Pub Date : 1992-06-15DOI: 10.1109/CVPR.1992.223141
Visvanathan Ramesh, R. Haralick
It is shown how random perturbation models can be set up for a vision algorithm sequence involving edge finding, edge linking, and gap filling. By starting with an appropriate noise model for the input data, the authors derive random perturbation models for the output data at each stage of their example sequence. These random perturbation models are useful for performing model-based theoretical comparisons of the performance of vision algorithms. Parameters of these random perturbation models are related to measures of error such as the probability of misdetection of feature units, probability of false alarm, and the probability of incorrect grouping. Since the parameters of the perturbation model at the output of an algorithm are indicators of the performance of the algorithm, one could utilize these models to automate the selection of various free parameters (thresholds) of the algorithm.<>
{"title":"Random perturbation models and performance characterization in computer vision","authors":"Visvanathan Ramesh, R. Haralick","doi":"10.1109/CVPR.1992.223141","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223141","url":null,"abstract":"It is shown how random perturbation models can be set up for a vision algorithm sequence involving edge finding, edge linking, and gap filling. By starting with an appropriate noise model for the input data, the authors derive random perturbation models for the output data at each stage of their example sequence. These random perturbation models are useful for performing model-based theoretical comparisons of the performance of vision algorithms. Parameters of these random perturbation models are related to measures of error such as the probability of misdetection of feature units, probability of false alarm, and the probability of incorrect grouping. Since the parameters of the perturbation model at the output of an algorithm are indicators of the performance of the algorithm, one could utilize these models to automate the selection of various free parameters (thresholds) of the algorithm.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130447793","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 : 1992-06-15DOI: 10.1109/CVPR.1992.223245
Yong C. Kim, K. Price
In automated feature-based motion analysis of multiple frames, correspondence data are usually noisy and fragmented. A technique that gradually refines the initial noisy correspondence data and links fragments of a single trajectory using feedback from 3D motion estimation is presented. First, 3D motion parameters are estimated using the initial correspondence data. Then, each noisy trajectory is partitioned into subsets of points, each of which conforms to the estimated motion. The best set is used as the input to the next motion estimation. This process is repeated, and the gaps in the refined correspondence data are filled by guidance from the predicted motion. Test results for a standard real image sequence are presented.<>
{"title":"Refinement of noisy correspondence using feedback from 3D motion","authors":"Yong C. Kim, K. Price","doi":"10.1109/CVPR.1992.223245","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223245","url":null,"abstract":"In automated feature-based motion analysis of multiple frames, correspondence data are usually noisy and fragmented. A technique that gradually refines the initial noisy correspondence data and links fragments of a single trajectory using feedback from 3D motion estimation is presented. First, 3D motion parameters are estimated using the initial correspondence data. Then, each noisy trajectory is partitioned into subsets of points, each of which conforms to the estimated motion. The best set is used as the input to the next motion estimation. This process is repeated, and the gaps in the refined correspondence data are filled by guidance from the predicted motion. Test results for a standard real image sequence are presented.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130623245","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 : 1992-06-15DOI: 10.1109/CVPR.1992.223258
Hari N. Nair, C. Stewart
Depth maps obtained from focus ranging can have numerous errors and distortions due to edge bleeding, feature shifts, image noise, and field curvature. An improved algorithm that examines an initial high depth-of-field image of the scene to identify regions susceptible to edge bleeding and image noise is given. Focus evaluation windows are adapted to local image content and optimize the tradeoff between spatial resolution and noise sensitivity. An elliptical paraboloid field curvature model is used to reduce range distortion in peripheral image areas. Spatio-temporal tracking compensates for image feature shifts. The result is a sparse but reliable depth map.<>
{"title":"Robust focus ranging","authors":"Hari N. Nair, C. Stewart","doi":"10.1109/CVPR.1992.223258","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223258","url":null,"abstract":"Depth maps obtained from focus ranging can have numerous errors and distortions due to edge bleeding, feature shifts, image noise, and field curvature. An improved algorithm that examines an initial high depth-of-field image of the scene to identify regions susceptible to edge bleeding and image noise is given. Focus evaluation windows are adapted to local image content and optimize the tradeoff between spatial resolution and noise sensitivity. An elliptical paraboloid field curvature model is used to reduce range distortion in peripheral image areas. Spatio-temporal tracking compensates for image feature shifts. The result is a sparse but reliable depth map.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128985205","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 : 1992-06-15DOI: 10.1109/CVPR.1992.223219
Charlie Rothwell, Andrew Zisserman, J. Mundy, D. Forsyth
