Pub Date : 1992-06-15DOI: 10.1109/CVPR.1992.223146
D. McKeown, F. Perlant
The authors examine how estimates of three-dimensional scene structure, as encoded in a scene disparity map, can be improved by the analysis of the original monocular imagery. They describe the utilization of surface illumination information provided by the segmentation of the monocular image into fine surface patches of nearly homogeneous intensity to remove mismatches generated during stereo matching. These patches are used to guide a statistical analysis of the disparity map based on the assumption that such patches correspond closely with physical surfaces in the scene. Such a technique is quite independent of whether the initial disparity map was generated by automated area-based or feature-based stereo matching. Refinement results on complex urban scenes containing various man-made and natural features are presented, and the improvements due to monocular fusion with a set of different region-based image segmentations are demonstrated.<>
{"title":"Refinement of disparity estimates through the fusion of monocular image segmentations","authors":"D. McKeown, F. Perlant","doi":"10.1109/CVPR.1992.223146","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223146","url":null,"abstract":"The authors examine how estimates of three-dimensional scene structure, as encoded in a scene disparity map, can be improved by the analysis of the original monocular imagery. They describe the utilization of surface illumination information provided by the segmentation of the monocular image into fine surface patches of nearly homogeneous intensity to remove mismatches generated during stereo matching. These patches are used to guide a statistical analysis of the disparity map based on the assumption that such patches correspond closely with physical surfaces in the scene. Such a technique is quite independent of whether the initial disparity map was generated by automated area-based or feature-based stereo matching. Refinement results on complex urban scenes containing various man-made and natural features are presented, and the improvements due to monocular fusion with a set of different region-based image segmentations are demonstrated.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"452 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":"126998629","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.1992.223166
M. Soucy, D. Laurendeau
A multiresolution surface modeling technique is presented. Several registered range views obtained from different viewpoints are first integrated into a nonredundant surface triangulation. The integration technique is based on the reparameterization of the canonic subsets of the Venn diagram of the set of views. The resulting triangulation is then input to a sequential optimization process that computes different levels of resolution of the surfaces of interest.<>
{"title":"Multi-resolution surface modeling from multiple range views","authors":"M. Soucy, D. Laurendeau","doi":"10.1109/CVPR.1992.223166","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223166","url":null,"abstract":"A multiresolution surface modeling technique is presented. Several registered range views obtained from different viewpoints are first integrated into a nonredundant surface triangulation. The integration technique is based on the reparameterization of the canonic subsets of the Venn diagram of the set of views. The resulting triangulation is then input to a sequential optimization process that computes different levels of resolution of the surfaces of interest.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"3 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":"122018671","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.1992.223156
H. Sawhney, A. Hanson
Potential obstacles in the path of a mobile robot that can often be characterized as shallow (i.e., their extent in depth is small compared to their distance from the camera) are considered. The constraint of affine trackability is applied to automatic identification and 3-D reconstruction of shallow structures in realistic scenes. It is shown how this approach can handle independent object motion, occlusion, and motion discontinuity. Although the reconstructed structure is only a frontal plane approximation to the corresponding real structure, the robustness of depth of the approximation might be useful for obstacle avoidance, where the exact shape of an object may not be of consequence so long as collisions with it can be avoided.<>
{"title":"Affine trackability aids obstacle detection","authors":"H. Sawhney, A. Hanson","doi":"10.1109/CVPR.1992.223156","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223156","url":null,"abstract":"Potential obstacles in the path of a mobile robot that can often be characterized as shallow (i.e., their extent in depth is small compared to their distance from the camera) are considered. The constraint of affine trackability is applied to automatic identification and 3-D reconstruction of shallow structures in realistic scenes. It is shown how this approach can handle independent object motion, occlusion, and motion discontinuity. Although the reconstructed structure is only a frontal plane approximation to the corresponding real structure, the robustness of depth of the approximation might be useful for obstacle avoidance, where the exact shape of an object may not be of consequence so long as collisions with it can be avoided.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"43 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":"125923467","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.1992.223239
