Pub Date : 1999-06-23DOI: 10.1109/CVPR.1999.784974
J. Mendelsohn, Kostas Daniilidis
This paper focuses on the estimation of the intrinsic camera parameters and the trajectory of the camera from an image sequence. Intrinsic camera calibration and pose estimation are the prerequisites for many applications involving navigation tasks, scene reconstruction, and merging of virtual and real environments. Proposed and evaluated is a technical solution to decrease the sensitivity of self-calibration by placing easily identifiable targets of known shape in the environment. The relative position of the targets need not be known a priori. Assuming an appropriate ratio of size to distance these targets resolve known ambiguities. Constraints on the target placement and the cameras' motions are explored. The algorithm is extensively tested in a variety of real-world scenarios.
{"title":"Constrained self-calibration","authors":"J. Mendelsohn, Kostas Daniilidis","doi":"10.1109/CVPR.1999.784974","DOIUrl":"https://doi.org/10.1109/CVPR.1999.784974","url":null,"abstract":"This paper focuses on the estimation of the intrinsic camera parameters and the trajectory of the camera from an image sequence. Intrinsic camera calibration and pose estimation are the prerequisites for many applications involving navigation tasks, scene reconstruction, and merging of virtual and real environments. Proposed and evaluated is a technical solution to decrease the sensitivity of self-calibration by placing easily identifiable targets of known shape in the environment. The relative position of the targets need not be known a priori. Assuming an appropriate ratio of size to distance these targets resolve known ambiguities. Constraints on the target placement and the cameras' motions are explored. The algorithm is extensively tested in a variety of real-world scenarios.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73990453","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.1999.784726
A. Shokoufandeh, Sven J. Dickinson, Kaleem Siddiqi, S. Zucker
In an object recognition system, if the extracted image features are multilevel or multiscale, the indexing structure may take the form of a tree. Such structures are not only common in computer vision, but also appear in linguistics, graphics, computational biology, and a wide range of other domains. In this paper, we develop an indexing mechanism that maps the topological structure of a tree into a low-dimensional vector space. Based on a novel eigenvalue characterization of a tree, this topological signature allows us to efficiently retrieve a small set of candidates from a database of models. To accommodate occlusion and local deformation, local evidence is accumulated in each of the tree's topological subspaces. We demonstrate the approach with a series of indexing experiments in the domain of 2-D object recognition.
{"title":"Indexing using a spectral encoding of topological structure","authors":"A. Shokoufandeh, Sven J. Dickinson, Kaleem Siddiqi, S. Zucker","doi":"10.1109/CVPR.1999.784726","DOIUrl":"https://doi.org/10.1109/CVPR.1999.784726","url":null,"abstract":"In an object recognition system, if the extracted image features are multilevel or multiscale, the indexing structure may take the form of a tree. Such structures are not only common in computer vision, but also appear in linguistics, graphics, computational biology, and a wide range of other domains. In this paper, we develop an indexing mechanism that maps the topological structure of a tree into a low-dimensional vector space. Based on a novel eigenvalue characterization of a tree, this topological signature allows us to efficiently retrieve a small set of candidates from a database of models. To accommodate occlusion and local deformation, local evidence is accumulated in each of the tree's topological subspaces. We demonstrate the approach with a series of indexing experiments in the domain of 2-D object recognition.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74645857","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.1999.786968
R. A. Manning, C. Dyer
We introduce the problem of view interpolation for dynamic scenes. Our solution to this problem extends the concept of view morphing and retains the practical advantages of that method. We are specifically concerned with interpolating between two reference views captured at different times, so that there is a missing interval of time between when the views were taken. The synthetic interpolations produced by our algorithm portray one possible physically-valid version of what transpired in the scene during the missing time. It is assumed that each object in the original scene underwent a series of rigid translations. Dynamic view morphing can work with widely-spaced reference views, sparse point correspondences, and uncalibrated cameras. When the camera-to-camera transformation can be determined, the synthetic interpolation will portray scene objects moving along straight-line, constant-velocity trajectories in world space.
