{"title":"Estimation of time-to-collision maps from first order motion models and normal flows","authors":"François G. Meyer, P. Bouthemy","doi":"10.1109/ICPR.1992.201512","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201512","url":null,"abstract":"Addresses the problem of estimating time-to-collision maps involving all the objects in relative motion with respect to the camera. The approach only takes into account normal flows. Moreover the authors prove that first-order visual motion models are sufficient to obtain time-to-collision. Experiments have been carried out on real images to validate the performance of the method.<<ETX>>","PeriodicalId":410961,"journal":{"name":"[1992] Proceedings. 11th IAPR International Conference on Pattern Recognition","volume":"27 1 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":"116710860","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":"An object oriented representational system for image features and their relations","authors":"J. Plomp","doi":"10.1109/ICPR.1992.201613","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201613","url":null,"abstract":"The objective of this research is the development of a general purpose image understanding system. The object-oriented libraries described in this paper contain object definitions of image features, operators to deal with these features, and a framework for storage. Upon creation of an image feature, links are established from this feature to source features and upon request other links may be established to otherwise related features. Referring to single features or groups of features may be done by a property selection rule. The first aim is to find and store perceptual groupings found in an image by bottom-up processing for later use by a top-down image understanding system.<<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":"127743706","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":"Learning 3D object descriptions from a set of stereo vision observations","authors":"J. J. D. Jong, J. Buurman","doi":"10.1109/ICPR.1992.201673","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201673","url":null,"abstract":"Describes a system for learning models of polyhedral objects. The system does not require exact knowledge about poses, instead only some course requirements are needed. The system obtains a 3D wireframe model of the object together with the statistical data. This is illustrated with an example.<<ETX>>","PeriodicalId":410961,"journal":{"name":"[1992] Proceedings. 11th IAPR International Conference on Pattern Recognition","volume":"116 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":"128030150","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":"Understanding three-view drawings based on heuristics","authors":"Chang-Hun Kim, M. Inoue, S. Nishihara","doi":"10.1109/ICPR.1992.201612","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201612","url":null,"abstract":"A system that reconstructs 3D models from hand-drawn three-view drawings represented by binary images is described. The authors lay main stress on the description of a heuristics directed reconstruction algorithm. The proposed algorithm performs a combinatorial search based on the face decision strategy along with two heuristics aiming at simulating the human's understanding way of interpretation. One is for finding a good sequence of search nodes, and the other for finding more natural scenes earlier than unusual ones.<<ETX>>","PeriodicalId":410961,"journal":{"name":"[1992] Proceedings. 11th IAPR International Conference on Pattern Recognition","volume":"20 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":"134436404","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 model of human estimation of 3D shape from shading information using zero crossings","authors":"S. Kondo, K. Atsuta","doi":"10.1109/ICPR.1992.201618","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201618","url":null,"abstract":"Proposes a model of human estimation of 3D shape from a single image using estimation theory. Firstly it is seen, using an example, that most human subjects estimate a 3D shape from the single image which is physically contradictory. Secondly it is seen that in order to explain the human false estimate it is necessary that in human estimation a given image is divided into several regions and different illuminant directions are used depending on the regions. Thirdly a model of human estimation of 3D shape and an algorithm of 3D shape estimation following the model are proposed.<<ETX>>","PeriodicalId":410961,"journal":{"name":"[1992] Proceedings. 11th IAPR International Conference on Pattern Recognition","volume":"307 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":"133889770","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":"Architecture of the knowledge based configuration system for image analysis 'CONNY'","authors":"C. Liedtke, Arnold Blömer","doi":"10.1109/ICPR.1992.201579","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201579","url":null,"abstract":"For successful image analysis it is necessary that the image analysis system be configured to meet the requirements of the specific task and the specific data material. This includes the selection of the operators and the adaptation of the free parameters. The system CONNY has been developed which performs this configuration process automatically based on a user-specified task definition and the knowledge of an image analysis expert. The expert's knowledge has been assessed, stored and used by employing different paradigms of explicit knowledge representation.<<ETX>>","PeriodicalId":410961,"journal":{"name":"[1992] Proceedings. 11th IAPR International Conference on Pattern Recognition","volume":"49 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1992-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114032887","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":"An expert module to recognize injured rat footprint images","authors":"Jérôme Benmouffek, Y. Belaïd, A. Belaïd","doi":"10.1109/ICPR.1992.201628","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201628","url":null,"abstract":"Many medical research centers need to analyse rat footprint images in order to evaluate some nerve lesions. The authors present a system, called RER, which is able to analyse rat footprint images and detect fingers automatically. This system is composed of a low level that transforms images into structured information and a high level to recognize fingers in the footprint frames. Techniques employed by the high level to select fingers in a set of marks including noise and fingerprints are presented.<<ETX>>","PeriodicalId":410961,"journal":{"name":"[1992] Proceedings. 11th IAPR International Conference on Pattern Recognition","volume":"94 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":"115123308","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 shape recognition by active vision-without camera velocity information","authors":"K. Kinoshita, K. Deguchi","doi":"10.1109/ICPR.1992.201535","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201535","url":null,"abstract":"Proposes a new method of active vision which recognizes the 3-D shape of objects without knowing camera motion parameters. The motion parameters are calculated from the optical flows and the depth of object points whose 3-D shape is already known. Then, using these calculated motion parameters and the optical flows, the 3-D position of unknown points are reconstructed, which, in turn, will be used as the known points in the next frame of image. These processes are iterated for a sequence of images to recognize the 3-D scene. In this method, the effects of quantization errors are overcome by two approaches. The errors of camera motion parameters are compensated by using a large number of points to calculate them. Then, the Kalman filtering method is applied to the sequence of images to reduce the 3-D position errors of each unknown point.<<ETX>>","PeriodicalId":410961,"journal":{"name":"[1992] Proceedings. 11th IAPR International Conference on Pattern Recognition","volume":"8 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":"114187182","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}
G. Cortelazzo, Giovanni Deretta, G. Mian, P. Zamperoni
{"title":"On the application of geometrical form description techniques to automatic key-sections recognition","authors":"G. Cortelazzo, Giovanni Deretta, G. Mian, P. Zamperoni","doi":"10.1109/ICPR.1992.201590","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201590","url":null,"abstract":"Automatic key-section recognition is approached by a two-step procedure. The first step is a screening based on arc/straight-segment classification, which associates to each key section a morphological pattern. The second step measures the string distances by means of nonlinear elastic matching among the key-sections possessing the same morphological description. Arc/straight-segment classification, a typical geometrical form description problem, is studied by two techniques, one based on Euclidean geometry notions and the other based on discrete geometry. The results achieved by the second technique appear superior. The performance of the recognition procedure on key-section databases of practical significance are very satisfactory.<<ETX>>","PeriodicalId":410961,"journal":{"name":"[1992] Proceedings. 11th IAPR International Conference on Pattern Recognition","volume":"157 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":"114650077","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":"Object detection in outdoor scenes by disparity map segmentation","authors":"R. Ma, M. Thonnat","doi":"10.1109/ICPR.1992.201620","DOIUrl":"https://doi.org/10.1109/ICPR.1992.201620","url":null,"abstract":"An approach for scene segmentation based on disparity map is proposed. The basic idea is to group features close in space into objects. The advantages of such an approach are that the search takes place in 2D space, instead of 3D space and that the uncertainty can be taken into account easily and uniformly. The authors show how to express a 3D proximity criterion in terms of disparity and how the problem of uncertainty is coped with efficiently. The result on a traffic sequence is presented.<<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":"124676400","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}