发布求助
文献互助 智能选刊 最新文献

Proceedings of the IEEE Workshop on Visual Motion最新文献

筛选
英文 中文
Factoring image sequences into shape and motion 将图像序列分解为形状和运动
Proceedings of the IEEE Workshop on Visual Motion Pub Date : 1991-10-07 DOI: 10.1109/WVM.1991.212792
Carlo Tomasi, T. Kanade
{"title":"Factoring image sequences into shape and motion","authors":"Carlo Tomasi, T. Kanade","doi":"10.1109/WVM.1991.212792","DOIUrl":"https://doi.org/10.1109/WVM.1991.212792","url":null,"abstract":"Recovery scene geometry and camera motion from a sequence of images is an important problem in computer vision. If the scene geometry is specified by depth measurements, that is, by specifying distances between the camera and feature points in the scene, noise sensitivity worsens rapidly with increasing depth. The authors show hat this difficulty can be overcome by computing scene geometry directly in terms of shape, that is, by computing the coordinates of feature points in the scene with respect to a world-centered system, without recovering camera-centered depth as an intermediate quantity. More specifically, the authors show that a matrix of image measurements can be factored by singular value decomposition into the product of two matrices that represent shape and motion, respectively. The results in this paper extend to three dimensions the solution the authors described in a previous paper for planar camera motion (ICCV, Osaka, Japan, 1990).<<ETX>>","PeriodicalId":208481,"journal":{"name":"Proceedings of the IEEE Workshop on Visual Motion","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128605244","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}
引用次数: 86
Passive Navigation in a partially known environment 在部分已知环境中的被动导航
Proceedings of the IEEE Workshop on Visual Motion Pub Date : 1991-10-07 DOI: 10.1109/WVM.1991.212795
S. Chandrashekhar, Ramalingam Chellappa
{"title":"Passive Navigation in a partially known environment","authors":"S. Chandrashekhar, Ramalingam Chellappa","doi":"10.1109/WVM.1991.212795","DOIUrl":"https://doi.org/10.1109/WVM.1991.212795","url":null,"abstract":"The paper presents an integrated solution to the problem of obtaining the kinematics of a moving vehicle and the 3D locations of salient points in the external environment, based on a sequence of monocular images. The structure of a small number of navigational landmarks in the scene is assumed to be known. The parameters of interest are expressed in an inertial, or 'world' coordinate system, external to the moving vehicle, and are estimated recursively using an extended Kalman filter (EKF). The extraction and matching of feature points are done using a gabor wavelet representation, and are interleaved with the recursive estimation. Experimental results on a real image sequence are given.<<ETX>>","PeriodicalId":208481,"journal":{"name":"Proceedings of the IEEE Workshop on Visual Motion","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116057536","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}
引用次数: 18
An adaptive multi-scale approach for estimating optical flow: computational theory and physiological implementation 一种自适应多尺度光流估计方法:计算理论与生理实现
Proceedings of the IEEE Workshop on Visual Motion Pub Date : 1991-10-07 DOI: 10.1109/WVM.1991.212780
C. Koch, H.T. Wang, R. Battiti, B. Mathur, C. Ziomkowski
{"title":"An adaptive multi-scale approach for estimating optical flow: computational theory and physiological implementation","authors":"C. Koch, H.T. Wang, R. Battiti, B. Mathur, C. Ziomkowski","doi":"10.1109/WVM.1991.212780","DOIUrl":"https://doi.org/10.1109/WVM.1991.212780","url":null,"abstract":"The accuracy of optical flow estimation depends on the spatio-temporal discretization used in the computation. The authors propose an adaptive multiscale method, where the discretization scale is chosen locally according to an estimate of the relative error in the velocity measurements. They show that their coarse-to-fine method provides substantially better results of optical flow than conventional algorithms. The authors map this multiscale strategy onto their model of motion computation in primate area MT. The model consists of two stages: (1) local velocities are measured across multiple spatio-temporal channels, while (2) the optical flow field is computed by a network of direction-selective neurons at multiple spatial resolutions. Their model neurons show the same nonclassical receptive field properties as Allman's type I MT neurons and lead to a novel interpretation of some aspect of the motion capture illusion.<<ETX>>","PeriodicalId":208481,"journal":{"name":"Proceedings of the IEEE Workshop on Visual Motion","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114239621","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}
引用次数: 12
Pointwise tracking of left-ventricular motion in 3D 三维左心室运动的点对跟踪
Proceedings of the IEEE Workshop on Visual Motion Pub Date : 1991-10-07 DOI: 10.1109/WVM.1991.212772
A. Amini, J. Duncan