{"title":"Interpolating view and scene motion by dynamic view morphing","authors":"R. A. Manning, C. Dyer","doi":"10.1109/CVPR.1999.786968","DOIUrl":"https://doi.org/10.1109/CVPR.1999.786968","url":null,"abstract":"We introduce the problem of view interpolation for dynamic scenes. Our solution to this problem extends the concept of view morphing and retains the practical advantages of that method. We are specifically concerned with interpolating between two reference views captured at different times, so that there is a missing interval of time between when the views were taken. The synthetic interpolations produced by our algorithm portray one possible physically-valid version of what transpired in the scene during the missing time. It is assumed that each object in the original scene underwent a series of rigid translations. Dynamic view morphing can work with widely-spaced reference views, sparse point correspondences, and uncalibrated cameras. When the camera-to-camera transformation can be determined, the synthetic interpolation will portray scene objects moving along straight-line, constant-velocity trajectories in world space.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74284480","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.1999.784733
H. Shum, Zhengyou Zhang, Qifa Ke
In this paper we present an efficient hierarchical approach to structure from motion for long image sequences. There are two key elements to our approach: accurate 3D reconstruction for each segment and efficient bundle adjustment for the whole sequence. The image sequence is first divided into a number of segments so that feature points can be reliably tracked across each segment. Each segment has a long baseline to ensure accurate 3D reconstruction. To efficiently bundle adjust 3D structures from ail segments, we reduce the number of frames in each segment by introducing "virtual keyframes". The virtual frames encode the 3D structure of each segment along with its uncertainty but they form a small subset of the original frames. Our method achieves significant speedup over conventional bundle adjustment methods.
{"title":"Efficient bundle adjustment with virtual key frames: a hierarchical approach to multi-frame structure from motion","authors":"H. Shum, Zhengyou Zhang, Qifa Ke","doi":"10.1109/CVPR.1999.784733","DOIUrl":"https://doi.org/10.1109/CVPR.1999.784733","url":null,"abstract":"In this paper we present an efficient hierarchical approach to structure from motion for long image sequences. There are two key elements to our approach: accurate 3D reconstruction for each segment and efficient bundle adjustment for the whole sequence. The image sequence is first divided into a number of segments so that feature points can be reliably tracked across each segment. Each segment has a long baseline to ensure accurate 3D reconstruction. To efficiently bundle adjust 3D structures from ail segments, we reduce the number of frames in each segment by introducing \"virtual keyframes\". The virtual frames encode the 3D structure of each segment along with its uncertainty but they form a small subset of the original frames. Our method achieves significant speedup over conventional bundle adjustment methods.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77623309","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.1999.784658
M. Werman, M. Qiu, Subhashis Banerjee, Sumantra Dutta Roy
We describe a set of image measurements which are invariant to the camera internals but are location variant. We show that using these measurements it is possible to calculate the self-localization of a robot using known landmarks and uncalibrated cameras. We also show that it is possible to compute, using uncalibrated cameras, the Euclidean structure of 3-D world points using multiple views from known positions. We are free to alter the internal parameters of the camera during these operations. Our initial experiments demonstrate the applicability of the method.
{"title":"Robot localization using uncalibrated camera invariants","authors":"M. Werman, M. Qiu, Subhashis Banerjee, Sumantra Dutta Roy","doi":"10.1109/CVPR.1999.784658","DOIUrl":"https://doi.org/10.1109/CVPR.1999.784658","url":null,"abstract":"We describe a set of image measurements which are invariant to the camera internals but are location variant. We show that using these measurements it is possible to calculate the self-localization of a robot using known landmarks and uncalibrated cameras. We also show that it is possible to compute, using uncalibrated cameras, the Euclidean structure of 3-D world points using multiple views from known positions. We are free to alter the internal parameters of the camera during these operations. Our initial experiments demonstrate the applicability of the method.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79833492","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.1999.784625
S. Lai, M. Fang
Image alignment is one of the most important task in computer vision. In this paper, we explicitly model spatial illumination variations by low-order polynomial functions in an energy minimization framework. Data constraints for the alignment and illumination parameters are derived from the first-order Taylor approximation of a generalized brightness assumption. We formulate the parameter estimation problem in a weighted least-square framework by using the influence function from robust estimation to derive an iterative re-weighted least-square algorithm. A dynamic weighting scheme, which combines the factors from influence function, consistency of image gradients and nonlinear image intensity sensing, is used to improve the robustness of the image matching. In addition, a constraint sampling scheme and an estimation-warping alternative strategy are used in the proposed algorithm to improve its efficiency and accuracy. Experimental results are shown to demonstrate the robustness, efficiency and accuracy of the algorithm.
