10.1109/CVPR.1999.786970
M. Fornefett, K. Rohr, H. Stiehl
We introduce radial basis functions with compact support for elastic registration of medical images. With these basis functions the influence of a landmark on the registration result is limited to a circle in 2D and, respectively, to a sphere in 3D. Therefore, the registration can be locally constrained which especially allows to deal with rather local changes in medical images due to, e.g., tumor resection. An important property of the used RBFs is that they are positive definite. Thus, the solvability of the resulting system of equations is always guaranteed. We demonstrate our approach for synthetic as well as for 2D and 3D tomographic images.
{"title":"Elastic registration of medical images using radial basis functions with compact support","authors":"M. Fornefett, K. Rohr, H. Stiehl","doi":"10.1109/CVPR.1999.786970","DOIUrl":"https://doi.org/10.1109/CVPR.1999.786970","url":null,"abstract":"We introduce radial basis functions with compact support for elastic registration of medical images. With these basis functions the influence of a landmark on the registration result is limited to a circle in 2D and, respectively, to a sphere in 3D. Therefore, the registration can be locally constrained which especially allows to deal with rather local changes in medical images due to, e.g., tumor resection. An important property of the used RBFs is that they are positive definite. Thus, the solvability of the resulting system of equations is always guaranteed. We demonstrate our approach for synthetic as well as for 2D and 3D tomographic images.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"10 1","pages":"402-407 Vol. 1"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75986358","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 : 1999-06-23DOI: 10.1109/CVPR.1999.786924
A. Broadhurst, R. Cipolla
The object of this paper is to find a quick and accurate method for computing the projection matrices of an image sequence, so that the error is distributed evenly along the sequence. It assumes that a set of correspondences between points in the images is known, and that these points represent rigid points in the world. This paper extends the algebraic minimisation approach developed by Hartley so that it can be used for long image sequences. This is achieved by initially computing a trifocal tensor using the three most extreme views. The intermediate views are then computed linearly using the trifocal tensor. An iterative algorithm as presented which perturbs the twelve entries of one camera matrix so that the algebraic error along the whole sequence is minimised.
{"title":"Calibration of image sequences for model visualisation","authors":"A. Broadhurst, R. Cipolla","doi":"10.1109/CVPR.1999.786924","DOIUrl":"https://doi.org/10.1109/CVPR.1999.786924","url":null,"abstract":"The object of this paper is to find a quick and accurate method for computing the projection matrices of an image sequence, so that the error is distributed evenly along the sequence. It assumes that a set of correspondences between points in the images is known, and that these points represent rigid points in the world. This paper extends the algebraic minimisation approach developed by Hartley so that it can be used for long image sequences. This is achieved by initially computing a trifocal tensor using the three most extreme views. The intermediate views are then computed linearly using the trifocal tensor. An iterative algorithm as presented which perturbs the twelve entries of one camera matrix so that the algebraic error along the whole sequence is minimised.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"28 1","pages":"100-105 Vol. 1"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74368278","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 : 1999-06-23DOI: 10.1109/CVPR.1999.784651
I. Cohen, G. Medioni
We address the problem of detection and tracking of moving objects in a video stream obtained from a moving airborne platform. The proposed method relies on a graph representation of moving objects which allows to derive and maintain a dynamic template of each moving object by enforcing their temporal coherence. This inferred template along with the graph representation used in our approach allows us to characterize objects trajectories as an optimal path in a graph. The proposed tracker allows to deal with partial occlusions, stop and go motion in very challenging situations. We demonstrate results on a number of different real sequences. We then define an evaluation methodology to quantify our results and show how tracking overcome detection errors.