{"title":"Pointwise tracking of left-ventricular motion in 3D","authors":"A. Amini, J. Duncan","doi":"10.1109/WVM.1991.212772","DOIUrl":"https://doi.org/10.1109/WVM.1991.212772","url":null,"abstract":"The problem of motion-tracking of the left-ventricular wall from 4D image data is addressed. The authors first discuss the forms of 4D data available, namely cine-X-ray CT, and gated and cine magnetic-resonance image data. They then discuss the approach that is utilized for tracking the movement of the endocardium. Based on these ideas, an algorithm is developed, and experimental results are presented.<<ETX>>","PeriodicalId":208481,"journal":{"name":"Proceedings of the IEEE Workshop on Visual Motion","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126225268","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}
引用次数: 49
Factorization-based segmentation of motions 基于分解的运动分割
Proceedings of the IEEE Workshop on Visual Motion Pub Date : 1991-10-07 DOI: 10.1109/WVM.1991.212809
Terrance E. Boult, L. M. G. Brown
{"title":"Factorization-based segmentation of motions","authors":"Terrance E. Boult, L. M. G. Brown","doi":"10.1109/WVM.1991.212809","DOIUrl":"https://doi.org/10.1109/WVM.1991.212809","url":null,"abstract":"The authors address the problem of motion segmentation using the singular value decomposition of a feature track matrix. It is shown that, under general assumptions, the number of numerically nonzero singular values can be used to determine the number of motions. Furthermore, motions can be separated using the right singular vectors associated with the nonzero singular values. A relationship is derived between a good segmentation, the number of nonzero singular values in the input and the sum of the number of nonzero singular values in the segments. The approach is demonstrated on real and synthetic examples. The paper ends with a critical analysis of the approach.<<ETX>>","PeriodicalId":208481,"journal":{"name":"Proceedings of the IEEE Workshop on Visual Motion","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124355675","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}
引用次数: 186
Segmentation of people in motion 运动中的人的分割
Proceedings of the IEEE Workshop on Visual Motion Pub Date : 1991-10-07 DOI: 10.1109/WVM.1991.212768
A. Shio, J. Sklansky
{"title":"Segmentation of people in motion","authors":"A. Shio, J. Sklansky","doi":"10.1109/WVM.1991.212768","DOIUrl":"https://doi.org/10.1109/WVM.1991.212768","url":null,"abstract":"A method for segmenting monocular images of people in motion from a cinematic sequence of frames is described. This method is based on image intensities, motion, and an object model-i.e., a model of the image of a person in motion. Though each part of a person may move in different directions at any instant, the time averaged motion of all parts must converge to a global average value over a few seconds. People in an image may be occluded by other people, and usually it is not easy to detect their boundaries. These boundaries can be detected with motion information if they move in different directions, even if there are almost no apparent differences among object intensities or colors. Each image of a person in a scene usually can be divided into several parts, each with distinct intensities or colors. The parts of a person can be merged into a single group by an iterative merging algorithm based on the object model and the motion information because the parts move coherently. This merging is analogous to the property of perceptual grouping in human visual perception of motion. Experiments based on a sequence of complex real scenes produced results that are supportive of the authors approach to the segmentation of people in motion.<<ETX>>","PeriodicalId":208481,"journal":{"name":"Proceedings of the IEEE Workshop on Visual Motion","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123755756","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}
引用次数: 140
Simultaneous estimation of 3D shape and motion of objects by computer vision 用计算机视觉同时估计物体的三维形状和运动
Proceedings of the IEEE Workshop on Visual Motion Pub Date : 1991-10-07 DOI: 10.1109/WVM.1991.212799
J. Schick, E. Dickmanns
{"title":"Simultaneous estimation of 3D shape and motion of objects by computer vision","authors":"J. Schick, E. Dickmanns","doi":"10.1109/WVM.1991.212799","DOIUrl":"https://doi.org/10.1109/WVM.1991.212799","url":null,"abstract":"A recursive estimation method based on the 4D-approach to real-time computer vision for simultaneously determining both 3D shape parameters and motion state of objects is discussed. The recognition processes exploit structurally given shape models and motion models given by difference-equations. This allows to confine the image analysis to feature evaluation of the last frame of the sequence only; no differencing between images has to be done, yet the spatial motion components (satisfying planar motion constraints) are recovered directly without inverting the perspective projection equations of the imaging process explicitly. Object recognition has been confined to a well structured, but otherwise general dynamic scene for the beginning: road traffic with a limited class of vehicles.<<ETX>>","PeriodicalId":208481,"journal":{"name":"Proceedings of the IEEE Workshop on Visual Motion","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131325020","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}
