Results 1  10
of
210
Performance of optical flow techniques
 INTERNATIONAL JOURNAL OF COMPUTER VISION
, 1994
"... While different optical flow techniques continue to appear, there has been a lack of quantitative evaluation of existing methods. For a common set of real and synthetic image sequences, we report the results of a number of regularly cited optical flow techniques, including instances of differential, ..."
Abstract

Cited by 1325 (32 self)
 Add to MetaCart
(Show Context)
While different optical flow techniques continue to appear, there has been a lack of quantitative evaluation of existing methods. For a common set of real and synthetic image sequences, we report the results of a number of regularly cited optical flow techniques, including instances of differential, matching, energybased and phasebased methods. Our comparisons are primarily empirical, and concentrate on the accuracy, reliability and density of the velocity measurements; they show that performance can differ significantly among the techniques we implemented.
Shape and motion from image streams under orthography: a factorization method
 INTERNATIONAL JOURNAL OF COMPUTER VISION
, 1992
"... Inferring scene geometry and camera motion from a stream of images is possible in principle, but is an illconditioned problem when the objects are distant with respect to their size. We have developed a factorization method that can overcome this difficulty by recovering shape and motion under orth ..."
Abstract

Cited by 1094 (38 self)
 Add to MetaCart
Inferring scene geometry and camera motion from a stream of images is possible in principle, but is an illconditioned problem when the objects are distant with respect to their size. We have developed a factorization method that can overcome this difficulty by recovering shape and motion under orthography without computing depth as an intermediate step. An image stream can be represented by the 2FxP measurement matrix of the image coordinates of P points tracked through F frames. We show that under orthographic projection this matrix is of rank 3. Based on this observation, the factorization method uses the singularvalue decomposition technique to factor the measurement matrix into two matrices which represent object shape and camera rotation respectively. Two of the three translation components are computed in a preprocessing stage. The method can also handle and obtain a full solution from a partially filledin measurement matrix that may result from occlusions or tracking failures. The method gives accurate results, and does not introduce smoothing in either shape or motion. We demonstrate this with a series of experiments on laboratory and outdoor image streams, with and without occlusions.
Catadioptric Omnidirectional Camera,”
 Proc. IEEE Conf. on Comp. Vis. Patt. Recog.,
, 1997
"... ..."
The Computation of Optical Flow
, 1995
"... Twodimensional image motion is the projection of the threedimensional motion of objects, relative to a visual sensor, onto its image plane. Sequences of timeordered images allow the estimation of projected twodimensional image motion as either instantaneous image velocities or discrete image dis ..."
Abstract

Cited by 295 (10 self)
 Add to MetaCart
(Show Context)
Twodimensional image motion is the projection of the threedimensional motion of objects, relative to a visual sensor, onto its image plane. Sequences of timeordered images allow the estimation of projected twodimensional image motion as either instantaneous image velocities or discrete image displacements. These are usually called the optical flow field or the image velocity field. Provided that optical flow is a reliable approximation to twodimensional image motion, it may then be used to recover the threedimensional motion of the visual sensor (to within a scale factor) and the threedimensional surface structure (shape or relative depth) through assumptions concerning the structure of the optical flow field, the threedimensional environment and the motion of the sensor. Optical flow may also be used to perform motion detection, object segmentation, timetocollision and focus of expansion calculations, motion compensated encoding and stereo disparity measurement. We investiga...
Kalman Filterbased Algorithms for Estimating Depth from Image Sequences
, 1989
"... Using known camera motion to estimate depth from image sequences is an important problem in robot vision. Many applications of depthfrommotion, including navigation and manipulation, require algorithms that can estimate depth in an online, incremental fashion. This requires a representation that ..."
Abstract

Cited by 259 (26 self)
 Add to MetaCart
Using known camera motion to estimate depth from image sequences is an important problem in robot vision. Many applications of depthfrommotion, including navigation and manipulation, require algorithms that can estimate depth in an online, incremental fashion. This requires a representation that records the uncertainty in depth estimates and a mechanism that integrates new measurements with existing depth estimates to reduce the uncertainty over time. Kalman filtering provides this mechanism. Previous applications of Kalman filtering to depthfrommotion have been limited to estimating depth at the location of a sparse set of features. In this paper, we introduce a new, pixelbased (iconic) algorithm that estimates depth and depth uncertainty at each pixel and incrementally refines these estimates over time. We describe the algorithm and contrast its formulation and performance to that of a featurebased Kalman filtering algorithm. We compare the performance of the two approaches by analyzing their theoretical convergence rates, by conducting quantitative experiments with images of a flat poster, and by conducting qualitative experiments with images of a realistic outdoorscene model. The results show that the new method is an effective way to extract depth from lateral camera translations. This approach can be extended to incorporate general motion and to integrate other sources of information, such as stereo. The algorithms we have developed, which combine Kalman filtering with iconic descriptions of depth, therefore can serve as a useful and general framework for lowlevel dynamic vision.
Epipolarplane image analysis: An approach to determining structure from motion
 INTERN..1. COMPUTER VISION
, 1987
"... We present a technique for building a threedimensional description of a static scene from a dense sequence of images. These images are taken in such rapid succession that they form a solid block of data in which the temporal continuity from image to image is approximately equal to the spatial conti ..."
Abstract