{"title":"Detecting and tracking moving objects for video surveillance","authors":"I. Cohen, G. Medioni","doi":"10.1109/CVPR.1999.784651","DOIUrl":"https://doi.org/10.1109/CVPR.1999.784651","url":null,"abstract":"We address the problem of detection and tracking of moving objects in a video stream obtained from a moving airborne platform. The proposed method relies on a graph representation of moving objects which allows to derive and maintain a dynamic template of each moving object by enforcing their temporal coherence. This inferred template along with the graph representation used in our approach allows us to characterize objects trajectories as an optimal path in a graph. The proposed tracker allows to deal with partial occlusions, stop and go motion in very challenging situations. We demonstrate results on a number of different real sequences. We then define an evaluation methodology to quantify our results and show how tracking overcome detection errors.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"18 1","pages":"319-325 Vol. 2"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74428868","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 : 1999-06-23DOI: 10.1109/CVPR.1999.784727
Peng Chang, J. Krumm
We use the color cooccurrence histogram (CH) for recognizing objects in images. The color CH keeps track of the number of pairs of certain colored pixels that occur at certain separation distances in image space. The color CH adds geometric information to the normal color histogram, which abstracts away all geometry. We compute model CHs based on images of known objects taken from different points of view. These model CHs are then matched to subregions in test images to find the object. By adjusting the number of colors and the number of distances used in the CH, we can adjust the tolerance of the algorithm to changes in lighting, viewpoint, and the flexibility of the object We develop a mathematical model of the algorithm's false alarm probability and use this as a principled way of picking most of the algorithm's adjustable parameters. We demonstrate our algorithm on different objects, showing that it recognizes objects in spite of confusing background clutter partial occlusions, and flexing of the object.
{"title":"Object recognition with color cooccurrence histograms","authors":"Peng Chang, J. Krumm","doi":"10.1109/CVPR.1999.784727","DOIUrl":"https://doi.org/10.1109/CVPR.1999.784727","url":null,"abstract":"We use the color cooccurrence histogram (CH) for recognizing objects in images. The color CH keeps track of the number of pairs of certain colored pixels that occur at certain separation distances in image space. The color CH adds geometric information to the normal color histogram, which abstracts away all geometry. We compute model CHs based on images of known objects taken from different points of view. These model CHs are then matched to subregions in test images to find the object. By adjusting the number of colors and the number of distances used in the CH, we can adjust the tolerance of the algorithm to changes in lighting, viewpoint, and the flexibility of the object We develop a mathematical model of the algorithm's false alarm probability and use this as a principled way of picking most of the algorithm's adjustable parameters. We demonstrate our algorithm on different objects, showing that it recognizes objects in spite of confusing background clutter partial occlusions, and flexing of the object.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"47 1","pages":"498-504 Vol. 2"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80570817","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 : 1999-06-23DOI: 10.1109/CVPR.1999.786956
Imari Sato, Yoichi Sato, K. Ikeuchi
The image irradiance of a three-dimensional object is known to be the function of three components: the distribution of light sources, the shape, and reflectance of a real object surface. In the past, recovering the shape and reflectance of an object surface from the recorded image brightness has been intensively investigated. On the other hand, there has been little progress in recovering illumination from the knowledge of the shape and reflectance of a real object. In this paper, we propose a new method for estimating the illumination distribution of a real scene from image brightness observed on a real object surface in that scene. More specifically, we recover the illumination distribution of the scene from a radiance distribution inside shadows cast by an object of known shape onto another object surface of known shape and reflectance. By using the occlusion information of the incoming light, we are able to reliably estimate the illumination distribution of a real scene, even in a complex illumination environment.
{"title":"Illumination distribution from shadows","authors":"Imari Sato, Yoichi Sato, K. Ikeuchi","doi":"10.1109/CVPR.1999.786956","DOIUrl":"https://doi.org/10.1109/CVPR.1999.786956","url":null,"abstract":"The image irradiance of a three-dimensional object is known to be the function of three components: the distribution of light sources, the shape, and reflectance of a real object surface. In the past, recovering the shape and reflectance of an object surface from the recorded image brightness has been intensively investigated. On the other hand, there has been little progress in recovering illumination from the knowledge of the shape and reflectance of a real object. In this paper, we propose a new method for estimating the illumination distribution of a real scene from image brightness observed on a real object surface in that scene. More specifically, we recover the illumination distribution of the scene from a radiance distribution inside shadows cast by an object of known shape onto another object surface of known shape and reflectance. By using the occlusion information of the incoming light, we are able to reliably estimate the illumination distribution of a real scene, even in a complex illumination environment.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"211 1","pages":"306-312 Vol. 1"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78125149","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 : 1999-06-23DOI: 10.1109/CVPR.1999.786948
G. Cong, B. Parvin
A new approach for segmentation of nuclei observed with an epi-fluorescence microscope is presented. The technique is model based and uses local feature activities such as step-edge segments, roof-edge segments, and concave corners to construct a set of initial hypotheses. These local feature activities are extracted using either local or global operators to form a possible set of hypotheses. Each hypothesis is expressed as a hyperquadric for better stability, compactness, and error handling. The search space is expressed as an assignment matrix with an appropriate cost function to ensure local adjacency, and global consistency. Each possible configuration of a set of nuclei defines a path, and the path with the least error corresponds to best representation. This result is then presented to an operator who verifies and eliminates a small number of errors.
