{"title":"Optimal motion estimation","authors":"M. Spetsakis, J. Aloimonos","doi":"10.1109/WVM.1989.47114","DOIUrl":"https://doi.org/10.1109/WVM.1989.47114","url":null,"abstract":"The problem of using feature correspondences to recover the structure and 3D motion of a moving object from its successive images is analyzed. They formulate the problem as a quadratic minimization problem with a nonlinear constraint. Then they derive the condition for the solution to be optimal under the assumption of Gaussian noise in the input, in the maximum-likelihood-principle sense. The authors present two efficient ways to approximate it and discuss some inherent limitations of the structure-from-motion problem when two frames are used that should be taken into account in robotics applications that involve dynamic imagery. Finally, it is shown that some of the difficulties inherent in the two-frame approach disappear when redundancy in the data is introduced. This is concluded from experiments using a structure-from-motion algorithm that is based on multiple frames and uses only the rigidity assumption.<<ETX>>","PeriodicalId":342419,"journal":{"name":"[1989] Proceedings. Workshop on Visual Motion","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125469842","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":"Estimation of 3-D motion and structure based on a temporally-oriented approach with the method of regression","authors":"S.-L. Iu, K. Wohn","doi":"10.1109/WVM.1989.47119","DOIUrl":"https://doi.org/10.1109/WVM.1989.47119","url":null,"abstract":"It is argued that the 3-D velocity of a single point up to a scalar factor can be recovered from its 2-D trajectory under the perspective projection. The authors then extend this idea to the recovery of 3-D motion of rigid objects. In both cases measurements are collected through temporal axis first. The analysis is based on the assumption that the 3-D motion of object is smooth so that its 3-D velocity can be approximated as a truncated Taylor series of the predetermined degree. Regression relations between unknown motion parameters and measurements for a single point and rigid body are derived. The method of maximum likelihood is used to estimate the motion. The uniqueness of determining the 3-D motion of the single point is discussed. Experimental results obtained from simulated data and real images are given to illustrate the robustness of this approach.<<ETX>>","PeriodicalId":342419,"journal":{"name":"[1989] Proceedings. Workshop on Visual Motion","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129240246","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 from images: image matching, parameter estimation and intrinsic stability","authors":"J. Weng, T.S. Huang, N. Ahuja","doi":"10.1109/WVM.1989.47130","DOIUrl":"https://doi.org/10.1109/WVM.1989.47130","url":null,"abstract":"Presents an image-matching algorithm that uses multiple attributes associated with a pixel to yield a generally overdetermined system of constraints. taking into account possible structural discontinuities and occlusions. Both top-down and bottom-up data flows are used in a multiresolution computational structure. The matching algorithm computes dense displacement fields and the associated occlusion maps. The motion and structure parameters are estimated through optimal estimation (e.g. maximal likelihood) using the solution of a linear algorithm as an initial guess. To investigate the intrinsic stability of the problem in the presence of noise, a theoretical lower bound on error variance of the estimates, the Cramer-Rao bound, is determined for motion parameters.<<ETX>>","PeriodicalId":342419,"journal":{"name":"[1989] Proceedings. Workshop on Visual Motion","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131463441","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":"Representing motion using chronogeneous transformation","authors":"W. Franzen","doi":"10.1109/WVM.1989.47120","DOIUrl":"https://doi.org/10.1109/WVM.1989.47120","url":null,"abstract":"The author introduces a matrix representation of rigid and nonrigid 3D motion, which generalizes homogeneous transformation. He calls this transformation a chronogeneous transformation. Just as homogeneous transformations allow rigid transformations and projection to be represented in a linear manner, chronogeneous transformations allow an analogous representation for certain classes of continuous motion/structural deformation. The author categorizes these classes of motion. For example, uniform translation of a rigid object that rotates with uniform angular velocity about a fixed axis is one kind of motion that can be represented. It is straightforward to calculate the matrix representation given the underlying motion parameters and vice versa. It is also shown how the position of a point on an object changes as a result of simultaneous uniform chronogeneous camera and objection motion.<<ETX>>","PeriodicalId":342419,"journal":{"name":"[1989] Proceedings. Workshop on Visual Motion","volume":"48 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134355781","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}
C. Koch, H. T. Wang, B. Mathur, A. Hsu, Humbert Suarez
{"title":"Computing optical flow in resistive networks and in the primate visual system","authors":"C. Koch, H. T. Wang, B. Mathur, A. Hsu, Humbert Suarez","doi":"10.1109/WVM.1989.47095","DOIUrl":"https://doi.org/10.1109/WVM.1989.47095","url":null,"abstract":"It is shown how the well-known algorithm of B. Horn and B.C. Schunk (1981) for computing optical flow, based on minimizing a quadratic functional using a relaxation scheme, maps onto two different kinds of massive parallel hardware: either resistive networks which are attractive for their technological potential, or neuronal networks related to the ones occurring in the motion pathway in the primate's visual system. If the x and y components of the motion field are coded explicitly as voltages within electrical circuits, simple resistive networks solve for the optical flow in the presence of motion discontinuities. These networks are being implemented into analog, subthreshold CMOS VLSI (complementary metal oxide semiconductor very large-scale integration) circuits. If velocity is represented within a population of direction selective cells, the resulting neuronal network maps onto the primate's striate and extrastriate visual cortex (middle temporal area). The performance of the network mimicks a large number of psychological illusions as well as electrophysical findings.