• Documents
  • Authors
  • Tables
  • Log in
  • Sign up
  • MetaCart
  • Donate

CiteSeerX logo

Advanced Search Include Citations
Advanced Search Include Citations | Disambiguate

Motion layer extraction in the presence of occlusion using graph cut (0)

by J Xiao, M Shah
Venue:In Proc. CVPR’04
Add To MetaCart

Tools

Sorted by:
Results 1 - 10 of 98
Next 10 →

Computer Vision: Algorithms and Applications

by Richard Szeliski , 2010
"... ..."
Abstract - Cited by 246 (2 self) - Add to MetaCart
Abstract not found

Object segmentation by long term analysis of point trajectories

by Thomas Brox, Jitendra Malik - In Proc. European Conference on Computer Vision , 2010
"... Abstract. Unsupervised learning requires a grouping step that defines which data belong together. A natural way of grouping in images is the segmentation of objects or parts of objects. While pure bottom-up segmentation from static cues is well known to be ambiguous at the object level, the story ch ..."
Abstract - Cited by 142 (9 self) - Add to MetaCart
Abstract. Unsupervised learning requires a grouping step that defines which data belong together. A natural way of grouping in images is the segmentation of objects or parts of objects. While pure bottom-up segmentation from static cues is well known to be ambiguous at the object level, the story changes as soon as objects move. In this paper, we present a method that uses long term point trajectories based on dense optical flow. Defining pair-wise distances between these trajectories allows to cluster them, which results in temporally consistent segmentations of moving objects in a video shot. In contrast to multi-body factorization, points and even whole objects may appear or disappear during the shot. We provide a benchmark dataset and an evaluation method for this so far uncovered setting. 1
(Show Context)

Citation Context

...he quality of these methods depends on picking a pair of frames with a clear motion difference between the objects. Some works have combined the flow analysis with the learning of an appearance model =-=[14,15]-=-. This leads to temporally consistent layers across multiple frames, but comes along with an increased number of mutually dependent variables. Rather than relying on optical flow, [16] estimates the m...

Bilayer segmentation of live video

by A. Criminisi, G. Cross, A. Blake, V. Kolmogorov - In: IEEE Conference on Computer Vision and Pattern Recognition , 2006
"... a input sequence b automatic layer separation and background substitution in three different frames Figure 1: An example of automatic foreground/background segmentation in monocular image sequences. Despite the challenging foreground motion the person is accurately extracted from the sequence and th ..."
Abstract - Cited by 107 (3 self) - Add to MetaCart
a input sequence b automatic layer separation and background substitution in three different frames Figure 1: An example of automatic foreground/background segmentation in monocular image sequences. Despite the challenging foreground motion the person is accurately extracted from the sequence and then composited free of aliasing upon a different background; a useful tool in video-conferencing applications. The sequences and ground truth data used throughout this paper are available from [1]. This paper presents an algorithm capable of real-time separation of foreground from background in monocular video sequences. Automatic segmentation of layers from colour/contrast or from motion alone is known to be error-prone. Here motion, colour and contrast cues are probabilistically fused together with spatial and temporal priors to infer layers accurately and efficiently. Central to our algorithm is the fact that pixel velocities are not needed, thus removing the need for optical flow estimation, with its tendency to error and computational expense. Instead, an efficient motion vs nonmotion classifier is trained to operate directly and jointly on intensity-change and contrast. Its output is then fused with colour information. The prior on segmentation is represented by a second order, temporal, Hidden Markov Model, together with a spatial MRF favouring coherence except where contrast is high. Finally, accurate layer segmentation and explicit occlusion detection are efficiently achieved by binary graph cut. The segmentation accuracy of the proposed algorithm is quantitatively evaluated with respect to existing groundtruth data and found to be comparable to the accuracy of a state of the art stereo segmentation algorithm. Foreground/background segmentation is demonstrated in the application of live background substitution and shown to generate convincingly good quality composite video. 1 1.
(Show Context)

Citation Context

...termination as in video-matting [8, 9], but with computational efficiency sufficient to attain live streaming speed. Layer extraction from images or sequences has long been an active area of research =-=[2, 4, 10, 13, 20, 21, 22, 23]-=-. The challenge addressed here is to segment the foreground layer efficiently without restrictions on appearance, motion, camera viewpoint or shape, and sufficiently accurately for use in background s...

