By Topic

# Proceedings of the IEEE Workshop on Visual Motion

## Filter Results

Displaying Results 1 - 25 of 47
• ### Estimation of velocity, acceleration and disparity in time sequences

Publication Year: 1991, Page(s):44 - 51
Cited by:  Papers (9)  |  Patents (1)
| | PDF (1048 KB)

The paper presents a general framework for the analysis of time sequences. Features extracted include speed, acceleration and disparity/depth. The method uses spatio-temporal filtering in a hierarchical structure. Synthetic and real world examples are included.<> View full abstract»

• ### Proceedings of the IEEE Workshop on Visual Motion (Cat. No.91TH0390-5)

Publication Year: 1991
| PDF (1465 KB)
• ### Non-rigid motion and structure from contour

Publication Year: 1991, Page(s):288 - 293
Cited by:  Papers (10)
| | PDF (548 KB)

The elastic properties of real materials constrain the types of non-rigid motion that can occur. The authors show that by modeling and simulating the physics of non-rigid motion they can obtain good estimates of both object shape and velocity from contour data. The underlying model is based on the finite element method, and decouples the degrees of freedom by breaking down object motion into rigid... View full abstract»

• ### Pointwise tracking of left-ventricular motion in 3D

Publication Year: 1991, Page(s):294 - 299
Cited by:  Papers (23)
| | PDF (832 KB)

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 prese... View full abstract»

• ### Stability of phase information

Publication Year: 1991, Page(s):52 - 60
Cited by:  Papers (3)  |  Patents (3)
| | PDF (696 KB)

This paper concerns the robustness of phase information for measuring image velocity and binocular disparity, its stability with respect to geometric deformations, and its linearity as a function of spatial position. These properties are shown to depend on the form of the filters used and their frequency bandwidths. The authors also discuss situations in which phase is unstable, many of which can ... View full abstract»

• ### Egomotion from global flow field data

Publication Year: 1991, Page(s):140 - 145
Cited by:  Papers (8)
| | PDF (404 KB)

The author presents two independent, global algorithms to compute the motion parameters. The flow circulation algorithm fits a linear surface to the curl of the flow field. The parameters of this linear surface are proportional to the angular velocity components. The author shows that instead of the curl values one can use circulation values that are simply contour integrals of the flow field on t... View full abstract»

• ### Computing motion using analog VLSI vision chips: an experimental comparison among four approaches

Publication Year: 1991, Page(s):312 - 324
Cited by:  Papers (17)  |  Patents (11)
| | PDF (1172 KB)

The authors have designed, built and tested a number of analog CMOS VLSI circuits for computing 1D motion from the time-varying intensity values provided by an array of on-chip phototransistors. The authors present experimental data for three such circuits and discuss their relative performance. One circuit approximates the correlation model, one the gradient model, while a third chip uses resisti... View full abstract»

• ### Motion analysis and modeling of epicardial surfaces from point and line correspondences

Publication Year: 1991, Page(s):300 - 305
Cited by:  Papers (10)
| | PDF (536 KB)

This paper presents a new algorithm for recovering motion parameters of nonrigid objects using both point and line correspondences. It requires estimating the coefficients of the first fundamental form before and after the motion. This algorithm has several advantages over a previously developed algorithm which uses only point correspondences and Gaussian curvature. First, it does not require any ... View full abstract»

• ### Estimating 3D vehicle motion in an outdoor scene from monocular and stereo image sequences

Publication Year: 1991, Page(s):62 - 68
Cited by:  Papers (4)  |  Patents (1)
| | PDF (504 KB)

The main goal of this research is to test how well existing feature extraction, matching and motion estimation algorithms (with appropriate modification) work on outdoor scenes. For this purpose, a careful calibrated image sequence data base has been created. The data used for the results reported in the paper consists of a sequence of 24 stereo images of an outdoor scene containing a moving truck... View full abstract»

• ### Motion and structure from long stereo image sequences

Publication Year: 1991, Page(s):75 - 80
Cited by:  Papers (2)
| | PDF (496 KB)

The treatment of uncertainty in 3D points determined by stereo triangulation affects significantly the reliability of the estimated 3D motion and structure. The authors first address this issue in the estimation of inter-frame motion. Two methods are discussed, a closed-form matrix-weighted least-squares solution and an iterative optimal solution. Using each of these two methods for two-view analy... View full abstract»

• ### Structure and motion in two dimensions from multiple images: a least squares approach

Publication Year: 1991, Page(s):242 - 248
Cited by:  Papers (15)  |  Patents (1)
| | PDF (556 KB)

The authors address a special case of the structure from motion problem for static scenes where the camera positions and feature points are confined to the two-dimensional plane. This problem is relevant to indoor mobile robots that construct a map of their environment from vertical line correspondences. The algorithm is based on the minimization of the mean square difference between the projectio... View full abstract»

• ### Direct multi-resolution estimation of ego-motion and structure from motion

Publication Year: 1991, Page(s):156 - 162
Cited by:  Papers (42)  |  Patents (21)
| | PDF (580 KB)