<<ETX>>","PeriodicalId":342419,"journal":{"name":"[1989] Proceedings. Workshop on Visual Motion","volume":"646 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127866671","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":"Curve motion constraint equation and its applications","authors":"S. Gong","doi":"10.1109/WVM.1989.47096","DOIUrl":"https://doi.org/10.1109/WVM.1989.47096","url":null,"abstract":"To understand the parallel computation of optic flow, the author introduces a novel algorithm to compute the flow field at certain locations in the image. These locations are on the gradient edges, called seeds. The proposed curve motion constraint equation provides additional constraints to fully and locally estimate the flow field at seeds. Initial computational experiments have used the improved local flow as the initial input to E.C. Hildreth's algorithm (1984). Results show that Hildreth's method is about ten times slower than the one proposed.<<ETX>>","PeriodicalId":342419,"journal":{"name":"[1989] Proceedings. Workshop on Visual Motion","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115367933","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":"Changes in connectivity in active contour models","authors":"R. Samadani","doi":"10.1109/WVM.1989.47127","DOIUrl":"https://doi.org/10.1109/WVM.1989.47127","url":null,"abstract":"Techniques that are useful for tracking objects that change their connectivity have been demonstrated. Contours are extracted from objects moving in two dimensions whose motion is nonrigid and whose connectivity may change. A previously proposed solution for nonrigid motion, which involves the use of simulated elastic curves to track objects, is extended to allow elastic materials to break, grow, and connect open endpoints. The extensions allow object tracking even when the connectivity of objects changes. An algorithm for tracking objects that divide in two is developed based on these extensions. The algorithm is tested using a computer-generated image sequence simulating cell division.<<ETX>>","PeriodicalId":342419,"journal":{"name":"[1989] Proceedings. Workshop on Visual Motion","volume":"607 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132079200","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":"Relative motion parallax and the perception of structure from motion","authors":"J. Loomis, D. Eby","doi":"10.1109/WVM.1989.47111","DOIUrl":"https://doi.org/10.1109/WVM.1989.47111","url":null,"abstract":"Empirical findings are reported that delineate properties of the process underlying the perception of structure from motion (SfM). First, it is shown that the usual rotating kinetic depth displays generally involve at least two sources of information: relative motion parallax and changes in the projected envelope of the rotating object. Then, evidence is presented that even when variations in projected envelope are minimized, altering the 3-D motion of an object can greatly affect its perceived shape in ways that hint at properties of the underlying process. It is also shown that circular patterns of relative motion parallax not associated with a rigidly moving object can elicit the perception of depth variation, and that added image rotations which by themselves do not elicit apparent depth variation can nevertheless influence the apparent shape of such circular patterns.<<ETX>>","PeriodicalId":342419,"journal":{"name":"[1989] Proceedings. Workshop on Visual Motion","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126385909","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 mathematical foundations of smoothness constraints for the determination of optical flow and for surface reconstruction","authors":"M. A. Snyder","doi":"10.1109/WVM.1989.47100","DOIUrl":"https://doi.org/10.1109/WVM.1989.47100","url":null,"abstract":"Gradient-based approaches to the computation of optical flow often use a minimization technique incorporating a smoothness constraint on the optical flow field. The author derives the most general form of such a smoothness constraint which is quadratic in first or second derivatives of the grey-level image intensity function, based on three simple assumptions about the smoothness constraint: (1) that it be expressed in a form which is independent of the choice of Cartesian coordinate system in the image; (2) that it be positive definite; and (3) that it not couple different components of the optical flow. It is shown that there are essentially only four such constraints; any smoothness constraint satisfying all three assumptions must be a linear combination of these four, possibly multipled by certain quantities of these four, possibly multipled by certain quantities invariant under a change in the Cartesian coordinate system. Beginning with the three assumptions mentioned above, the author mathematically demonstrates that all the best-known smoothness constraints appearing in the literature are special cases of this general form, and, in particular, that the 'weight matrix' introduced by H.-H. Nagel (1983) is essentially the only physically plausible such constraint.<<ETX>>","PeriodicalId":342419,"journal":{"name":"[1989] Proceedings. Workshop on Visual Motion","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127940099","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":"Issues in extracting motion parameters and depth from approximate translational motion","authors":"R. Manmatha, R. Dutta, E. Riseman, M. A. Snyder","doi":"10.1109/WVM.1989.47118","DOIUrl":"https://doi.org/10.1109/WVM.1989.47118","url":null,"abstract":"In dynamic situations where the sensor is undergoing primarily translational motion with a relatively small rotational components, it might seem likely that approximate translational motion algorithms can be effective. It is shown quantitatively, however, that even small rotations can significantly affect the computation of the focus of expansion (FOE). This is shown theoretically for the case in which the environment is a frontal plane, and also experimentally. Two algorithms are presented. One is an existing general motion algorithm. The second is a pure translational algorithm based on the weighted Hough transform. The depth results obtained using the second algorithm are reasonable, although they are not as good as those using general motion.<<ETX>>","PeriodicalId":342419,"journal":{"name":"[1989] Proceedings. Workshop on Visual Motion","volume":"147 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123490147","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}