Cited by 253 (3 self)
 Add to MetaCart
(Show Context)
We present a technique for building a threedimensional description of a static scene from a dense sequence of images. These images are taken in such rapid succession that they form a solid block of data in which the temporal continuity from image to image is approximately equal to the spatial continuity in an individual image. The technique utilizes knowledge of the camera motion to form and analyze slices of this solid. These slices directly encode not only the threedimensional positions of objects, but also such spatiotemporal events as the occlusion of one object by another. For straightline camera motions, these slices have a simple linear structure that makes them easier to analyze. The analysis computes the threedimensional positions of object features, marks occlusion boundaries on the objects, and builds a threedimensional map of "free space." In our article, we first describe the application of this technique to a simple camera motion, and then show how projective duality is used to extend the analysis to a wider class of camera motions and object types that include curved and moving objects.
ThreeDimensional Scene Flow
, 1999
"... Scene flow is the threedimensional motion field of points in the world, just as optical flow is the twodimensional motion field of points in an image. Any optical flow is simply the projection of the scene flow onto the image plane of a camera. In this paper, we present a framework for the computa ..."
Abstract

Cited by 171 (8 self)
 Add to MetaCart
(Show Context)
Scene flow is the threedimensional motion field of points in the world, just as optical flow is the twodimensional motion field of points in an image. Any optical flow is simply the projection of the scene flow onto the image plane of a camera. In this paper, we present a framework for the computation of dense, nonrigid scene flow from optical flow. Our approach leads to straightforward linear algorithms and a classification of the task into three major scenarios: (1) complete instantaneous knowledge of the scene structure, (2) knowledge only of correspondence information, and (3) no knowledge of the scene structure. We also show that multiple estimates of the normal flow cannot be used to estimate dense scene flow directly without some form of smoothing or regularization.
Direct methods for recovering motion
 International Journal of Computer Vision
, 1988
"... We have developed direct methods for recovering the motion of an observer in a static environment in th e case of pure rotation, pure translation, and arbitrary motion when the rotation is known. Some of these methods are based on the minimization of the difference between the observed time derivati ..."
Abstract

Cited by 167 (7 self)
 Add to MetaCart
We have developed direct methods for recovering the motion of an observer in a static environment in th e case of pure rotation, pure translation, and arbitrary motion when the rotation is known. Some of these methods are based on the minimization of the difference between the observed time derivative of brightness and that predicted from the spatial brightness gradient, given the estimated motion. We minimize the square of the integral of this difference taken over the image region of interest. Other methods presented here exploit the fact that surfaces have to be in front of the observer in order to be seen. We do not establish point correspondences, nor do we estimate the optical flow. We use only firstorde r derivatives of the image brightness, and we do not assume an analytic form for the surface. We show tha t the field of view should be large to accurately recover the components of motion in the direction towar d the image region. We also demonstrate the importance of points where the time derivative of brightness is small and discuss difficulties resulting from very large depth ranges. We emphasize the need for adequat e filtering of the image data before sampling to avoid aliasing, in both the spatial and tempora l dimensions. I.
Optimal motion and structure estimation
 IEEE Trans. Pattern Anal. Mach. Intell
, 1993
"... This paper studies optimal estimation for motion and structure from point correspondences. (1) A study of the characteristics of thc problem provides insight into the need for optimal estimation. (2) Methods have been developed for optimal estimation with known or unknown noise distribution. The sim ..."
Abstract

Cited by 150 (5 self)
 Add to MetaCart
This paper studies optimal estimation for motion and structure from point correspondences. (1) A study of the characteristics of thc problem provides insight into the need for optimal estimation. (2) Methods have been developed for optimal estimation with known or unknown noise distribution. The simulations showed that the optimal estimations achieve remarkable improvement over the preliminary estimates given by the linear algorithm. (3) An approach to estimating errors in the optimized solution is presented. (4) The performance of the algorithm is compared with a theoretical lower bound CramCrRao bound. Simulations show that the actual errors have essentially reached the bound. (5) A batch leastsquares technique (LevenbergMarquardt) and a sequential leastsquares technique (iterated extended Kalman filtering) are analyzed and compared. The analysis and experiments show that, in general, a batch technique will perform better than a sequential technique for any nonlinear problems. Recursive batch processing technique is proposed for nonlinear problems that require recursive estimation. 1.
Relative Orientation
 International Journal of Computer Vision
, 1990
"... Abstract: Before corresponding points in images taken with two cameras can be used to recover distances to objects in a scene, one has to determine the position and orientation of one camera relative to the other. This is the classic photogrammetric problem of relative orientation, central to the in ..."
Abstract

Cited by 149 (2 self)
 Add to MetaCart
Abstract: Before corresponding points in images taken with two cameras can be used to recover distances to objects in a scene, one has to determine the position and orientation of one camera relative to the other. This is the classic photogrammetric problem of relative orientation, central to the interpretation of binocular stereo information. Iterative methods for determining relative orientation were developed long ago; without them we would not have most of the topographic maps we do today. Relative orientation is also of importance in the recovery of motion and shape from an image sequence when successive frames are widely separated in time. Workers in motion vision are rediscovering some of the methods of photogrammetry. Described here is a simple iterative scheme for recovering relative orientation that, unlike existing methods, does not require a good initial guess for the baseline and the rotation. The data required is a pair of bundles of corresponding rays from the two projection centers to points in the scene. It is well known that at least five pairs of rays are needed. Less appears to be known about the existence of multiple solutions and their interpretation. These issues are discussed here. The unambiguous determination of all of the parameters of relative orientation is not possible when the observed points lie on a critical surface. These surfaces and their degenerate forms are analysed as well.