Results 1  10
of
29
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 1055 (32 self)
 Add to MetaCart
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.
Vision Guided Navigation for A Nonholonomic Mobile Robot
 IEEE TRANSACTIONS ON ROBOTICS AND AUTOMATION
, 1997
"... Visual servoing, i.e. the use of the vision sensor in feedback control, has been of increasing interest. A fair amount of work has been done in applications in autonomous driving, manipulation, mobile robot navigation and surveillance. However, the theoretical and analytical aspects of the problem h ..."
Abstract

Cited by 53 (5 self)
 Add to MetaCart
Visual servoing, i.e. the use of the vision sensor in feedback control, has been of increasing interest. A fair amount of work has been done in applications in autonomous driving, manipulation, mobile robot navigation and surveillance. However, the theoretical and analytical aspects of the problem have not received much attention. Furthermore, the problem of estimation from the vision measurements has been considered separately from the design of the control strategies. Instead of addressing the pose estimation and control problems separately, we attempt to characterize the types of control tasks which can be achieved using only quantities directly measurable in the image, bypassing the pose estimation phase. We consider the navigation task for a nonholonomic ground mobile base tracking an arbitrarily shaped continuous ground curve. This tracking problem is formulated as one of controlling the shape of the curve in the image plane. We study the controllability of the system characteriz...
Reducing "Structure From Motion": a General Framework for Dynamic Vision  Part 2: Experimental Evaluation
 IEEE trans. PAMI
, 1998
"... A number of methods have been proposed in the literature for estimating scenestructure and egomotion from a sequence of images using dynamical models. Despite the fact that all methods may be derived from a "natural " dynamical model within a unified framework, from an engineering ..."
Abstract

Cited by 33 (2 self)
 Add to MetaCart
A number of methods have been proposed in the literature for estimating scenestructure and egomotion from a sequence of images using dynamical models. Despite the fact that all methods may be derived from a &quot;natural &quot; dynamical model within a unified framework, from an engineering perspective there are a number of tradeoffs that lead to different strategies depending upon the applications and the goals one is targeting. We want to characterize and compare the properties of each model such that the engineer may choose the one best suited to the specific application. We analyze the properties of filters derived from each dynamical model under a variety of experimental conditions, assess the accuracy of the estimates, their robustness to measurement noise, sensitivity to initial conditions and visual angle, effects of the basrelief ambiguity and occlusions, dependence upon the number of image measurements and their sampling rate.
Optimal Structure From Motion: Local Ambiguities and Global Estimates
, 1998
"... "Structure From Motion" (SFM) refers to the problem of estimating threedimensional information about the environment from the motion of its twodimensional projection onto a surface (for instance the retina). We present an analysis of SFM from the point of view of noise. This analysis res ..."
Abstract

Cited by 33 (1 self)
 Add to MetaCart
"Structure From Motion" (SFM) refers to the problem of estimating threedimensional information about the environment from the motion of its twodimensional projection onto a surface (for instance the retina). We present an analysis of SFM from the point of view of noise. This analysis results in algorithms that are provably convergent and provably optimal with respect to a chosen norm. In particular, we cast SFM as a nonlinear optimization problem and define a bilinear projection iteration that converges to fixed points of a certain costfunction. We then show that such fixed points are "fundamental", i.e. intrinsic to the problem of SFM and not an artifact introduced by our algorithms. We classify and interpret geometrically local extrema, and we argue that they correspond to phenomena observed in visual psychophysics. Finally, we show under what conditions it is possible  given convergence to a local extremum  to "jump" to the valley containing the optimum; this leads us to sugges...
Recursive Motion and Structure Estimation with Complete Error Characterization
, 1993
"... We present an algorithm that performs recursive estimation of egomotion and ambient structure from a stream of monocular perspective images of a number of feature points. The algorithm is based on an Extended Kalman Filter (EKF) that integrates over time the instantaneous motion and structure measu ..."
Abstract

Cited by 28 (8 self)
 Add to MetaCart
We present an algorithm that performs recursive estimation of egomotion and ambient structure from a stream of monocular perspective images of a number of feature points. The algorithm is based on an Extended Kalman Filter (EKF) that integrates over time the instantaneous motion and structure measurements computed by a 2perspectiveviews step. Key features of our filter are (1) global observability of the model, (2) complete online characterization of the uncertainty of the measurements provided by the twoviews step. The filter is thus guaranteed to be wellbehaved regardless of the particular motion undergone by the observer. Regions of motion space that do not allow recovery of structure (e.g. pure rotation) may be crossed while maintaining good estimates of structure and motion; whenever reliable measurements are available they are exploited. The algorithm works well for arbitrary motions with minimal smoothness assumptions and no ad hoc tuning. Simulations are presented that il...
Optimal Structure from Motion: Local Ambiguities and Global Estimates
, 2000
"... “Structure From Motion” (SFM) refers to the problem of estimating spatial properties of a threedimensional scene from the motion of its projection onto a twodimensional surface, such as the retina. We present an analysis of SFM which results in algorithms that are provably convergent and provably o ..."
Abstract

