{"title":"Surface reconstruction directly from binocular stereo images by multiscale-multistage regularization","authors":"N. Yokoya","doi":"10.1109/ICPR.1992.201643","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201643","url":null,"abstract":"This paper describes a method of surface reconstruction from stereo images. The problem addressed is formulated as the minimization of an energy functional that integrates a similarity term and a smoothness term. The minimization reduces to solving a system of nonlinear equations. A disparity map is obtained by solving the system of equations through scale hierarchy. The proposed method can compute a dense disparity map directly from stereo images preserving discontinuities.<<ETX>>","PeriodicalId":410961,"journal":{"name":"[1992] Proceedings. 11th IAPR International Conference on Pattern Recognition","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125855710","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":"Three-dimensional symmetry measurement of medical entities","authors":"Predrag Minovic, S. Ishikawa, K. Kato","doi":"10.1109/ICPR.1992.201599","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201599","url":null,"abstract":"Describes a technique for symmetry detection and measurement of 3D medical entities based on an algorithm for general 3D symmetry identification. The technique can recognize a number of symmetries including bilateral, central, and rotational; and it expresses them in terms of a symmetry measure called 'the symmetry degree'. It is based on traversals of the octree obtained by the principal axis transform of the input octree, therefore it requires that the medical entity be represented by its octree. This may be the only technique for 3D symmetry measurement that can deal with arbitrary medical entities. The procedure is demonstrated on two skull models reconstructed from axial CT scans but it is applicable to entity models obtained by other techniques as well. It is also shown how to use this procedure for invariant alignment of different images of the same entity for their comparative analysis.<<ETX>>","PeriodicalId":410961,"journal":{"name":"[1992] Proceedings. 11th IAPR International Conference on Pattern Recognition","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124330227","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":"The dominant views of solid objects","authors":"S. Chen, H. Freeman","doi":"10.1109/ICPR.1992.201569","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201569","url":null,"abstract":"Introduces the concept of the dominant views (DVs) of a solid object as those views that, in a sense to be defined, contain maximal visual information about the solid. The set of dominant views of a solid object is a minimal subset of the object's characteristic views (CVs) that represents all of the object's surfaces in the most general manner. The authors present a method for computing the dominant views of a solid object from its characteristic-view set and illustrate the method on some sample objects. By providing a basis for multi-level indexing of an object-model database, the DV concept should prove useful in object recognition and pose determination. A scheme for multi-level indexing is considered essential for solving the problem of inexact matching in multiview model-based recognition.<<ETX>>","PeriodicalId":410961,"journal":{"name":"[1992] Proceedings. 11th IAPR International Conference on Pattern Recognition","volume":"777 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123284003","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":"Direct estimation of structure from nonlinear motion by voting algorithm without tracking and matching","authors":"T. Hamano, T. Yasuno, K. Ishii","doi":"10.1109/ICPR.1992.201610","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201610","url":null,"abstract":"Presents a robust approach to estimate structure from an image sequence taken by a moving camera. This approach is based on a Hough-type weighted voting algorithm and has the following features: (1) needs no feature tracking and no image-to-image matching; and (2) allows arbitrary nonlinear motion of camera. Experimental results using actual complex scenes are presented.<<ETX>>","PeriodicalId":410961,"journal":{"name":"[1992] Proceedings. 11th IAPR International Conference on Pattern Recognition","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131817863","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":"Contribution to the matching problem in stereovision","authors":"D. Maravall, E. Fernandez","doi":"10.1109/ICPR.1992.201588","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201588","url":null,"abstract":"A matching algorithm for stereo digital images, in which speed of computation is the main objective, is briefly expounded. The generic characteristics of a hierarchical algorithm for the matching of stereo pairs operating in quite general conditions, including scenes with overlapped objects, is then described.<<ETX>>","PeriodicalId":410961,"journal":{"name":"[1992] Proceedings. 