{"title":"Robust and efficient image alignment with spatially varying illumination models","authors":"S. Lai, M. Fang","doi":"10.1109/CVPR.1999.784625","DOIUrl":"https://doi.org/10.1109/CVPR.1999.784625","url":null,"abstract":"Image alignment is one of the most important task in computer vision. In this paper, we explicitly model spatial illumination variations by low-order polynomial functions in an energy minimization framework. Data constraints for the alignment and illumination parameters are derived from the first-order Taylor approximation of a generalized brightness assumption. We formulate the parameter estimation problem in a weighted least-square framework by using the influence function from robust estimation to derive an iterative re-weighted least-square algorithm. A dynamic weighting scheme, which combines the factors from influence function, consistency of image gradients and nonlinear image intensity sensing, is used to improve the robustness of the image matching. In addition, a constraint sampling scheme and an estimation-warping alternative strategy are used in the proposed algorithm to improve its efficiency and accuracy. Experimental results are shown to demonstrate the robustness, efficiency and accuracy of the algorithm.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81262952","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.1999.784649
Peter Lehel, E. Hemayed, A. Farag
We present an algorithm to solve the sensor planning problem for a trinocular, active vision system. This algorithm uses an iterative optimization method to first solve for the translation between the three cameras and then uses this result to solve for parameters such as pan, tilt angles of the cameras and zoom setting.
{"title":"Sensor planning for a trinocular active vision system","authors":"Peter Lehel, E. Hemayed, A. Farag","doi":"10.1109/CVPR.1999.784649","DOIUrl":"https://doi.org/10.1109/CVPR.1999.784649","url":null,"abstract":"We present an algorithm to solve the sensor planning problem for a trinocular, active vision system. This algorithm uses an iterative optimization method to first solve for the translation between the three cameras and then uses this result to solve for parameters such as pan, tilt angles of the cameras and zoom setting.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85114174","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.1999.784611
Lin Zhou, C. Kambhamettu
Superquadrics are a family of parametric shapes which can model a diverse set of objects. They have received significant attention because of their compact representation and robust methods for recovery of 3D models. However, their assumption of intrinsical symmetry fails in modeling numerous real-world examples such as human, body, animals, and other naturally occurring objects. In this paper, we present a novel approach, which is called extended superquadric to extend superquadric's representation power with exponent functions. An extended superquadric model can be deformed in any direction because it extends the exponents of superquadrics from constants to functions of the latitude and longitude angles in the spherical coordinate system. Thus extended superquadrics can model more complex shapes than superquadrics. It also maintains many desired properties of superquadrics such as compactness controllability, and intuitive meaning, which are all advantageous for shape modeling, recognition, and reconstruction. In this paper, besides the use of extended superquadrics for modeling, we also discuss our research into the recovery of extended superquadrics from 3D information (reconstruction). Experimental results of fitting extended superquadrics to 3D real data are presented. Our results are very encouraging and indicate that the use of extended superquadric is a promising paradigm for shape representation and recovery in computers vision and has potential benefits for the generation of synthetic images for computer graphics.
