{"title":"Qualitatively describing objects using spatial prepositions","authors":"A. Abella, J. Kender","doi":"10.1109/WQV.1993.262952","DOIUrl":"https://doi.org/10.1109/WQV.1993.262952","url":null,"abstract":"The paper presents a framework for a system that describes objects in a qualitative fashion. A subset of spatial prepositions is chosen and an appropriate quantification is applied to each of them that capture their inherent qualitative properties. The quantifications use such object attributes as area, centers, and elongation properties. The familiar zeroth, first, and second order moments are used to characterize these attributes. The paper details how and why the particular quantifications were chosen. Since spatial prepositions are by their nature rather vague and dependent on context a technique for fuzzifying the definition of the spatial preposition is explained. Finally an example task is chosen to illustrate the appropriateness of the quantification techniques.<<ETX>>","PeriodicalId":309941,"journal":{"name":"[1993] Proceedings IEEE Workshop on Qualitative Vision","volume":"243 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114580298","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 hierarchy of invariant representations of 3D shape","authors":"D. Weinshall","doi":"10.1109/WQV.1993.262945","DOIUrl":"https://doi.org/10.1109/WQV.1993.262945","url":null,"abstract":"The representation of geometrical 3D shape is discussed in this paper. A hierarchy of representations, which are invariant under weak perspective to either rigid or affine 3D transformations is described. These representations can be computed efficiently from a sequence of images with a linear and incremental algorithm. This hierarchy provides the means for adding a controlled amount of quantitative information to a symbolic representation. It also provides a library of representations, which may be used for different tasks (or purposes).<<ETX>>","PeriodicalId":309941,"journal":{"name":"[1993] Proceedings IEEE Workshop on Qualitative Vision","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122716425","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":"Motion constraint patterns","authors":"Cornelia Fermuller","doi":"10.1109/WQV.1993.262942","DOIUrl":"https://doi.org/10.1109/WQV.1993.262942","url":null,"abstract":"The problem of egomotion recovery has been treated by using as input local image motion, with the published algorithms utilizing the geometric constraint relating 2-D local image motion (optical flow, correspondence, derivatives of the image flow) to 3-D motion and structure. Since it has proved very difficult to achieve accurate input (local image motion), a lot of effort has been devoted to the development of robust techniques. A new approach to the problem of egomotion estimation is taken, based on constraints of a global nature. It is proved that local normal flow measurements form global patterns in the image plane. The position of these patterns is related to the three dimensional motion parameters. By locating some of these patterns, which depend only on subsets of the motion parameters, through a simple search technique, the 3-D motion parameters can be found. The proposed algorithmic procedure is very robust, since it is not affected by small perturbations in the normal flow measurements. As a matter of fact, since only the sign of the normal flow measurement is employed, the direction of translation and the axis of rotation can be estimated with up to 100% error in the image measurements.<<ETX>>","PeriodicalId":309941,"journal":{"name":"[1993] Proceedings IEEE Workshop on Qualitative Vision","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125603401","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":"Finite resolution aspect graphs of polyhedral objects","authors":"I. Shimshoni, J. Ponce","doi":"10.1109/WQV.1993.262941","DOIUrl":"https://doi.org/10.1109/WQV.1993.262941","url":null,"abstract":"The authors address the problem of computing the exact aspect graph of a polyhedral object observed by an orthographic camera with finite resolution, such that two image points separated by a distance smaller than a preset threshold cannot be resolved. Under this projection model, views that would be different under normal orthographic projection may become equivalent, while 'accidental' views may occur over finite areas of the view space. They present a catalogue of visual events for polyhedral objects and give an algorithm for computing the aspect graph and enumerating all qualitatively different aspects. The algorithm has been fully implemented and results are presented.<<ETX>>","PeriodicalId":309941,"journal":{"name":"[1993] Proceedings IEEE Workshop on Qualitative Vision","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126232662","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 geometric invariant for visual recognition and 3D reconstruction from two perspective/orthographic views","authors":"A. Shashua","doi":"10.1109/WQV.1993.262944","DOIUrl":"https://doi.org/10.1109/WQV.1993.262944","url":null,"abstract":"The author addresses the problem of reconstructing 3D space in a projective framework from two views, and the problem of artificially generating novel views of the scene from two given views. He shows that with the correspondences coming from four non-coplanar points in the scene and the corresponding epipoles, one can define and reconstruct (using simple linear methods) a projective invariant, referred to as projective depth, that can be used later to reconstruct the projective or affine structure of the scene, or directly to generate novel views of the scene. The derivation has the advantage that the viewing transformation matrix need not be recovered in the course of computations (i.e., he computes structure without motion).