发布求助
文献互助 智能选刊 最新文献

[1989] Proceedings. Workshop on Visual Motion最新文献

筛选
英文 中文
In search of the elusive flow field 为了寻找难以捉摸的流场
[1989] Proceedings. Workshop on Visual Motion Pub Date : 1989-03-20 DOI: 10.1109/WVM.1989.47108
J. Perrone
{"title":"In search of the elusive flow field","authors":"J. Perrone","doi":"10.1109/WVM.1989.47108","DOIUrl":"https://doi.org/10.1109/WVM.1989.47108","url":null,"abstract":"A specific set of problems must be overcome before an optical-flow field can be derived from an image sequence. These problems are discussed and an outline of a scheme for overcoming these obstacles is presented. A 2-D motion sensor is presented which is capable of measuring edge velocity in twelve separate directions at any point in the image. However, because of the aperture problem, the sensors can only determine the velocity component in the direction orthogonal to the edge. A second stage which uses a cosine-weighted voting scheme is used to derive the true flow field from the edge velocities. The whole system is based on a parallel network of connections and weights and is potentially a very fast method of obtaining the 2-D flow field.<<ETX>>","PeriodicalId":342419,"journal":{"name":"[1989] Proceedings. Workshop on Visual Motion","volume":"12 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":"128016977","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: 6
Constraints for the computation of optical flow 光流计算的约束条件
[1989] Proceedings. Workshop on Visual Motion Pub Date : 1989-03-20 DOI: 10.1109/WVM.1989.47101
F. Girosi, A. Verri, V. Torre
{"title":"Constraints for the computation of optical flow","authors":"F. Girosi, A. Verri, V. Torre","doi":"10.1109/WVM.1989.47101","DOIUrl":"https://doi.org/10.1109/WVM.1989.47101","url":null,"abstract":"A number of constraints are proposed for which both the components of optical flow can be obtained by local differential techniques and the aperture problem can usually be solved. The constraints are suggested by the observation that it is possible to describe spatial and temporal changes of the image brightness in terms of infinitesimal deformations. An arbitrary choice of two of the four equations which correspond to the elementary deformations of a 2-D pattern implies that the spatial gradient of the image brightness is stationary and leads to a linear system of equations for optical flow which seems best suited for numerical implementation on real data in the absence of a priori information. In that case, the error term between the computed optical flow and the motion field-that is, the 2-D vector field associated with the true displacement of points on the image plane-is derived and the conditions under which it can safely be neglected are discussed. Experiments on real images are reported which show that the obtained optical flows allow the estimate of 3-D motion parameters, the detection of discontinuities in the flow field, and the segmentation of the image in different moving objects.<<ETX>>","PeriodicalId":342419,"journal":{"name":"[1989] Proceedings. Workshop on Visual Motion","volume":"55 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":"127567955","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
Point matching in a time sequence of stereo image pairs and its parallel implementation on a multiprocessor 立体图像对时间序列中的点匹配及其在多处理器上的并行实现
[1989] Proceedings. Workshop on Visual Motion Pub Date : 1989-03-20 DOI: 10.1109/WVM.1989.47125
M. K. Leung, A. Choudhary, J.H. Patel, T.S. Huang
{"title":"Point matching in a time sequence of stereo image pairs and its parallel implementation on a multiprocessor","authors":"M. K. Leung, A. Choudhary, J.H. Patel, T.S. Huang","doi":"10.1109/WVM.1989.47125","DOIUrl":"https://doi.org/10.1109/WVM.1989.47125","url":null,"abstract":"An algorithm for finding point correspondences among stereo image pairs at two consecutive time instants (t/sub i-1/,t/sub i/) and its parallel implementation on an Intel ipsc/2 hypercube multiprocessor system are presented. There are 137 unambiguous matched-point pairs among the images used. This number of points may be not enough for generating the structure of the object in the images; however, for motion estimation using stereo imagery, only three pairs of points (for the ideal case) are required, which implies that the results are more than enough for the estimation of motion parameters. From the parallel implementation of the feature extraction and stereo match algorithms on a hypercube multiprocessor system, it is observed that if the computation is uniformly distributed across the image (feature extraction) then almost linear speed-ups can be obtained by partitioning the data equally among the processor of the hypercube.<<ETX>>","PeriodicalId":342419,"journal":{"name":"[1989] Proceedings. Workshop on Visual Motion","volume":"452 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":"134427327","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: 15
Stereo/motion cues in pre-attentive vision processing-some experiments with random-dot stereographic image sequences 预注意视觉处理中的立体/运动线索——随机点立体图像序列的一些实验