Cited by 23 (5 self)
 Add to MetaCart
“Structure From Motion” (SFM) refers to the problem of estimating spatial properties of a threedimensional scene from the motion of its projection onto a twodimensional surface, such as the retina. We present an analysis of SFM which results in algorithms that are provably convergent and provably optimal with respect to a chosen norm. In particular, we cast SFM as the minimization of a highdimensional quadratic cost function, and show how it is possible to reduce it to the minimization of a twodimensional function whose stationary points are in onetoone correspondence with those of the original cost function. As a consequence, we can plot the reduced cost function and characterize the configurations of structure and motion that result in local minima. As an example, we discuss two local minima that are associated with wellknown visual illusions. Knowledge of the topology of the residual in the presence of such local minima allows us to formulate minimization algorithms that, in addition to provably converge to stationary points of the original cost function, can switch between different local extrema in order to converge to the global minimum, under suitable conditions. We also offer an experimental study of the distribution of the estimation error in the presence of noise in the measurements, and characterize the sensitivity of the algorithm using the structure of Fisher’s Information matrix.
Optimal and Suboptimal Structure From Motion
 Proceedings of International Conference on Computer Vision
, 1997
"... "Structure From Motion" (SFM) refers to the problem of estimating threedimensional information about the environment from the motion of its twodimensional projection onto a surface (for instance the retina). Noise plays an important role in this problem, but it has been addressed only ma ..."
Abstract

Cited by 13 (0 self)
 Add to MetaCart
"Structure From Motion" (SFM) refers to the problem of estimating threedimensional information about the environment from the motion of its twodimensional projection onto a surface (for instance the retina). Noise plays an important role in this problem, but it has been addressed only marginally in more than twenty years of research. We present an analysis of SFM from the point of view of noise. This analysis results in algorithms that are provably convergent and provably optimal with respect to a chosen norm. In particular, we cast SFM as a nonlinear optimization problem and define a bilinear projection iteration that converges to fixed points of a certain costfunction. We then show that such fixed points are "fundamental", i.e. are intrinsic to the problem of SFM and not an artifact introduced by our algorithms. We classify and interpret geometrically local extrema, and we argue that they correspond to phenomena observed in visual psychophysics. Finally, we show under what conditi...
A General Approach for Egomotion Estimation with Omnidirectional Images
 In IEEE Workshop on Omnidirectional Vision
, 2002
"... Computing a camera's egomotion from an image sequence is easier to accomplish when a spherical retina is used, as opposed to a standard retinal plane. On a spherical field of view both the focus of expansion and contraction are visible, whereas for a planar retina that is not necessarily the c ..."
Abstract

Cited by 12 (0 self)
 Add to MetaCart
Computing a camera's egomotion from an image sequence is easier to accomplish when a spherical retina is used, as opposed to a standard retinal plane. On a spherical field of view both the focus of expansion and contraction are visible, whereas for a planar retina that is not necessarily the case.
Scene and Motion Reconstruction from Defocused and MotionBlurred Images via Anisotropic Diffusion
 In Computer Vision  ECCV 2004, 8th European Conference on Computer Vision
, 2004
"... We propose a solution to the problem of inferring the depth map, radiance and motion field of a scene from a collection of motionblurred and defocused images. We model motionblurred and defocused images as the solution of an anisotropic diffusion equation, whose initial conditions depend on the ..."
Abstract

Cited by 10 (0 self)
 Add to MetaCart
We propose a solution to the problem of inferring the depth map, radiance and motion field of a scene from a collection of motionblurred and defocused images. We model motionblurred and defocused images as the solution of an anisotropic diffusion equation, whose initial conditions depend on the radiance and whose diffusion tensor encodes the shape of the scene, the motion field and the optics parameters. We show that this model is wellposed and propose an efficient algorithm to infer the unknowns of the model. Inference is performed by minimizing the discrepancy between the measured defocused images and the ones synthesized via diffusion. Since the problem is illposed, we also introduce additional Tikhonov regularization terms. The resulting method is fast and robust to noise as shown by experiments with both synthetic and real data.
Omnidirectional Egomotion Estimation From Backprojection Flow
 IN OMNIVIS
, 2003
"... The current stateoftheart for egomotion estimation with omnidirectional cameras is to map the optical flow to the sphere and then apply egomotion algorithms for spherical projection. In this paper, we propose to backproject image points to a virtual curved retina that is intrinsic to the geometr ..."
Abstract

Cited by 7 (1 self)
 Add to MetaCart
The current stateoftheart for egomotion estimation with omnidirectional cameras is to map the optical flow to the sphere and then apply egomotion algorithms for spherical projection. In this paper, we propose to backproject image points to a virtual curved retina that is intrinsic to the geometry of the central panoramic camera, and compute the optical flow on this retina: the socalled backprojection flow. We show that wellknown egomotion algorithms can be easily adapted to work with the backprojection flow. We present extensive simulation results showing that in the presence of noise, egomotion algorithms perform better by using backprojection flow when the camera translation is in the XY plane. Thus, the proposed method is preferable in applications where there is no Zaxis translation, such as ground robot navigation.