Projectively invariant shape descriptors allow fast indexing into model libraries without the need for pose computation or camera calibration. Progress in building a model-based vision system for plane objects that uses algebraic projective invariants is described. A brief account of these descriptors is given, and the recognition system is described, giving examples of the invariant techniques working on real images.<>
{"title":"Efficient model library access by projectively invariant indexing functions","authors":"Charlie Rothwell, Andrew Zisserman, J. Mundy, D. Forsyth","doi":"10.1109/CVPR.1992.223219","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223219","url":null,"abstract":"Projectively invariant shape descriptors allow fast indexing into model libraries without the need for pose computation or camera calibration. Progress in building a model-based vision system for plane objects that uses algebraic projective invariants is described. A brief account of these descriptors is given, and the recognition system is described, giving examples of the invariant techniques working on real images.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131028932","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 : 1992-06-15DOI: 10.1109/CVPR.1992.223153
D. Jacobs
It is shown that the set of 2-D images produced by a group of 3-D point features of a rigid model can be optimally represented with two lines in two high-dimensional spaces. This result is used to match images and model groups by table lookup. The table is efficiently built and accessed through analytic methods that account for the effect of sensing error. In real images, it reduces the set of potential matches by a factor of several thousand. This representation of a model's images is used to analyze two other approaches to recognition. It is determined when invariants exist in several domains, and it is shown that there is an infinite set of qualitatively similar nonaccidental properties.<>
{"title":"Space efficient 3-D model indexing","authors":"D. Jacobs","doi":"10.1109/CVPR.1992.223153","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223153","url":null,"abstract":"It is shown that the set of 2-D images produced by a group of 3-D point features of a rigid model can be optimally represented with two lines in two high-dimensional spaces. This result is used to match images and model groups by table lookup. The table is efficiently built and accessed through analytic methods that account for the effect of sensing error. In real images, it reduces the set of potential matches by a factor of several thousand. This representation of a model's images is used to analyze two other approaches to recognition. It is determined when invariants exist in several domains, and it is shown that there is an infinite set of qualitatively similar nonaccidental properties.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"89 11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129753427","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 : 1992-06-15DOI: 10.1109/CVPR.1992.223267
Sudeep Sarkar, K. Boyer
It is shown that the formalism of Bayesian networks provides an elegant solution, in a probabilistic framework, to the problem of integrating top-down and bottom-up visual processes as well serving as a knowledge base. The formalism is modified to handle spatial data and thus extends the applicability of Bayesian networks to visual processing. The modified form is called the perceptual inference network (PIN). The theoretical background of a PIN is presented, and its viability is demonstrated in the context of perceptual organization. The PIN imparts an active inferential and integrating nature to perceptual organization.<>
{"title":"Perceptual organization using Bayesian networks","authors":"Sudeep Sarkar, K. Boyer","doi":"10.1109/CVPR.1992.223267","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223267","url":null,"abstract":"It is shown that the formalism of Bayesian networks provides an elegant solution, in a probabilistic framework, to the problem of integrating top-down and bottom-up visual processes as well serving as a knowledge base. The formalism is modified to handle spatial data and thus extends the applicability of Bayesian networks to visual processing. The modified form is called the perceptual inference network (PIN). The theoretical background of a PIN is presented, and its viability is demonstrated in the context of perceptual organization. The PIN imparts an active inferential and integrating nature to perceptual organization.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134594003","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 : 1992-06-15DOI: 10.1109/CVPR.1992.223147
Kyoung Mu Lee, C.-C. Jay Kuo
Two iterative algorithms for shape reconstruction based on multiple images taken under different lighting conditions, known as photometric stereo, are proposed. It is shown that single-image shape-from-shading (SFS) algorithms have an inherent problem, i.e., the accuracy of the reconstructed surface height is related to the slope of the reflectance map function defined on the gradient space. This observation motivates the authors to generalize the single-image SFS algorithm to two photometric stereo SFS algorithms aiming at more accurate surface reconstruction. The two algorithms directly determine the surface height by minimizing a quadratic cost functional, which is defined to be the square of the brightness error obtained from each individual image in a parallel or cascade manner. The optimal illumination condition that leads to best shape reconstruction is examined.<>
