{"title":"Deformable kernels for early vision","authors":"P. Perona","doi":"10.1109/CVPR.1991.139691","DOIUrl":"https://doi.org/10.1109/CVPR.1991.139691","url":null,"abstract":"A technique is presented that allows (1) computing the best approximation of a given family using linear combinations of a small number of basis functions; and (2) describing all finite-dimensional families, i.e. the families of filters for which a finite-dimensional representation is possible with no error. The technique is general and can be applied to generating filters in arbitrary dimensions. Experimental results that demonstrate the applicability of the technique to generating multi-orientation multiscale 2-D edge-detection kernels are presented. The implementation issues are also discussed.<<ETX>>","PeriodicalId":367228,"journal":{"name":"Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124197934","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":"Temporal slice analysis of image sequences","authors":"S. Peng","doi":"10.1109/CVPR.1991.139703","DOIUrl":"https://doi.org/10.1109/CVPR.1991.139703","url":null,"abstract":"An early-processing algorithm to extract motion information from closely sampled image sequences is presented. This method outputs dense displacement field, based on the extraction of strips in slices taken from the image volume along the temporal dimension. The extracted strips provide estimates of the velocity component along the slice orientation. Because of the high sampling rate, the motion is assumed to be piecewisely translational. A voting scheme to estimate the position of FOE while extracting strips is proposed. The true velocity can then be calculated. Results on several real image sequences and a promising speedup from the parallel implementation on the Connection Machine are presented.<<ETX>>","PeriodicalId":367228,"journal":{"name":"Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114469738","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 the representation of occluded shapes","authors":"Trevor Darrell, A. Pentland","doi":"10.1109/CVPR.1991.139802","DOIUrl":"https://doi.org/10.1109/CVPR.1991.139802","url":null,"abstract":"Most approaches to simultaneously recovering both model parameters and segmentation have relied on an edge field to represent segmentation. This restriction, and the implementations it leads to, have fundamental limitations in representing occluded stimuli. The authors develop a framework that overcomes these limitations by using multiple layers of explicit support to represent segmentation. Results from an initial implementation demonstrate that this method can segment images containing occluded objects.<<ETX>>","PeriodicalId":367228,"journal":{"name":"Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129864601","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":"Unified computational theory for motion transparency and motion boundaries based on eigenenergy analysis","authors":"M. Shizawa, K. Mase","doi":"10.1109/CVPR.1991.139704","DOIUrl":"https://doi.org/10.1109/CVPR.1991.139704","url":null,"abstract":"A unified theoretical framework for motion transparency and motion boundaries by devising fundamental constraint equations of multiple optical flow is proposed. This framework can handle flow discontinuities at motion boundaries as well as flow multiplicities due to transparency of objects in a unified manner. The constraint equations are formulated by a composition of homogeneously parametrized differential operators on the space-time image. Fitting algorithms for the constraints which result in eigensystem analyses are described. To determine the number of flows, the authors use the margin energy, a measure of goodness of fit which is the difference between the first and the second lower eigenenergy of the eigensystem. They also hypothesize a criterion for multiplicity. The measure and the criterion are derived from the analogy of quantum mechanics. It is demonstrated that the margin energy can determine the transparency and discontinuities of the flow field as regions of more than one flow.<<ETX>>","PeriodicalId":367228,"journal":{"name":"Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128418420","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":"Closed-loop adaptive image segmentation","authors":"B. Bhanu, John C. Ming, Sungkee Lee","doi":"10.1109/CVPR.1991.139805","DOIUrl":"https://doi.org/10.1109/CVPR.1991.139805","url":null,"abstract":"A closed-loop image segmentation system that incorporates a genetic algorithm to adapt the segmentation process to changes in image characteristics caused by variable environmental conditions is presented. The genetic algorithm efficiently searches the hyperspace of segmentation parameter combinations to determine the parameter set which maximizes the segmentation quality criteria. A summary of the experimental results that demonstrates the ability to perform adaptive image segmentation and to learn from experience using a collection of outdoor color imagery is given.