引用次数: 34
Quantitative interpretation of image velocities in real time 实时图像速度的定量解释
Proceedings of the IEEE Workshop on Visual Motion Pub Date : 1991-10-07 DOI: 10.1109/WVM.1991.212805
J. Huber, V. Graefe
{"title":"Quantitative interpretation of image velocities in real time","authors":"J. Huber, V. Graefe","doi":"10.1109/WVM.1991.212805","DOIUrl":"https://doi.org/10.1109/WVM.1991.212805","url":null,"abstract":"A concept for motion stereo is introduced. It is based on an explicit determination of the velocities with which features move in images of dynamic scenes. A mobile robot carrying a single TV-camera may use this method to determine its distance to external objects accurately and in real time. While the robot approaches an object the accuracy of the measurement improves continuously as the distance decreases, making the method particularly suitable for tasks like collision avoidance or docking. The method may be implemented in such a way that it does not require a camera calibration, provided the lens of the camera is sufficiently free from distortion. The method has been applied on a mobile robot equipped with a real-time vision system, and experiments have been performed to test its practicality in a real-world environment. Accuracies better than 1% of the distance have been demonstrated while the robot was moving in the direction towards the object.<<ETX>>","PeriodicalId":208481,"journal":{"name":"Proceedings of the IEEE Workshop on Visual Motion","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123356584","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}
引用次数: 19
Direct computation of the focus of expansion from velocity field measurements 由速度场测量直接计算膨胀焦点
Proceedings of the IEEE Workshop on Visual Motion Pub Date : 1991-10-07 DOI: 10.1109/WVM.1991.212776
Rami Guissin, S. Ullman
{"title":"Direct computation of the focus of expansion from velocity field measurements","authors":"Rami Guissin, S. Ullman","doi":"10.1109/WVM.1991.212776","DOIUrl":"https://doi.org/10.1109/WVM.1991.212776","url":null,"abstract":"A new method for computing the direction of translational motion (focus of expansion) of a moving observer (or camera) in a stationary environment is proposed. The method applied simple 1D search directly to velocity field measurements of the changing image, for cases of general motion and constrained motion. In the case of general motion, the velocity field is derotated to cancel the velocity of the observed point at the image origin. In principle, a single moving closed contour which encircles the origin is sufficient to recover the focus of expansion. In practice, additional velocity measurements in the image may be incorporated in the computation, for improved robustness in the face of image noise and velocity field inaccuracies.<<ETX>>","PeriodicalId":208481,"journal":{"name":"Proceedings of the IEEE Workshop on Visual Motion","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125758081","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}
引用次数: 17
Incremental estimation of image-flow using a Kalman filter 基于卡尔曼滤波的图像流增量估计
Proceedings of the IEEE Workshop on Visual Motion Pub Date : 1991-10-07 DOI: 10.1109/WVM.1991.212790
A. Singh
{"title":"Incremental estimation of image-flow using a Kalman filter","authors":"A. Singh","doi":"10.1109/WVM.1991.212790","DOIUrl":"https://doi.org/10.1109/WVM.1991.212790","url":null,"abstract":"Many applications of visual motion, such as navigation, tracking, etc., require that image-flow be estimated in an on-line, incremental fashion. Kalman filtering provides a robust and efficient mechanism to record image-flow estimates along with their uncertainty and to integrate new measurements with the existing estimates. The fundamental form of motion information in time-varying imagery (conservation information) is recovered along with its uncertainty from a pair of images using a correlation-based approach. As more images are acquired, this information is integrated temporally and spatially using a Kalman filter. The uncertainty in the estimates decreases with the progress of time. This framework is shown to behave very well at the discontinuities of the flow-field. Algorithms based on this framework are used to recover image-flow from a variety of image-sequences.<<ETX>>","PeriodicalId":208481,"journal":{"name":"Proceedings of the IEEE Workshop on Visual Motion","volume":"122 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114015470","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}
引用次数: 17
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信