Results 1  10
of
44
Piecewisesmooth dense optical flow via level sets
 Vision and Image Analysis Laboratory, School of Electrical Engineering, Tel Aviv
, 2005
"... We propose a new algorithm for dense optical flow computation. Dense optical flow schemes are challenged by the presence of motion discontinuities. In state of the art optical flow methods, oversmoothing of flow discontinuities accounts for most of the error. A breakthrough in the performance of op ..."
Abstract

Cited by 19 (2 self)
 Add to MetaCart
We propose a new algorithm for dense optical flow computation. Dense optical flow schemes are challenged by the presence of motion discontinuities. In state of the art optical flow methods, oversmoothing of flow discontinuities accounts for most of the error. A breakthrough in the performance of optical flow computation has recently been achieved by Brox et al. Our algorithm embeds their functional within a two phase active contour segmentation framework. Piecewisesmooth flow fields are accommodated and flow boundaries are crisp. Experimental results show the superiority of our algorithm with respect to alternative techniques. We also study a special case of optical flow computation, in which the camera is static. In this case we utilize a known background image to separate the moving elements in the sequence from the static elements. Tests with challenging real world sequences demonstrate the performance gains made possible by incorporating the static camera assumption in our algorithm. 1
C.: Spectral clustering of linear subspaces for motion segmentation
 In: IEEE I. Conf. Comp. Vis
"... This paper studies automatic segmentation of multiple motions from tracked feature points through spectral embedding and clustering of linear subspaces. We show that the dimension of the ambient space is crucial for separability, and that low dimensions chosen in prior work are not optimal. We sugge ..."
Abstract

Cited by 11 (0 self)
 Add to MetaCart
This paper studies automatic segmentation of multiple motions from tracked feature points through spectral embedding and clustering of linear subspaces. We show that the dimension of the ambient space is crucial for separability, and that low dimensions chosen in prior work are not optimal. We suggest lower and upper bounds together with a datadriven procedure for choosing the optimal ambient dimension. Application of our approach to the Hopkins155 video benchmark database uniformly outperforms a range of stateoftheart methods both in terms of segmentation accuracy and computational speed. 1.
Motion segmentation at any speed
 in Proceedings of British Machine Vision Conference
, 2006
"... We present an incremental approach to motion segmentation. Feature points are detected and tracked throughout an image sequence, and the features are grouped using a regiongrowing algorithm with an affine motion model. The primary parameter used by the algorithm is the amount of evidence that must ..."
Abstract

Cited by 8 (1 self)
 Add to MetaCart
We present an incremental approach to motion segmentation. Feature points are detected and tracked throughout an image sequence, and the features are grouped using a regiongrowing algorithm with an affine motion model. The primary parameter used by the algorithm is the amount of evidence that must accumulate before features are grouped. Contrasted with previous work, the algorithm allows for a variable number of image frames to affect the decision process, thus enabling objects to be detected independently of their velocity in the image. Procedures are presented for grouping features, measuring the consistency of the resulting groups, assimilating new features into existing groups, and splitting groups over time. Experimental results on a number of challenging image sequences demonstrate the effectiveness of the technique. 1
Actionable Information in Vision
"... I propose a notion of visual information as the complexity not of the raw images, but of the images after the effects of nuisance factors such as viewpoint and illumination are discounted. It is rooted in ideas of J. J. Gibson, and stands in contrast to traditional information as entropy or coding l ..."
Abstract