Dynamic Graph Cuts for Efficient Inference in Markov Random Fields

by Pushmeet Kohli, Philip H. S. Torr
"... In this paper we present a fast new fully dynamic algorithm for the st-mincut/max-flow problem. We show how this algorithm can be used to efficiently compute MAP solutions for certain dynamically changing MRF models in computer vision such as image segmentation. Specifically, given the solution of ..."
Abstract - Cited by 76 (3 self) - Add to MetaCart
In this paper we present a fast new fully dynamic algorithm for the st-mincut/max-flow problem. We show how this algorithm can be used to efficiently compute MAP solutions for certain dynamically changing MRF models in computer vision such as image segmentation. Specifically, given the solution of the max-flow problem on a graph, the dynamic algorithm efficiently computes the maximum flow in a modified version of the graph. The time taken by it is roughly proportional to the total amount of change in the edge weights of the graph. Our experiments show that, when the number of changes in the graph is small, the dynamic algorithm is significantly faster than the best known static graph cut algorithm. We test the performance of our algorithm on one particular problem: the object-background segmentation problem for video. It should be noted that the application of our algorithm is not limited to the above problem, the algorithm is generic and can be used to yield similar improvements in many other cases that involve dynamic change.
(Show Context)

Citation Context

...sion to compute the maximum a posteriori (MAP) solutions for various discrete pixel labelling problems such as image restoration, segmentation, voxel occupancy and stereo [17], [18], [24], [26]–[30], =-=[36]-=-, [38]. One of the primary reasons behind their growing popularity is the availability of efficient algorithms with low polynomial time algorithmic complexity for computing the maximum flow (max-flow)...

Track to the Future: Spatio-temporal Video Segmentation with Long-range Motion Cues

by José Lezama, Karteek Alahari, Josef Sivic, Ivan Laptev, École Normale, Supérieure Cachan
"... Video provides not only rich visual cues such as motion and appearance, but also much less explored long-range temporal interactions among objects. We aim to capture such interactions and to construct a powerful intermediatelevel video representation for subsequent recognition. Motivated by this goa ..."
Abstract - Cited by 53 (2 self) - Add to MetaCart
Video provides not only rich visual cues such as motion and appearance, but also much less explored long-range temporal interactions among objects. We aim to capture such interactions and to construct a powerful intermediatelevel video representation for subsequent recognition. Motivated by this goal, we seek to obtain spatio-temporal oversegmentation of a video into regions that respect object boundaries and, at the same time, associate object pixels over many video frames. The contributions of this paper are two-fold. First, we develop an efficient spatiotemporal video segmentation algorithm, which naturally incorporates long-range motion cues from the past and future frames in the form of clusters of point tracks with coherent motion. Second, we devise a new track clustering cost function that includes occlusion reasoning, in the form of depth ordering constraints, as well as motion similarity along the tracks. We evaluate the proposed approach on a challenging set of video sequences of office scenes from feature length movies. 1.
(Show Context)

Citation Context

...sed segmentation method of Grundmann et al. [16] and extend it by incorporating long-range motion cues into the segmentation. There has been significant related work on layered representation methods =-=[33, 36, 38]-=-, which learn parametric motion and appearance models of video. In this line of research Kumar et al. [20] demonstrate detection and tracking of articulated models of walking people and animals, but a...

Graph Cuts in Vision and Graphics: Theories and Applications

by Yuri Boykov, Olga Veksler - “MATH. MODELS OF C.VISION: THE HANDBOOK”, EDTS. PARAGIOS, CHEN, FAUGERAS
"... Combinatorial min-cut algorithms on graphs emerged as an increasingly useful tool for problems in vision. Typically, the use of graphcuts is motivated by one of the following two reasons. Firstly, graph-cuts allow geometric interpretation; under certain conditions a cut on a graph can be seen as a ..."
Abstract - Cited by 39 (2 self) - Add to MetaCart
Combinatorial min-cut algorithms on graphs emerged as an increasingly useful tool for problems in vision. Typically, the use of graphcuts is motivated by one of the following two reasons. Firstly, graph-cuts allow geometric interpretation; under certain conditions a cut on a graph can be seen as a hypersurface in N-D space embedding the corresponding graph. Thus, many applications in vision and graphics use min-cut algorithms as a tool for computing optimal hypersurfaces. Secondly, graphcuts also work as a powerful energy minimization tool for a fairly wide class of binary and non-binary energies that frequently occur in early vision. In some cases graph cuts produce globally optimal solutions. More generally, there are iterative graph-cut based techniques that produce provably good approximations which (were empirically shown to) correspond to high-quality solutions in practice. Thus, another large group of applications use graph-cuts as an optimization technique for low-level vision problems based on global energy formulations. This chapter is intended as a tutorial illustrating these two aspects of graph-cuts in the context of problems in computer vision and graphics. We explain general theoretical properties that motivate the use of graph cuts, as well as, show their limitations.

