Computer Vision, Graphics, and Image Processing最新文献

{"title":"Exploiting image-plane data in the interpretation of edge-based binocular disparity","authors":"Tony P. Pridmore ,&nbsp;John E.W. Mayhew,&nbsp;John P. Frisby","doi":"10.1016/0734-189X(90)90121-B","DOIUrl":"10.1016/0734-189X(90)90121-B","url":null,"abstract":"<div><p>We consider the exploitation of 2D, image-plane measurements by the 3D grouping (CONNECT) and contour segmentation/description (GDF) modules of the TINA binocular vision system. The combination of point strings obtained separately by CONNECT from matched and raw edges is discussed and a simple approach to grouping 2 and 3D edges presented. An upgraded GDF is also described. This uses raw edges to guide both segmentation and description. Over-segmentation is thus reduced and a greater proportion of the connected edges assigned to reliable, 3D descriptive elements. Should binocular correspondence fail for any reason, default, two-dimensional descriptions are produced automatically.</p></div>","PeriodicalId":100319,"journal":{"name":"Computer Vision, Graphics, and Image Processing","volume":"52 1","pages":"Pages 1-25"},"PeriodicalIF":0.0,"publicationDate":"1990-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/0734-189X(90)90121-B","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125145353","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}

{"title":"On characterizing ribbons and finding skewed symmetries","authors":"Jean Ponce","doi":"10.1016/0734-189X(90)90129-J","DOIUrl":"https://doi.org/10.1016/0734-189X(90)90129-J","url":null,"abstract":"","PeriodicalId":100319,"journal":{"name":"Computer Vision, Graphics, and Image Processing","volume":"52 1","pages":"Page 143"},"PeriodicalIF":0.0,"publicationDate":"1990-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/0734-189X(90)90129-J","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136556920","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}

{"title":"Hough transform and signal detectin theory performance for images with additive noise","authors":"Douglas J. Hunt,&nbsp;Loren W. Nolte,&nbsp;Amy R. Reibman,&nbsp;W. Howard Ruedger","doi":"10.1016/0734-189X(90)90128-I","DOIUrl":"https://doi.org/10.1016/0734-189X(90)90128-I","url":null,"abstract":"","PeriodicalId":100319,"journal":{"name":"Computer Vision, Graphics, and Image Processing","volume":"52 1","pages":"Page 143"},"PeriodicalIF":0.0,"publicationDate":"1990-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/0734-189X(90)90128-I","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136556923","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}

{"title":"On topology as applied to image analysis","authors":"Gabor T. Herman","doi":"10.1016/0734-189X(90)90133-G","DOIUrl":"https://doi.org/10.1016/0734-189X(90)90133-G","url":null,"abstract":"","PeriodicalId":100319,"journal":{"name":"Computer Vision, Graphics, and Image Processing","volume":"52 1","pages":"Page 144"},"PeriodicalIF":0.0,"publicationDate":"1990-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/0734-189X(90)90133-G","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136556981","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}

{"title":"Simultaneous fitting of several planes to point sets using neural networks","authors":"Behrooz Kamgar-Parsi,&nbsp;Behzad Kamgar-Parsi,&nbsp;Harry Wechsler","doi":"10.1016/0734-189X(90)90130-N","DOIUrl":"https://doi.org/10.1016/0734-189X(90)90130-N","url":null,"abstract":"","PeriodicalId":100319,"journal":{"name":"Computer Vision, Graphics, and Image Processing","volume":"52 1","pages":"Page 143"},"PeriodicalIF":0.0,"publicationDate":"1990-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/0734-189X(90)90130-N","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136556921","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}

{"title":"A hierarchical approach to line extraction based on the Hough transform","authors":"John Princen,&nbsp;John Illingworth,&nbsp;Josef Kittler","doi":"10.1016/0734-189X(90)90123-D","DOIUrl":"10.1016/0734-189X(90)90123-D","url":null,"abstract":"<div><p>An efficient method for finding straight lines in edge maps is described. The algorithm is based on a pyramid structure with each layer in the pyramid splitting the complete image into a number of subimages. At the bottom level of the pyramid short line segments are detected by applying a Hough transform to small subimages. The algorithm proceeds, bottom up, from this low level description by grouping line segments within local neighborhoods into longer lines. Line segments which have local support propagate up the hierarchy and take part in grouping at higher levels. The length of a line determines approximately the level in the pyramid to which it propagates. Hence we obtain a hierarchical description of the line segments in a scene which can be useful in matching. The algorithm has a number of advantages over previously proposed hierarchical methods for the detection of straight lines. It is quite efficient and has a particularly attractive architecture which is suitable for parallel implementation.</p></div>","PeriodicalId":100319,"journal":{"name":"Computer Vision, Graphics, and Image Processing","volume":"52 1","pages":"Pages 57-77"},"PeriodicalIF":0.0,"publicationDate":"1990-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/0734-189X(90)90123-D","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122989142","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}