[1989] Proceedings. Workshop on Visual Motion Pub Date : 1989-03-20 DOI: 10.1109/WVM.1989.47124
T. Pong, M. Kenner, J. Otis
{"title":"Stereo/motion cues in pre-attentive vision processing-some experiments with random-dot stereographic image sequences","authors":"T. Pong, M. Kenner, J. Otis","doi":"10.1109/WVM.1989.47124","DOIUrl":"https://doi.org/10.1109/WVM.1989.47124","url":null,"abstract":"Exploration of human, low-level, pre-attentive vision processing is facilitated using stroboscopic presentation of sequences of random dot stereograms, which contain only local spatial and temporal information thereby limiting the processing of these images to low level. The paper describes four demonstrations that utilize these sequences to explore the relationships of various cues, i.e. optical flow, stereo disparity, and occlusion, at the low level. To better study these relationships, especially the resolution of conflicting information among the cues, some of the image sequences present information not generally encountered in 'natural' scenes. Dominance of the stereo cue and the complex relationship between optical flow cues and disparity cues are well demonstrated.<<ETX>>","PeriodicalId":342419,"journal":{"name":"[1989] Proceedings. Workshop on Visual Motion","volume":"21 10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114033373","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: 3
Computing visual motion in the short and the long: from receptive fields to neural networks 计算长、短视觉运动:从感受野到神经网络
[1989] Proceedings. Workshop on Visual Motion Pub Date : 1989-03-20 DOI: 10.1109/WVM.1989.47105
A. Waxman, J. Wu, M. Seibert
{"title":"Computing visual motion in the short and the long: from receptive fields to neural networks","authors":"A. Waxman, J. Wu, M. Seibert","doi":"10.1109/WVM.1989.47105","DOIUrl":"https://doi.org/10.1109/WVM.1989.47105","url":null,"abstract":"Theoretical approaches to the study of perceptual phenomena of short-range and long-range apparent motion are discussed. Short-range motion is estimated by real-time receptive fields sensitive to velocities of image features. The design of these receptive fields follows from the concept of convected activation profiles, where shape-preserving activity waves are excited by, and ride atop, dynamic features. Long-range motion concerns the correspondence between features in disparate images, and the perceptual impletion of a path between these corresponding features. It is argued that this illusory motion is an artifact of a more general spatiotemporal grouping process. This process is realized in a dynamic nonlinear feedback neural network that is called a neural analog diffusion-enhancement layer (NADEL). Computations suggest that the NADEL can support a variety of long-range motion percepts popularized by the Gestalt psychologists. The authors illustrate (on videotape) both classes of computation in real time on the PIPE parallel computer.<<ETX>>","PeriodicalId":342419,"journal":{"name":"[1989] Proceedings. Workshop on Visual Motion","volume":"314 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":"133645479","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: 10
Tracking points and line segments in image sequences 跟踪图像序列中的点和线段
[1989] Proceedings. Workshop on Visual Motion Pub Date : 1989-03-20 DOI: 10.1109/WVM.1989.47092
J. Gambotto
{"title":"Tracking points and line segments in image sequences","authors":"J. Gambotto","doi":"10.1109/WVM.1989.47092","DOIUrl":"https://doi.org/10.1109/WVM.1989.47092","url":null,"abstract":"The author examines different constraints which can be used to find the correspondences between line segments in an image sequence. These constraints are imposed by the continuity of the 3-D motion and also by certain types of motions. The author derives simple equations which relate corresponding tokens in three consecutive images when the 3-D motion is a translation. Next, he describes an algorithm for matching line segments when the motion of the camera is approximately known and presents some experimental results. If a camera moving in a stationary environment is considered, an image motion is related to the location of the corresponding object in space with respect to the instantaneous axis of translation. The author performs a geometrical analysis of this relationship and introduces concepts for this analysis. It is noted that this relationship is useful for tracking objects in the field of view.<<ETX>>","PeriodicalId":342419,"journal":{"name":"[1989] Proceedings. Workshop on Visual Motion","volume":"14 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":"121174117","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: 6
Structure from limited motion of complex rigid objects 复杂刚体的有限运动结构
[1989] Proceedings. Workshop on Visual Motion Pub Date : 1989-03-20 DOI: 10.1109/WVM.1989.47117
R. Jaenicke