Cited by 7 (6 self)
 Add to MetaCart
I propose a notion of visual information as the complexity not of the raw images, but of the images after the effects of nuisance factors such as viewpoint and illumination are discounted. It is rooted in ideas of J. J. Gibson, and stands in contrast to traditional information as entropy or coding length of the data regardless of its use, and regardless of the nuisance factors affecting it. The noninvertibility of nuisances such as occlusion and quantization induces an “information gap ” that can only be bridged by controlling the data acquisition process. Measuring visual information entails early vision operations, tailored to the structure of the nuisances so as to be “lossless ” with respect to visual decision and control tasks (as opposed to data transmission and storage tasks implicit in traditional Information Theory). I illustrate these ideas on visual exploration, whereby a “Shannonian Explorer ” guided by the entropy of the data navigates unaware of the structure of the physical space surrounding it, while a “Gibsonian Explorer ” is guided by the topology of the environment, despite measuring only images of it, without performing 3D reconstruction. The operational definition of visual information suggests desirable properties that a visual representation should possess to best accomplish visionbased decision and control tasks. 1.
A New Geometric Metric in the Space of Curves, and Applications to Tracking Deforming Objects by Prediction and Filtering
, 2010
"... We define a novel metric on the space of closed planar curves. According to this metric centroid translations, scale changes and deformations are orthogonal, and the metric is also invariant with respect to reparameterizations of the curve. The Riemannian structure that is induced on the space of cu ..."
Abstract

Cited by 7 (0 self)
 Add to MetaCart
We define a novel metric on the space of closed planar curves. According to this metric centroid translations, scale changes and deformations are orthogonal, and the metric is also invariant with respect to reparameterizations of the curve. The Riemannian structure that is induced on the space of curves is a smooth Riemannian manifold, which is isometric to a classical wellknown manifold. As a consequence, geodesics and gradients of energies defined on the space can be computed using fast closedform formulas, and this has obvious benefits in numerical applications. The obtained Riemannian manifold of curves is apt to address complex problems in computer vision; one such example is the tracking of highly deforming objects. Previous works have assumed that the object deformation is smooth, which is realistic for the tracking problem, but most have restricted the deformation to belong to a finitedimensional group – such as affine motions – or to finitelyparameterized models. This is too restrictive for highly deforming objects such as the contour of a beating heart. We adopt the smoothness assumption implicit in previous work, but we lift the restriction to finitedimensional motions/deformations. We define a dynamical model in this Riemannian manifold of curves, and use it to perform filtering and prediction to infer and extrapolate not just the pose (a finitely parameterized quantity) of an object, but its deformation (an infinitedimensional quantity) as well. We illustrate these ideas using a simple firstorder dynamical model, and show that it can be effective even on data sets where existing methods fail. 1
TriangleFlow: Optical Flow with Triangulationbased HigherOrder Likelihoods
"... Abstract. We use a simple yet powerful higherorder conditional random field (CRF) to model optical flow. It consists of a standard photoconsistency cost and a prior on affine motions both modeled in terms of higherorder potential functions. Reasoning jointly over a large set of unknown variables p ..."
Abstract

Cited by 7 (1 self)
 Add to MetaCart
Abstract. We use a simple yet powerful higherorder conditional random field (CRF) to model optical flow. It consists of a standard photoconsistency cost and a prior on affine motions both modeled in terms of higherorder potential functions. Reasoning jointly over a large set of unknown variables provides more reliable motion estimates and a robust matching criterion. One of the main contributions is that unlike previous regionbased methods, we omit the assumption of constant flow. Instead, we consider local affine warps whose likelihood energy can be computed exactly without approximations. This results in a tractable, socalled, higherorder likelihood function. We realize this idea by employing triangulation meshes which immensely reduce the complexity of the problem. Optimization is performed by hierarchical QPBO moves and an adaptive mesh refinement strategy. Experiments show that we achieve highquality motion fields on several data sets including the Middlebury optical flow database. 1
Motion Segmentation with Occlusions on the Superpixel Graph
"... We present a motion segmentation algorithm that partitions the image plane into disjoint regions based on their parametric motion. It relies on a finer partitioning of the image domain into regions of uniform photometric properties, with motion segments made of unions of such “superpixels.” We explo ..."
Abstract