{"title":"3D symmetry-curvature duality theorems","authors":"A. Yuille,&nbsp;M. Leyton","doi":"10.1016/0734-189X(90)90126-G","DOIUrl":"10.1016/0734-189X(90)90126-G","url":null,"abstract":"<div><p>We prove theorems showing a duality between the surface curvatures of three-dimensional objects and the existence of symmetry axes. More precisely, we prove that, given a surface, for each maximum or minimum of the principle curvature along a line of curvature, there is a symmetry axis terminating at this point. Moreover, such points are generically the only points at which these axes can terminate. These theorems generalize results obtained by Leyton for two-dimensional objects.</p></div>","PeriodicalId":100319,"journal":{"name":"Computer Vision, Graphics, and Image Processing","volume":"52 1","pages":"Pages 124-140"},"PeriodicalIF":0.0,"publicationDate":"1990-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/0734-189X(90)90126-G","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131266555","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}

{"title":"Pyramidal algorithms for iconic indexing","authors":"Genoveffa Tortora,&nbsp;Gennaro Costagliola,&nbsp;Timothy Arndt,&nbsp;Shi-Kuo Chang","doi":"10.1016/0734-189X(90)90122-C","DOIUrl":"https://doi.org/10.1016/0734-189X(90)90122-C","url":null,"abstract":"","PeriodicalId":100319,"journal":{"name":"Computer Vision, Graphics, and Image Processing","volume":"52 1","pages":"Pages 26-56"},"PeriodicalIF":0.0,"publicationDate":"1990-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/0734-189X(90)90122-C","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91973089","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}

{"title":"Representation and recognition of surface shapes in range images: A differential geometry approach","authors":"Ping Liang ,&nbsp;John S. Todhunter","doi":"10.1016/0734-189X(90)90124-E","DOIUrl":"10.1016/0734-189X(90)90124-E","url":null,"abstract":"<div><p>Theory and matching algorithms are developed for accurate orientation determination and recognition of 3D surface shapes in range images. Two corollaries to the fundamental theory of surface theory are proved. The first corollary proves the invariance of the fundamental coefficients when lines of curvature are used as the intrinsic parameter curves. The second corollary proves that a diffeomorphism which preserves the intrinsic distance along the principal directions, in addition to preserving the eigenvectors and eigenvalues of the shape operator (Weingarten map), is necessarily an isometry. Based on these two corollaries, a set of geometric descriptors which satisfy the uniqueness and invariance requirements are theoretically identified for all classes of surfaces, namely, hyperbolic, elliptic, and developable surfaces. The<em>unit normal and shape descriptors list array</em> (UNSDLA) representation and the corresponding matching algorithm are developed. The UNSDLA is a generalization of the extended Gaussian image (EGI). The EGI has a fundamental limitation; that is, it can only uniquely represent convex shapes. The new representation overcomes this limitation of the EGI and extends the scope of unique representation to all classes of surfaces. Moreover, it still has all the advantages of the EGI. This is achieved by preserving the connectivity of the original data. Connectivity here should include not only the adjacency relation of points or patches on a surface, but also the direction and order in which the points or patches are traversed in a connected path. The importance of the direction and order of connectivity is emphasized. Surface matching can be performed more accurately using the UNSDLA than the EGI. Based on the UNSDLA representations, surfaces can be matched via the Gaussian map by optimization over all possible rotations of a surface shape. The representation and matching algorithm can deal with hyperbolic and elliptic surfaces whose Gaussian maps are not one-to-one. Developable surfaces whose Gaussian maps of lines of curvature with nonzero principal curvature are not one-to-one can also be accommodated. Two theorems on developable surfaces are proved.</p></div>","PeriodicalId":100319,"journal":{"name":"Computer Vision, Graphics, and Image Processing","volume":"52 1","pages":"Pages 78-109"},"PeriodicalIF":0.0,"publicationDate":"1990-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/0734-189X(90)90124-E","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127062986","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}

{"title":"Automated stereophotogrammetry","authors":"Greg Brookshire,&nbsp;Morton Nadler,&nbsp;Choon Lee","doi":"10.1016/0734-189X(90)90131-E","DOIUrl":"https://doi.org/10.1016/0734-189X(90)90131-E","url":null,"abstract":"","PeriodicalId":100319,"journal":{"name":"Computer Vision, Graphics, and Image Processing","volume":"52 1","pages":"Page 144"},"PeriodicalIF":0.0,"publicationDate":"1990-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/0734-189X(90)90131-E","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136556922","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}