{"title":"Model based segmentation of nuclei","authors":"G. Cong, B. Parvin","doi":"10.1109/CVPR.1999.786948","DOIUrl":"https://doi.org/10.1109/CVPR.1999.786948","url":null,"abstract":"A new approach for segmentation of nuclei observed with an epi-fluorescence microscope is presented. The technique is model based and uses local feature activities such as step-edge segments, roof-edge segments, and concave corners to construct a set of initial hypotheses. These local feature activities are extracted using either local or global operators to form a possible set of hypotheses. Each hypothesis is expressed as a hyperquadric for better stability, compactness, and error handling. The search space is expressed as an assignment matrix with an appropriate cost function to ensure local adjacency, and global consistency. Each possible configuration of a set of nuclei defines a path, and the path with the least error corresponds to best representation. This result is then presented to an operator who verifies and eliminates a small number of errors.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"79 1","pages":"256-261 Vol. 1"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90963933","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 : 1999-06-23DOI: 10.1109/CVPR.1999.784621
M. Lhuillier, Long Quan
Creating novel views by interpolating prestored images or view morphing has many applications in visual simulation. We present in this paper a new method of automatically interpolating two images which tackles two most difficult problems of morphing due to the lack of depth informational pixel matching and visibility handling. We first describe a quasi-dense matching algorithm based on region growing with the best first strategy for match propagation. Then, we describe a robust construction of matched planar patches using local geometric constraints encoded by a homography. After that we introduce a novel representation, joint view triangulation, for visible and half-occluded patches in two images to handle their visibility during the creation of new view. Finally we demonstrate these techniques on real image pairs.
{"title":"Image interpolation by joint view triangulation","authors":"M. Lhuillier, Long Quan","doi":"10.1109/CVPR.1999.784621","DOIUrl":"https://doi.org/10.1109/CVPR.1999.784621","url":null,"abstract":"Creating novel views by interpolating prestored images or view morphing has many applications in visual simulation. We present in this paper a new method of automatically interpolating two images which tackles two most difficult problems of morphing due to the lack of depth informational pixel matching and visibility handling. We first describe a quasi-dense matching algorithm based on region growing with the best first strategy for match propagation. Then, we describe a robust construction of matched planar patches using local geometric constraints encoded by a homography. After that we introduce a novel representation, joint view triangulation, for visible and half-occluded patches in two images to handle their visibility during the creation of new view. Finally we demonstrate these techniques on real image pairs.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"33 1","pages":"139-145 Vol. 2"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84529897","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 : 1999-06-23DOI: 10.1109/CVPR.1999.787003
K. Nishino, Yoichi Sato, K. Ikeuchi
Image-based and model-based methods are two representative rendering methods for generating virtual images of objects from their real images. Extensive research on these two methods has been made in CV and CG communities. However, both methods still have several drawbacks when it comes to applying them to the mixed reality where we integrate such virtual images with real background images. To overcome these difficulties, we propose a new method which we refer to as the Eigen-Texture method. The proposed method samples appearances of a real object under various illumination and viewing conditions, and compresses them in the 2D coordinate system defined on the 3D model surface. The 3D model is generated from a sequence of range images. The Eigen-Texture method is practical because it does not require any detailed reflectance analysis of the object surface, and has great advantages due to the accurate 3D geometric models. This paper describes the method, and reports on its implementation.