A. K. Chhabra, T. A. Grogan
T. Simchony et al. (1990) proposed a semidirect method for computing area-based optical flow, based on the iterative application of a direct Poisson solver. This method is restricted to Dirichlet boundary conditions, i.e. it is applicable only when velocity vectors at the boundary of the domain are known a priori. It is shown, both experimentally and through analysis, that the semidirect method converges only for a very high degree of smoothness. At such levels of smoothness, the solution is obtained merely by filling in the known boundary values; the data from the image is almost totally ignored. It is concluded that the semidirect method is not suited for the computation of area-based optical flow.<>
T. Simchony等人(1990)基于直接泊松求解器的迭代应用，提出了一种计算基于区域的光流的半直接方法。该方法仅适用于Dirichlet边界条件，即仅当域边界处的速度矢量先验已知时才适用。实验和分析表明，半直接方法只在非常高的平滑度下收敛。在这样的平滑水平上，只需填入已知的边界值即可得到解;图像中的数据几乎完全被忽略。结果表明，半直接法不适合计算基于面积的光流
{"title":"On Poisson solvers and semi-direct methods for computing area based optical flow","authors":"A. K. Chhabra, T. A. Grogan","doi":"10.1109/CVPR.1992.223239","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223239","url":null,"abstract":"T. Simchony et al. (1990) proposed a semidirect method for computing area-based optical flow, based on the iterative application of a direct Poisson solver. This method is restricted to Dirichlet boundary conditions, i.e. it is applicable only when velocity vectors at the boundary of the domain are known a priori. It is shown, both experimentally and through analysis, that the semidirect method converges only for a very high degree of smoothness. At such levels of smoothness, the solution is obtained merely by filling in the known boundary values; the data from the image is almost totally ignored. It is concluded that the semidirect method is not suited for the computation of area-based optical flow.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"24 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":"126732826","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.1992.223230
M. Dhome, R. Glachet, J. Lapresté
An algorithm for recovering the scaling function of a straight homogeneous generalized cylinder (SHGC) from an image contour is presented. Both location and reference cross section are supposed known. Perspective view assumption and geometric properties of SHGCs are used to derive the method. No additional constraints have been imposed on the object shape. The method has been tested on synthetic image, with promising results.<>
{"title":"Recovering the scaling function of a SHGC from a single perspective view","authors":"M. Dhome, R. Glachet, J. Lapresté","doi":"10.1109/CVPR.1992.223230","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223230","url":null,"abstract":"An algorithm for recovering the scaling function of a straight homogeneous generalized cylinder (SHGC) from an image contour is presented. Both location and reference cross section are supposed known. Perspective view assumption and geometric properties of SHGCs are used to derive the method. No additional constraints have been imposed on the object shape. The method has been tested on synthetic image, with promising results.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"30 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":"121664700","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.1992.223203
Anil K. Jain, Sushil K. Bhattacharjee, Yao Chen
A multichannel filtering-based texture segmentation method is applied to a variety of document image processing problems: text-graphics separation, address-block location, and bar code localization. In each of these segmentation problems, the text context or bar code in the image is considered to define a unique texture. Thus, all three document analysis problems can be posed as texture segmentation problems. Two-dimensional Gabor filters are used to compute texture features. Both supervised and unsupervised methods are used to identify regions of text or bar code in the document images. The performance of the segmentation and classification scheme for a variety of document images demonstrates the generality and effectiveness of the approach.<>
{"title":"On texture in document images","authors":"Anil K. Jain, Sushil K. Bhattacharjee, Yao Chen","doi":"10.1109/CVPR.1992.223203","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223203","url":null,"abstract":"A multichannel filtering-based texture segmentation method is applied to a variety of document image processing problems: text-graphics separation, address-block location, and bar code localization. In each of these segmentation problems, the text context or bar code in the image is considered to define a unique texture. Thus, all three document analysis problems can be posed as texture segmentation problems. Two-dimensional Gabor filters are used to compute texture features. Both supervised and unsupervised methods are used to identify regions of text or bar code in the document images. The performance of the segmentation and classification scheme for a variety of document images demonstrates the generality and effectiveness of the approach.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"43 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":"130519459","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.1992.223276
Sukhan Lee, J. C. Pan