<<ETX>>","PeriodicalId":309941,"journal":{"name":"[1993] Proceedings IEEE Workshop on Qualitative Vision","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133691877","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":"Studying control of selective perception using T-world and TEA","authors":"R.D. Rimey","doi":"10.1109/WQV.1993.262950","DOIUrl":"https://doi.org/10.1109/WQV.1993.262950","url":null,"abstract":"The author hypothesizes that selective perception allows more accurate solutions to visual tasks to be found in less wall-clock time than non-selective techniques. The best way to assess the practical truth of this hypothesis is by studying, designing and building complete vision systems-the issues are fundamentally systems issues. On the other hand, special-case systems are not convincing: he presents the T-world problem as an abstraction of an interesting class of real-world vision problems. T-world has enough structure to support basic study of fundamental tradeoffs inherent in selective computer perception. The complete system is called TEA-1: it is a purposive and sufficing vision system that solves a version of the T-world problem. TEA-1 is a fully implemented system, and extensive experiments in the laboratory and simulation have explored the key factors that make the selective perception approach appealing, analyzing how each factor affects the overall performance of TEA-1 when solving a set of automatically generated (in simulation) T-world domains and tasks.<<ETX>>","PeriodicalId":309941,"journal":{"name":"[1993] Proceedings IEEE Workshop on Qualitative Vision","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116516564","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":"Dynamic shading, motion parallax and qualitative shape","authors":"S. Waldon, C. Dyer","doi":"10.1109/WQV.1993.262949","DOIUrl":"https://doi.org/10.1109/WQV.1993.262949","url":null,"abstract":"The authors address the problem of qualitative shape recovery from moving surfaces. The analysis is unique in that they consider specular interreflections and explore the effects of both motion parallax and changes in shading. To study this situation they define an image flow field called the reflection flow field, which describes the motion of reflection points and the motion of the surface. From a kinematic analysis, they show that the reflection flow is qualitatively different from the motion parallax because it is discontinuous at or near parabolic curves. They also show that when the gradient of the reflected image is strong, gradient-based flow measurement techniques approximate the reflection flow field and not the motion parallax. They conclude that reliable qualitative shape information is generally available only at discontinuities in the image flow field.<<ETX>>","PeriodicalId":309941,"journal":{"name":"[1993] Proceedings IEEE Workshop on Qualitative Vision","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127836916","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":"Motion understanding from qualitative visual dynamics","authors":"E. Shavit, A. Jepson","doi":"10.1109/WQV.1993.262947","DOIUrl":"https://doi.org/10.1109/WQV.1993.262947","url":null,"abstract":"In many situations, motion is naturally grasped as an ordered sequence of poses, expressing stages in a general development. Capturing the underlying dynamics is an important first step for gaining insight and constructing a representation that has expressive power. The authors compute a pose function for a motion that qualitatively characterizes it in terms of dynamics. The study is based in dynamic systems analysis, constructing the function in phase space-a geometric depiction of the observed behaviour. The analysis itself is geometrical, but yields a representation of the visual dynamics. The global component of the pose function is an expression of external forces, and the local component and expression of deformation. The computation is simple, making only few general assumptions. The function captures all the relevant parameters of the motion in the sense that a qualitative simulation of the behavior is made possible, thus, facilitating subsequent reasoning about observed events.<<ETX>>","PeriodicalId":309941,"journal":{"name":"[1993] Proceedings IEEE Workshop on Qualitative Vision","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122880118","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 recognition using steerable filters at multiple scales","authors":"Dana H. Ballard, L. Wixson","doi":"10.1109/WQV.1993.262955","DOIUrl":"https://doi.org/10.1109/WQV.1993.262955","url":null,"abstract":"The identification and location of objects in images is difficult owing to the view variance of geometric features. This problem can be solved by developing view-insensitive descriptions of image points. View-insensitive descriptions are achieved by describing points in terms of the responses of steerable filters at multiple scales. The steerability allows the normalizing of rotations about the view vector. Owing to the use of multiple scales, the vector for each point is, for all practical purposes, unique, and thus can be easily matched to other instances of the point in other images.<<ETX>>","PeriodicalId":309941,"journal":{"name":"[1993] Proceedings IEEE Workshop on Qualitative Vision","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121418519","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":"Using causal scene analysis to direct focus of attention","authors":"L. Birnbaum, M. Brand, P. Cooper","doi":"10.1109/WQV.1993.262953","DOIUrl":"https://doi.org/10.1109/WQV.1993.262953","url":null,"abstract":"Vision should provide an explanation of the scene in terms of a causal semantics-what affects what, and why. For mobile agents, the structural integrity of the immediate environment is a major concern. Thus, an important part of the causal explanation of static scenes is what supports what, or, counterfactually: Why aren't things moving? The authors use simple naive physical knowledge as the basis of a vertically integrated vision system that explains arbitrarily complex stacked block structures. The semantics provides a basis for controlling the application of visual attention, and forms a framework for the explanation that is generated. They show how the program sequentially explores scenes of complex blocks structures, identifies functional substructures such as arches and cantilevers, and develops an explanation of why the whole construction stands and the role of each block in its stability.<<ETX>>","PeriodicalId":309941,"journal":{"name":"[1993] Proceedings IEEE Workshop on Qualitative Vision","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127090484","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}