{"title":"Shape reconstruction from photometric stereo","authors":"Kyoung Mu Lee, C.-C. Jay Kuo","doi":"10.1109/CVPR.1992.223147","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223147","url":null,"abstract":"Two iterative algorithms for shape reconstruction based on multiple images taken under different lighting conditions, known as photometric stereo, are proposed. It is shown that single-image shape-from-shading (SFS) algorithms have an inherent problem, i.e., the accuracy of the reconstructed surface height is related to the slope of the reflectance map function defined on the gradient space. This observation motivates the authors to generalize the single-image SFS algorithm to two photometric stereo SFS algorithms aiming at more accurate surface reconstruction. The two algorithms directly determine the surface height by minimizing a quadratic cost functional, which is defined to be the square of the brightness error obtained from each individual image in a parallel or cascade manner. The optimal illumination condition that leads to best shape reconstruction is examined.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129398793","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 : 1992-06-15DOI: 10.1109/CVPR.1992.223144
S. B. Marapane, M. Trivedi
A computational framework for an accurate, robust, and efficient stereo approach is developed. Most of the deficiencies prevailing in current computational models of stereo can be attributed to their use of a single, typically edge-element-based, primitive for stereo analysis and to their use of a single-level control strategy. The multi-primitive hierarchical (MPH) framework for stereo analysis presented is directed toward overcoming these deficiencies. In the MPH model, stereo analysis is performed in multiple stages, incorporating multiple primitives and utilizing a hierarchical control strategy. The higher levels of the hierarchical system are based on primitives containing more semantic information, and the results of stereo analysis at higher levels are used for guidance at the lower levels. It is shown that such a stereo system is superior to a single-level, single-primitive system.<>
{"title":"Multi-primitive hierarchical (MPH) stereo system","authors":"S. B. Marapane, M. Trivedi","doi":"10.1109/CVPR.1992.223144","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223144","url":null,"abstract":"A computational framework for an accurate, robust, and efficient stereo approach is developed. Most of the deficiencies prevailing in current computational models of stereo can be attributed to their use of a single, typically edge-element-based, primitive for stereo analysis and to their use of a single-level control strategy. The multi-primitive hierarchical (MPH) framework for stereo analysis presented is directed toward overcoming these deficiencies. In the MPH model, stereo analysis is performed in multiple stages, incorporating multiple primitives and utilizing a hierarchical control strategy. The higher levels of the hierarchical system are based on primitives containing more semantic information, and the results of stereo analysis at higher levels are used for guidance at the lower levels. It is shown that such a stereo system is superior to a single-level, single-primitive system.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129579361","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 : 1992-06-15DOI: 10.1109/CVPR.1992.223207
J. L. Véhel, Pascal Mignot, J. Berroir
Image analysis using texture and multifractal paradigms is addressed. Multifractal theory and its application to image description are discussed, and it is shown that this approach allows the discrete signal to be worked on directly. A system for texture classification that is based on a learning scheme and does not make use of any a priori model is introduced. Image segmentation is then considered, and the notion of mixed classes, which allows accurate detection of texture boundaries on complex images, is introduced.<>
{"title":"Multifractals, texture, and image analysis","authors":"J. L. Véhel, Pascal Mignot, J. Berroir","doi":"10.1109/CVPR.1992.223207","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223207","url":null,"abstract":"Image analysis using texture and multifractal paradigms is addressed. Multifractal theory and its application to image description are discussed, and it is shown that this approach allows the discrete signal to be worked on directly. A system for texture classification that is based on a learning scheme and does not make use of any a priori model is introduced. Image segmentation is then considered, and the notion of mixed classes, which allows accurate detection of texture boundaries on complex images, is introduced.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128403567","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 : 1992-06-15DOI: 10.1109/CVPR.1992.223145
Liang-Hua Chen, Wei-Chung Lin
An algorithm for extracting and segmenting surface descriptions from stereo images is presented. Compared with the advance of range image segmentation, the progress of surface segmentation from stereo images is slow. The algorithm integrates the boundary-based and region-based approaches to achieve more satisfactory segmentation results. The algorithm yields such a rich description of a scene in terms of global surface patches and closed surface boundaries. These shape primitives are useful for subsequent high-level processing.<>
{"title":"Surface segmentation from stereo","authors":"Liang-Hua Chen, Wei-Chung Lin","doi":"10.1109/CVPR.1992.223145","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223145","url":null,"abstract":"An algorithm for extracting and segmenting surface descriptions from stereo images is presented. Compared with the advance of range image segmentation, the progress of surface segmentation from stereo images is slow. The algorithm integrates the boundary-based and region-based approaches to achieve more satisfactory segmentation results. The algorithm yields such a rich description of a scene in terms of global surface patches and closed surface boundaries. These shape primitives are useful for subsequent high-level processing.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122515614","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：