An approach for tracing, representation, and recognition of a handwritten numeral in an offline environment is presented. A 2D spatial representation of a numeral is first transformed into a 3D spatiotemporal representation by identifying the tracing sequence based on a set of heuristic rules acting as transformation operators. Given the dynamic information of the tracing sequence, a multiresolution critical-point segmentation method is proposed to extract local feature points, at varying degrees of scale and coarseness. A neural network architecture, the hierarchically self-organizing learning (HSOL) network (S. Lee, J.C. Pan, 1989), especially for handwritten numeral recognition, is presented. Experimental results based on a bidirectional HSOL network indicated that the method is robust in terms of variations, deformations, and corruption, achieving about 99% recognition rate for the test patterns.<>
{"title":"Handwritten numeral recognition based on hierarchically self-organizing learning networks with spatio-temporal pattern representation","authors":"Sukhan Lee, J. C. Pan","doi":"10.1109/CVPR.1992.223276","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223276","url":null,"abstract":"An approach for tracing, representation, and recognition of a handwritten numeral in an offline environment is presented. A 2D spatial representation of a numeral is first transformed into a 3D spatiotemporal representation by identifying the tracing sequence based on a set of heuristic rules acting as transformation operators. Given the dynamic information of the tracing sequence, a multiresolution critical-point segmentation method is proposed to extract local feature points, at varying degrees of scale and coarseness. A neural network architecture, the hierarchically self-organizing learning (HSOL) network (S. Lee, J.C. Pan, 1989), especially for handwritten numeral recognition, is presented. Experimental results based on a bidirectional HSOL network indicated that the method is robust in terms of variations, deformations, and corruption, achieving about 99% recognition rate for the test patterns.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"8 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":"114935325","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.1992.223206
Li Wang, T. Pavlidis
An approach to feature extraction that eliminates binarization by extracting features directly from gray scale images is presented. It not only allows the processing of poor quality input (e.g., low contrast, dirty images), but also offers the possibility of significantly lower resolution for digitization.<>
{"title":"A geometric approach to machine-printed character recognition","authors":"Li Wang, T. Pavlidis","doi":"10.1109/CVPR.1992.223206","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223206","url":null,"abstract":"An approach to feature extraction that eliminates binarization by extracting features directly from gray scale images is presented. It not only allows the processing of poor quality input (e.g., low contrast, dirty images), but also offers the possibility of significantly lower resolution for digitization.<<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":"129584827","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.1992.223120
G. Roth, M. Levine
A genetic algorithm based on a minimal subset representation of a geometric primitive is used to perform primitive extraction. A genetic algorithm is an optimization method that uses the metaphor of evolution, and a minimal subset is the smallest number of points necessary to define a unique instance of a geometric primitive. The approach is capable of extracting more complex primitives than the Hough transform. While similar to a hierarchical merging algorithm, it does not suffer from the problem of premature commitment.<>
{"title":"Geometric primitive extraction using a genetic algorithm","authors":"G. Roth, M. Levine","doi":"10.1109/CVPR.1992.223120","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223120","url":null,"abstract":"A genetic algorithm based on a minimal subset representation of a geometric primitive is used to perform primitive extraction. A genetic algorithm is an optimization method that uses the metaphor of evolution, and a minimal subset is the smallest number of points necessary to define a unique instance of a geometric primitive. The approach is capable of extracting more complex primitives than the Hough transform. While similar to a hierarchical merging algorithm, it does not suffer from the problem of premature commitment.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"24 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131658005","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.1992.223183
R. Collins
A priori knowledge of the relative positions of four or more coplanar points or lines is used to derive the positions of other points and lines on the same plane in a manner invariant to camera location and intrinsic camera parameters. A framework for data fusion in the projective plane is presented to merge the position estimates of coplanar points and lines derived in this way.<>
{"title":"Single plane model extension using projective transformations and data fusion","authors":"R. Collins","doi":"10.1109/CVPR.1992.223183","DOIUrl":"https://doi.org/10.1109/CVPR.1992.223183","url":null,"abstract":"A priori knowledge of the relative positions of four or more coplanar points or lines is used to derive the positions of other points and lines on the same plane in a manner invariant to camera location and intrinsic camera parameters. A framework for data fusion in the projective plane is presented to merge the position estimates of coplanar points and lines derived in this way.<<ETX>>","PeriodicalId":325476,"journal":{"name":"Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"797 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":"133486964","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：