Cited by 6 (0 self)
 Add to MetaCart
We present a motion segmentation algorithm that partitions the image plane into disjoint regions based on their parametric motion. It relies on a finer partitioning of the image domain into regions of uniform photometric properties, with motion segments made of unions of such “superpixels.” We exploit recent advances in combinatorial graph optimization that yield computationally efficient estimates. The energy functional is built on a superpixel graph, and is iteratively minimized by computing a parametric motion model in closedform, followed by a graph cut of the superpixel adjacency graph. It generalizes naturally to multilabel partitions that can handle multiple motions. 1.
RealTime Motion Segmentation of Sparse Feature Points at Any Speed
"... Abstract—We present a realtime incremental approach to motion segmentation operating on sparse feature points. In contrast to previous work, the algorithm allows for a variable number of image frames to affect the segmentation process, thus enabling an arbitrary number of objects traveling at diffe ..."
Abstract

Cited by 6 (0 self)
 Add to MetaCart
Abstract—We present a realtime incremental approach to motion segmentation operating on sparse feature points. In contrast to previous work, the algorithm allows for a variable number of image frames to affect the segmentation process, thus enabling an arbitrary number of objects traveling at different relative speeds to be detected. Feature points are detected and tracked throughout an image sequence, and the features are grouped using a spatially constrained expectation–maximization (EM) algorithm that models the interactions between neighboring features using the Markov assumption. The primary parameter used by the algorithm is the amount of evidence that must accumulate before features are grouped. A statistical goodnessoffit test monitors the change in the motion parameters of a group over time in order to automatically update the reference frame. Experimental results on a number of challenging image sequences demonstrate the effectiveness and computational efficiency of the technique. Index Terms—Expectation–maximization (EM), feature tracking, motion segmentation. I.
Inferring segmented dense motion layers using 5d tensor voting
 IEEE Trans. Pattern Anal. Machine Intell
, 2008
"... Abstract—We present a novel local spatiotemporal approach to produce motion segmentation and dense temporal trajectories from an image sequence. A common representation of image sequences is a 3D spatiotemporal volume ðx; y; tÞ, and its corresponding mathematical formalism is the fiber bundle. Howev ..."
Abstract

Cited by 5 (1 self)
 Add to MetaCart
Abstract—We present a novel local spatiotemporal approach to produce motion segmentation and dense temporal trajectories from an image sequence. A common representation of image sequences is a 3D spatiotemporal volume ðx; y; tÞ, and its corresponding mathematical formalism is the fiber bundle. However, directly enforcing the spatiotemporal smoothness constraint is difficult in the fiber bundle representation. Thus, we convert the representation into a new 5D space ðx; y; t; vx;vyÞ with an additional velocity domain, where each moving object produces a separate 3D smooth layer. The smoothness constraint is now enforced by extracting 3D layers using the tensor voting framework in a single step that solves both correspondence and segmentation simultaneously. Motion segmentation is achieved by identifying those layers and the dense temporal trajectories are obtained by converting the layers back into the fiber bundle representation. We proceed to address three applications (tracking, mosaic, and 3D reconstruction) that are hard to solve from the video stream directly because of the segmentation and dense matching steps but become straightforward with our framework. The approach does not make restrictive assumptions about the observed scene or camera motion and is therefore generally applicable. We present results on a number of data sets. Index Terms—Motion analysis, tensor voting, optical flow, segmentation, mosaicking. Ç 1
Joint motion estimation and segmentation of complex scenes with label costs and occlusion modeling
 In CVPR
, 2012
"... We propose a unified variational formulation for joint motion estimation and segmentation with explicit occlusion handling. This is done by a multilabel representation of the flow field, where each label corresponds to a parametric representation of the motion. We use a convex formulation of the mu ..."
Abstract

Cited by 5 (0 self)
 Add to MetaCart
We propose a unified variational formulation for joint motion estimation and segmentation with explicit occlusion handling. This is done by a multilabel representation of the flow field, where each label corresponds to a parametric representation of the motion. We use a convex formulation of the multilabel Potts model with label costs and show that the asymmetric mapuniqueness criterion can be integrated into our formulation by means of convex constraints. Explicit occlusion handling eliminates errors otherwise created by the regularization. As occlusions can occur only at object boundaries, a large number of objects may be required. By using a fast primaldual algorithm we are able to handle several hundred motion segments. Results are shown on several classical motion segmentation and optical flow examples. 1.