<<ETX>>","PeriodicalId":367228,"journal":{"name":"Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128213623","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":"Adaptive estimation of hysteresis thresholds","authors":"E. Hancock, J. Kittler","doi":"10.1109/CVPR.1991.139687","DOIUrl":"https://doi.org/10.1109/CVPR.1991.139687","url":null,"abstract":"It is shown that the hitherto heuristic hysteresis linking idea of J.F. Canny (1986) can be formulated as a Bayesian contextual decision process. This approach draws on an explicit image model which accounts both for the way in which noisy raw-edge information is characterized via filtering operations and how the required edge-connectivity information is quantified. The main advantage is that the previously ad hoc hysteresis thresholds can be related to the parameters of an image model. One feature is the requirement of a third hysteresis threshold based on the consistency of non-edge configurations; this results in an increased capability to reject inconsistent edge candidates. The parameters of the image model can be robustly estimated from image-statistics. The approach endows the hysteresis linking algorithm with adaptive capabilities.<<ETX>>","PeriodicalId":367228,"journal":{"name":"Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127215168","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 contour texture","authors":"B. Subirana-Vilanova","doi":"10.1109/CVPR.1991.139814","DOIUrl":"https://doi.org/10.1109/CVPR.1991.139814","url":null,"abstract":"It is suggested that non-smooth or complex boundaries are processed by the visual system so as to obtain a simple abstract description, called contour texture, which contains much less information than that provided by the location of all points of the contour. A discussion is presented of what the nature of the contour texture of a curve is and its relation with two-dimensional texture, which the author contends should be thought of as a separate concept. Several applications are suggested, and an implemented filter-based scheme is presented.<<ETX>>","PeriodicalId":367228,"journal":{"name":"Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127494183","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":"Recovery of non-rigid motion and structure","authors":"A. Pentland, B. Horowitz","doi":"10.1109/CVPR.1991.139710","DOIUrl":"https://doi.org/10.1109/CVPR.1991.139710","url":null,"abstract":"The elastic properties of real materials provide constraint on the types of non-rigid motion that can occur, and thus allow overconstrained estimates of 3-D non-rigid motion from optical flow data. It is shown that by modeling and simulating the physics of non-rigid motion it is possible to obtain good estimates of both object shape and velocity. Examples using grey-scale and X-ray imagery are presented, including an example of tracking a complex articulated figure.<<ETX>>","PeriodicalId":367228,"journal":{"name":"Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130172667","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":"Planar shape classification using hidden Markov model","authors":"Yang He, A. Kundu","doi":"10.1109/CVPR.1991.139653","DOIUrl":"https://doi.org/10.1109/CVPR.1991.139653","url":null,"abstract":"A planar shape-recognition approach is presented which is based on hidden Markov models and autoregressive parameters. This approach segments closed shapes into segments and explores the characteristic relations between consecutive segments to make classification at a finer level. The algorithm can tolerate much shape contour perturbation, and a moderate amount of occlusion. The overall classification scheme is independent of shape orientation. Excellent recognition results have been reported. A distinct advantage of the approach is that the classifier does not have to be trained all over again when a new class of shapes is added.<<ETX>>","PeriodicalId":367228,"journal":{"name":"Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130174291","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":"Positional estimation of a mobile robot using edge visibility regions","authors":"R. Talluri, J. Aggarwal","doi":"10.1109/CVPR.1991.139795","DOIUrl":"https://doi.org/10.1109/CVPR.1991.139795","url":null,"abstract":"A technique is presented for estimating the position and pose of an autonomous mobile robot navigating in an outdoor, urban environment consisting of polyhedral buildings. The 3-D description of the roof tops of the buildings are assumed to be given as a world model. A discussion is presented of the uses of an intermediate representation of the environment, called the edge visibility regions (EVRs), in the positional estimation process.<<ETX>>","PeriodicalId":367228,"journal":{"name":"Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126408582","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}