{"title":"Extending superquadrics with exponent functions: modeling and reconstruction","authors":"Lin Zhou, C. Kambhamettu","doi":"10.1109/CVPR.1999.784611","DOIUrl":"https://doi.org/10.1109/CVPR.1999.784611","url":null,"abstract":"Superquadrics are a family of parametric shapes which can model a diverse set of objects. They have received significant attention because of their compact representation and robust methods for recovery of 3D models. However, their assumption of intrinsical symmetry fails in modeling numerous real-world examples such as human, body, animals, and other naturally occurring objects. In this paper, we present a novel approach, which is called extended superquadric to extend superquadric's representation power with exponent functions. An extended superquadric model can be deformed in any direction because it extends the exponents of superquadrics from constants to functions of the latitude and longitude angles in the spherical coordinate system. Thus extended superquadrics can model more complex shapes than superquadrics. It also maintains many desired properties of superquadrics such as compactness controllability, and intuitive meaning, which are all advantageous for shape modeling, recognition, and reconstruction. In this paper, besides the use of extended superquadrics for modeling, we also discuss our research into the recovery of extended superquadrics from 3D information (reconstruction). Experimental results of fitting extended superquadrics to 3D real data are presented. Our results are very encouraging and indicate that the use of extended superquadric is a promising paradigm for shape representation and recovery in computers vision and has potential benefits for the generation of synthetic images for computer graphics.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81213883","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.1999.784619
H. Kang, Seong-Whan Lee
Although Behavior-Knowledge Space (BKS) method does not need any assumptions in combining multiple experts, it should build theoretically exponential storage spaces for storing and managing jointly observed K decisions from K experts. That is, combining K experts needs a (K+1)st-order probability distribution. However, it is well known that the distribution becomes unmanageable in storing and estimating, even for a small K. In order to overcome such weakness, it would be attractive to decompose the distribution into a number of component distributions and to approximate the distribution with a product of the component distributions. One of such previous works is to apply a conditional independence assumption to the distribution. Another work is to approximate the distribution with a product of only first-order tree dependencies or second-order distributions. In this paper, a dependency-based framework is proposed to optimality approximate a probability distribution with a product set of dth-order dependencies where 1
{"title":"A dependency-based framework of combining multiple experts for the recognition of unconstrained handwritten numerals","authors":"H. Kang, Seong-Whan Lee","doi":"10.1109/CVPR.1999.784619","DOIUrl":"https://doi.org/10.1109/CVPR.1999.784619","url":null,"abstract":"Although Behavior-Knowledge Space (BKS) method does not need any assumptions in combining multiple experts, it should build theoretically exponential storage spaces for storing and managing jointly observed K decisions from K experts. That is, combining K experts needs a (K+1)st-order probability distribution. However, it is well known that the distribution becomes unmanageable in storing and estimating, even for a small K. In order to overcome such weakness, it would be attractive to decompose the distribution into a number of component distributions and to approximate the distribution with a product of the component distributions. One of such previous works is to apply a conditional independence assumption to the distribution. Another work is to approximate the distribution with a product of only first-order tree dependencies or second-order distributions. In this paper, a dependency-based framework is proposed to optimality approximate a probability distribution with a product set of dth-order dependencies where 1<d<K, and to combine multiple experts based on the product set using the Bayesian formalism. This framework was experimented and evaluated with a standardized CEN-PARIMl data base.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82250588","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.1999.784656
Hiroyuki Segawa, T. Totsuka
In this paper we introduce a recursive filtering method to recover the 3D articulated motion from image sequences. In recursive filtering frameworks, the quality of the results heavily depends on the choice of state variables and the determination of the process model; which models a real object whose motion is to be estimated. Our approach employs robotics dynamics into the recursive filtering framework. And the key strategy is to incorporate joint torques into the model state variables. In addition, we assumed the variations of the joint torques are Gaussian noises. We describe how to integrate dynamics equations into Kalman filters, and with the experimental results our method is shown to be effective.
{"title":"Torque-based recursive filtering approach to the recovery of 3D articulated motion from image sequences","authors":"Hiroyuki Segawa, T. Totsuka","doi":"10.1109/CVPR.1999.784656","DOIUrl":"https://doi.org/10.1109/CVPR.1999.784656","url":null,"abstract":"In this paper we introduce a recursive filtering method to recover the 3D articulated motion from image sequences. In recursive filtering frameworks, the quality of the results heavily depends on the choice of state variables and the determination of the process model; which models a real object whose motion is to be estimated. Our approach employs robotics dynamics into the recursive filtering framework. And the key strategy is to incorporate joint torques into the model state variables. In addition, we assumed the variations of the joint torques are Gaussian noises. We describe how to integrate dynamics equations into Kalman filters, and with the experimental results our method is shown to be effective.","PeriodicalId":20644,"journal":{"name":"Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1999-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76564085","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：