{"title":"Structure from limited motion of complex rigid objects","authors":"R. Jaenicke","doi":"10.1109/WVM.1989.47117","DOIUrl":"https://doi.org/10.1109/WVM.1989.47117","url":null,"abstract":"A feature-based method is presented for recovering the structure of rigid objects rotating about a fixed axis. The emphasis is on using several views that span only a small angle of rotation to recover the structure of a complex object. First, the correspondence problem for densely-packed features of a complex object undergoing slow rotations is solved by applying the smoothness of motion constraint to higher-order motion approximations. Second, the inaccurate feature motion solution that results from having only a limited extent of rotation is augmented by utilizing any symmetries discovered in the object to constrain one feature motion solution by the gross approximate motion of another feature. These constraints are in addition to those derived from the assumptions of a fixed axis of rotation and a rigid object. The data source presented is a sequence of radar range-Doppler images; similarities to optical image understanding are noted.<<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":"121266886","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: 4
Motion estimation from points without correspondences from orthographic projections 从正射影中没有对应点的运动估计
[1989] Proceedings. Workshop on Visual Motion Pub Date : 1989-03-20 DOI: 10.1109/WVM.1989.47129
Dmitry B. Goldgof, T. S. Huang, H. Lee
{"title":"Motion estimation from points without correspondences from orthographic projections","authors":"Dmitry B. Goldgof, T. S. Huang, H. Lee","doi":"10.1109/WVM.1989.47129","DOIUrl":"https://doi.org/10.1109/WVM.1989.47129","url":null,"abstract":"The authors present a novel algorithm for recovering motion parameters of the 3D point sets given point coordinates in three orthographic projections before and after motion. The algorithm requires no correspondences between two time instants and only a few correspondences in projections at the second time instant. The 3S scatter matrix of the 3D sets is calculated from 2D scatter matrices of projections. The algorithm uses matrix-eigendecomposition of the 3D scatter matrix to determine four candidate solutions for the rotation matrix.<<ETX>>","PeriodicalId":342419,"journal":{"name":"[1989] Proceedings. Workshop on Visual Motion","volume":"8 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1989-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113963653","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: 3
On combining points and lines in an image sequence to recover 3D structure and motion 结合图像序列中的点和线来恢复三维结构和运动
[1989] Proceedings. Workshop on Visual Motion Pub Date : 1989-03-20 DOI: 10.1109/WVM.1989.47113
R. Laganière, A. Mitiche
{"title":"On combining points and lines in an image sequence to recover 3D structure and motion","authors":"R. Laganière, A. Mitiche","doi":"10.1109/WVM.1989.47113","DOIUrl":"https://doi.org/10.1109/WVM.1989.47113","url":null,"abstract":"The authors consider the problem of combining the use of points and lines in a sequence of images to recover the 3D structure and motion. They determine the configurations that yield a resolvable system of equations, treating the cases of two and three views in more detail. For the case of two views, they show that lines are not needed, as they do not contribute to the obtaining of a resolvable system of equations. For the case of three views, the authors list the few interesting resolvable configurations. They also indicate how to obtain rigidity-based equations using structural invariance. Finally, they show why combining points and lines can be particularly useful when occultation occurs.<<ETX>>","PeriodicalId":342419,"journal":{"name":"[1989] Proceedings. Workshop on Visual Motion","volume":"45 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":"125583330","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: 6
The interpretation of visual motion: recognizing moving light displays 视觉运动的解释:识别移动的光显示
[1989] Proceedings. Workshop on Visual Motion Pub Date : 1989-03-20 DOI: 10.1109/WVM.1989.47112
N. H. Goddard
{"title":"The interpretation of visual motion: recognizing moving light displays","authors":"N. H. Goddard","doi":"10.1109/WVM.1989.47112","DOIUrl":"https://doi.org/10.1109/WVM.1989.47112","url":null,"abstract":"A computational model of visual motion discrimination in the human visual system is being developed, with application to interpretation of moving light displays. The author provides an overview of the current state of the model and discusses ideas that are being pursued. The computational model incorporates bottom-up feature computation, scenario indexing, and top-down contextual information flow. Emphasis is on the intermediate and higher-level visual processes, assuming the work of others for the low-level processes. The nature of memory structures devoted to representation and recognition of visual motion sequences is explored.<<ETX>>","PeriodicalId":342419,"journal":{"name":"[1989] Proceedings. Workshop on Visual Motion","volume":"22 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":"129924900","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: 29
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