The paper describes an iterative algorithm that estimates the motion of a camera through an environment directly from brightness derivatives of an image pair. A global ego-motion constraint is combined with the local brightness constancy constraint to relate local surface models with the global ego-motion model and local brightness derivatives. In an iterative process, the author first refines the... View full abstract»

• ### Direct computation of the focus of expansion from velocity field measurements

Publication Year: 1991, Page(s):146 - 155
Cited by:  Papers (266)
| | PDF (672 KB)

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 ... View full abstract»

• ### Parallel visual motion analysis using multiscale Markov random fields

Publication Year: 1991, Page(s):30 - 35
Cited by:  Papers (11)  |  Patents (1)
| | PDF (516 KB)

The use of Markov Random Field (MRF) models within the framework of global bayesian decision has brought new powerful solutions to visual motion analysis. The efficiency of MRF models for image sequence analysis has been proved on various classes of real-world sequences: outdoor and indoor scenes including several moving objects and camera motion. The authors extend this work by investigating new ... View full abstract»

• ### An adaptive multi-scale approach for estimating optical flow: computational theory and physiological implementation

Publication Year: 1991, Page(s):111 - 122
Cited by:  Papers (2)  |  Patents (6)
| | PDF (824 KB)

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 convention... View full abstract»

• ### Motion-boundary illusions and their regularization

Publication Year: 1991, Page(s):88 - 94
Cited by:  Papers (1)
| | PDF (632 KB)

The authors performed several experiments where they made sure that the only cues available to the observer were contour and motion. It turns out that when humans combine information from contour and motion to reconstruct the shape of an object in view, if the results of the two modules-shape from contour and structure from motion-are inconsistent, they totally discard one of the cues and an illus... View full abstract»

• ### Segmentation of people in motion

Publication Year: 1991, Page(s):325 - 332
Cited by:  Papers (41)  |  Patents (15)
| | PDF (672 KB)

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 s... View full abstract»

• ### Passive Navigation in a partially known environment

Publication Year: 1991, Page(s):2 - 7
Cited by:  Papers (5)
| | PDF (392 KB)

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, exte... View full abstract»

• ### Simultaneous estimation of 3D shape and motion of objects by computer vision

Publication Year: 1991, Page(s):256 - 261
Cited by:  Papers (7)
| | PDF (580 KB)

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;... View full abstract»

• ### Robust estimation of a multi-layered motion representation

Publication Year: 1991, Page(s):173 - 178
Cited by:  Papers (65)  |  Patents (2)
| | PDF (456 KB)

In order to recover an accurate representation of a scene containing multiple moving objects, one must use estimation methods that can recover both model parameters and segmentation at the same time. Traditional approaches to this problem rely on an edge-based discontinuity model, and have problems with transparent phenomena. The authors introduce a layered model of scene segmentation based on exp... View full abstract»

• ### Realizing active vision by a mobile robot

Publication Year: 1991, Page(s):205 - 210
Cited by:  Papers (2)
| | PDF (392 KB)

Most active systems use a camera mounted on a manipulator, because the control of the camera motion is easy and accurate. A limited range of the camera motion by the fixed manipulator, however, often prevents the method from real applications. The paper explores a more general method that a camera on a mobile robot freely moves in the environment and acquires the spatial information based on the a... View full abstract»

• ### Hierarchical feature based matching for motion correspondence

Publication Year: 1991, Page(s):280 - 285
Cited by:  Papers (3)  |  Patents (2)
| | PDF (560 KB)

The authors design a feature based motion correspondence system. They propose a hierarchical grouping process that groups line segments into more complex structures that are easier to match. The hierarchy consists of lines, vertices, edges and surfaces. Matching starts at the highest level of the hierarchy (surfaces) and proceeds to the lowest (lines). Higher level features are easier to match, be... View full abstract»

• ### Motion recovery from image sequences using First-order optical flow information

Publication Year: 1991, Page(s):132 - 139
Cited by:  Papers (14)
| | PDF (676 KB)

A closed-form solution for motion estimation from first-order flow in two distinct' image regions is described. Uniqueness is guaranteed when these correspond to surface patches with different normal vectors. given an image sequence, the authors show how the image many be segmented into regions with the necessary properties, optical flow is computed for these regions, and motion parameters are co... View full abstract»

• ### Recursive estimation of shape and nonrigid motion

Publication Year: 1991, Page(s):306 - 311
Cited by:  Papers (6)
| | PDF (536 KB)

The authors paper presents an approach for recursively estimating 3D object shape and general nonrigid motion, which makes use of physically based dynamic models. The models provide global deformation parameters which represent the salient shape features of natural parts, and local deformation parameters which capture shape details. The equations of motion governing the models, augmented by point-... View full abstract»

• ### Recovering a boundary-level structural description from dynamic stereo

Publication Year: 1991, Page(s):69 - 74
| | PDF (676 KB)

The authors present a stereo algorithm to recursively compute a boundary-level structural description of a scene, from a sequence of stereo images. This algorithm utilizes connected line segments as the basic match primitive, which yields a description composed primary of boundaries of objects in the scene. A description of this nature is very useful for obstacle avoidance and path planning for mo... View full abstract»