{"title":"Eigen-texture method: Appearance compression based on 3D model","authors":"K. Nishino, Yoichi Sato, K. Ikeuchi","doi":"10.1109/CVPR.1999.787003","DOIUrl":"https://doi.org/10.1109/CVPR.1999.787003","url":null,"abstract":"Image-based and model-based methods are two representative rendering methods for generating virtual images of objects from their real images. Extensive research on these two methods has been made in CV and CG communities. However, both methods still have several drawbacks when it comes to applying them to the mixed reality where we integrate such virtual images with real background images. To overcome these difficulties, we propose a new method which we refer to as the Eigen-Texture method. The proposed method samples appearances of a real object under various illumination and viewing conditions, and compresses them in the 2D coordinate system defined on the 3D model surface. The 3D model is generated from a sequence of range images. The Eigen-Texture method is practical because it does not require any detailed reflectance analysis of the object surface, and has great advantages due to the accurate 3D geometric models. This paper describes the method, and reports on its implementation.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"21 1","pages":"618-624 Vol. 1"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85416334","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 : 1999-06-23DOI: 10.1109/CVPR.1999.786962
A. Rajagopalan, S. Chaudhuri
We propose a method for simultaneous recovery of depth and restoration of scene intensity, given two defocused images of a scene. The space-variant blur parameter and the focused image of the scene are modeled as Markov random fields (MRFs). Line fields are included to preserve discontinuities. The joint posterior distribution of the blur parameter and the intensity process is examined for locality property and we derive an important result that the posterior is again Markov. The result enables us to obtain the maximum a posterior (MAP) estimates of the blur parameter and the focused image, within reasonable computational limits. The estimates of depth and the quality of the restored image are found to be quite good, even in the presence of discontinuities.
{"title":"Simultaneous depth recovery and image restoration from defocused images","authors":"A. Rajagopalan, S. Chaudhuri","doi":"10.1109/CVPR.1999.786962","DOIUrl":"https://doi.org/10.1109/CVPR.1999.786962","url":null,"abstract":"We propose a method for simultaneous recovery of depth and restoration of scene intensity, given two defocused images of a scene. The space-variant blur parameter and the focused image of the scene are modeled as Markov random fields (MRFs). Line fields are included to preserve discontinuities. The joint posterior distribution of the blur parameter and the intensity process is examined for locality property and we derive an important result that the posterior is again Markov. The result enables us to obtain the maximum a posterior (MAP) estimates of the blur parameter and the focused image, within reasonable computational limits. The estimates of depth and the quality of the restored image are found to be quite good, even in the presence of discontinuities.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"99 1","pages":"348-353 Vol. 1"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81019172","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 : 1999-06-23DOI: 10.1109/CVPR.1999.786961
B. Matei, P. Meer
A new method for 3D rigid motion estimation is derived under the most general assumption that the measurements are corrupted by inhomogeneous and anisotropic, i.e., heteroscedastic noise. This is the case, for example, when the motion of a calibrated stereo-head is to be determined from image pairs. Linearization in the quaternion space transforms the problem into a multivariate, heteroscedastic errors-in-variables (HEIV) regression, from which the rotation and translation estimates are obtained simultaneously. The significant performance improvement is illustrated, for real data, by comparison with the results of quaternion, subspace and renormalization based approaches described in the literature. Extensive use as made of bootstrap, an advanced numerical tool from statistics, both to estimate the covariances of the 3D data points and to obtain confidence regions for the rotation and translation estimates. Bootstrap enables an accurate recovery of these information using only the two image pairs serving as input.
{"title":"Optimal rigid motion estimation and performance evaluation with bootstrap","authors":"B. Matei, P. Meer","doi":"10.1109/CVPR.1999.786961","DOIUrl":"https://doi.org/10.1109/CVPR.1999.786961","url":null,"abstract":"A new method for 3D rigid motion estimation is derived under the most general assumption that the measurements are corrupted by inhomogeneous and anisotropic, i.e., heteroscedastic noise. This is the case, for example, when the motion of a calibrated stereo-head is to be determined from image pairs. Linearization in the quaternion space transforms the problem into a multivariate, heteroscedastic errors-in-variables (HEIV) regression, from which the rotation and translation estimates are obtained simultaneously. The significant performance improvement is illustrated, for real data, by comparison with the results of quaternion, subspace and renormalization based approaches described in the literature. Extensive use as made of bootstrap, an advanced numerical tool from statistics, both to estimate the covariances of the 3D data points and to obtain confidence regions for the rotation and translation estimates. Bootstrap enables an accurate recovery of these information using only the two image pairs serving as input.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":"3 1","pages":"339-345 Vol. 1"},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82416473","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：