11th IAPR International Conference on Pattern Recognition","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130609597","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 multi-specialist architecture for sensor fusion in remote sensing","authors":"V. Clément, G. Giraudon, Stéphane Houzelle","doi":"10.1109/ICPR.1992.201541","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201541","url":null,"abstract":"Presents a scene interpretation architecture in the context of multi-sensor fusion. This architecture is based on blackboard and multi-specialist concepts, and offers knowledge representation capabilities to express knowledge about an application in an explicit way. Knowledge description includes the characteristics of the sensors, and a semantic object description independent of the sensor characteristics. The detection strategy is based on the fundamental notion of spatial context linking the objects of the scene, and the notion of salient object. An interpretation is a semantic model of the real observed scene, including object location, object characteristics and relations between objects. This architecture has a highly modular structure allowing easy incorporation of new knowledge, and new specialists. To demonstrate the reliability of the approach, an application of SAR/SPOT data fusion developed with this architecture is briefly presented, and the results of an interpretation session are shown.<<ETX>>","PeriodicalId":410961,"journal":{"name":"[1992] Proceedings. 11th IAPR International Conference on Pattern Recognition","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116617659","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":"3-D object representation in range images using geons","authors":"Quang-Loc Nguyen, M. Levine","doi":"10.1109/ICPR.1992.201529","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201529","url":null,"abstract":"Proposes an approach for representing an object by its constituent parts and their spatial connections based on a set of primitive volumes called geons. The authors utilize the edge-junction graph of an object range image as input, then decompose this graph into different subgraphs which correspond to the constituent parts of the object. For each part, edge characteristics guide one to an inference regarding the corresponding geon shape. Also, the spatial connections among these parts can be deduced from the concave edges and T-junctions. Experimental results with a laser rangefinder are presented.<<ETX>>","PeriodicalId":410961,"journal":{"name":"[1992] Proceedings. 11th IAPR International Conference on Pattern Recognition","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121035894","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 robust image processing approach used to ALV road following","authors":"W. Gu, Hui Liu, Hui Wang","doi":"10.1109/ICPR.1992.201651","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201651","url":null,"abstract":"A robust image processing approach used for ALV (autonomous land vehicle) road following is presented. The approach can cope with illumination variation, bad road surface condition such as shadows, defects, dirt and water stains. And it is effective for images of multi-branched road intersections. The approach consists of key techniques: color band automatic selection; adaptive road area segmentation; binary image post-processing and knowledge-based road trend line fitting. The approach is easy to implement in real time because its processing stages can be arranged into a pipeline. A set of experimental results is also presented.<<ETX>>","PeriodicalId":410961,"journal":{"name":"[1992] Proceedings. 11th IAPR International Conference on Pattern Recognition","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129917934","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":"Constrained implicit function fitting","authors":"G. Taubin, R. Bolle, B. Vemuri","doi":"10.1109/ICPR.1992.201555","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201555","url":null,"abstract":"Describes techniques for stabilizing the implicit function fitting process. The key drawback of implicit function fitting methods described in literature thus far has been the stability with respect to outliners in the data. In this paper methods for stabilizing the implicit function fitting using additional constraints in the form of surface (curve) normals are described. These constraints eliminate the problem of sensitivity of the implicit function fitting method to outliners in the data. The authors demonstrate that in certain cases the fitting process can be reduced to a generalized eigenvalue problem that can be efficiently solved by standard numerical procedures. Preliminary experimental results with 2D curves consisting of point location and curve normal constraints as data are encouraging.<<ETX>>","PeriodicalId":410961,"journal":{"name":"[1992] Proceedings. 11th IAPR International Conference on Pattern Recognition","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132960302","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":"Edge length ratios: an affine invariant shape representation for recognition with occlusions","authors":"T. Glauser, H. Bunke","doi":"10.1109/ICPR.1992.201594","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201594","url":null,"abstract":"The authors propose a set of local shape descriptors for polygons based on edge length ratios. These descriptors are invariant under any affine transformation, i.e. translation, scaling, rotation and projection from 3D to any 2D plane. Furthermore, they are complete in the sense that they allow the reconstruction of any polygon in 3D space given at least three consecutive vertices. The authors then consider the recognition of 2D polygonal objects under any affine transformation and in the presence of occlusion. they introduce a recognition procedure that is based on the matching of edge length ratios, using a simplified version of the standard dynamic programming procedure commonly employed for string matching.<<ETX>>","PeriodicalId":410961,"journal":{"name":"[1992] Proceedings. 11th IAPR International Conference on Pattern Recognition","volume":"351 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132077833","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}