Illumination-Invariant Tracking via Graph Cuts

by Daniel Freedman, Matthew W. Turek - IN PROC. OF IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION , 2005
"... Illumination changes are a ubiquitous problem in computer vision. They present a challenge in many applications, including tracking: for example, an object may move in and out of a shadow. We present a new tracking algorithm which is insensitive to illumination changes, while at the same time using ..."
Abstract - Cited by 30 (0 self) - Add to MetaCart
Illumination changes are a ubiquitous problem in computer vision. They present a challenge in many applications, including tracking: for example, an object may move in and out of a shadow. We present a new tracking algorithm which is insensitive to illumination changes, while at the same time using all of the available photometric information. The algorithm is based on computing an illumination-invariant optical flow field; the computation is made robust by using a graph cuts formulation. Experimentally, the new technique is shown to quite reliable in both synthetic and real sequences, dealing with a variety of illumination changes that cause problems for density based trackers.

Accurate motion layer segmentation and matting

by Jiangjian Xiao, Mubarak Shah - In CVPR , 2005
"... Given a video sequence, obtaining accurate layer segmentation and alpha matting is very important for various applications. However, when a non-textured or smooth area is present in the scene, the segmentation based on only single motion cue usually cannot provide satisfactory results. Conversely, t ..."
Abstract - Cited by 28 (2 self) - Add to MetaCart
Given a video sequence, obtaining accurate layer segmentation and alpha matting is very important for various applications. However, when a non-textured or smooth area is present in the scene, the segmentation based on only single motion cue usually cannot provide satisfactory results. Conversely, the most matting approaches require a smooth assumption on foreground and background to obtain a good result. In this paper, we combine the merits of motion segmentation and alpha matting technique together to simultaneously achieve high-quality layer segmentation and alpha mattes. First, we explore a general occlusion constraint and design a novel graph cuts framework to solve the layerbased motion segmentation problem for the textured regions using multiple frames. Then, an alpha matting technique is further used to refine the segmentation and resolve the nontextured ambiguities by determining proper alpha values for the foreground and background respectively. 1
(Show Context)

Citation Context

... by determining proper alpha values for the foreground and background respectively. 1 Introduction Layer-based motion segmentation has been investigated by computer vision researchers for a long time =-=[2, 9, 16]-=-. Given a video sequence, motion segmentation consists of two major steps: (1) layer clustering which is to determine the number of layers in the scene and the associated motion parameters for each la...

Occlusion Boundary Detection and Figure/Ground Assignment from Optical Flow

by Patrik Sundberg, Thomas Brox, Michael Maire, Pablo Arbeláez, Jitendra Malik
"... In this work, we propose a contour and region detector for video data that exploits motion cues and distinguishes occlusion boundaries from internal boundaries based on optical flow. This detector outperforms the state-of-the-art on the benchmark of Stein and Hebert [24], improving average precision ..."
Abstract - Cited by 27 (2 self) - Add to MetaCart
In this work, we propose a contour and region detector for video data that exploits motion cues and distinguishes occlusion boundaries from internal boundaries based on optical flow. This detector outperforms the state-of-the-art on the benchmark of Stein and Hebert [24], improving average precision from.58 to.72. Moreover, the optical flow on and near occlusion boundaries allows us to assign a depth ordering to the adjacent regions. To evaluate performance on this edge-based figure/ground labeling task, we introduce a new video dataset that we believe will support further research in the field by allowing quantitative comparison of computational models for occlusion boundary detection, depth ordering and segmentation in video sequences. 1.
(Show Context)

Citation Context

...n literature, many works have dealt with the problem of optical flow estimation over the past three decades, and there have been numerous approaches to make use of the optical flow field for grouping =-=[10, 22, 23, 28, 9]-=-. Most of them are similar to the work of Wang and Adelson, which proposes to partition the image into motion layers by clustering similar optical flow vectors according to a parametric motion model [...

A feature-based approach for dense segmentation and estimation of large disparity motion

by Josh Wills, Sameer Agarwal, Serge Belongie - IJCV
"... We present a novel framework for motion segmentation that combines the concepts of layer-based methods and feature-based motion estimation. We estimate the initial correspondences by comparing vectors of filter outputs at interest points, from which we compute candidate scene relations via random sa ..."
Abstract - Cited by 22 (0 self) - Add to MetaCart
We present a novel framework for motion segmentation that combines the concepts of layer-based methods and feature-based motion estimation. We estimate the initial correspondences by comparing vectors of filter outputs at interest points, from which we compute candidate scene relations via random sampling of minimal subsets of correspondences. We achieve a dense, piecewise smooth assignment of pixels to motion layers using a fast approximate graphcut algorithm based on a Markov random field formulation. We demonstrate our approach on image pairs containing large inter-frame motion and partial occlusion. The approach is efficient and it successfully segments scenes with inter-frame disparities previously beyond the scope of layer-based motion segmentation methods. We also present an extension that accounts for the case of non-planar motion, in which we use our planar motion segmentation results as an initialization for a regularized Thin Plate Spline fit. In addition, we present applications of our method to automatic object removal and to structure from motion. 1
(Show Context)

Citation Context

...g about occlusion ordering constraints over more than than two frames, one can retain and explicitly label occluded pixels in the output segmentation; see for example the recent work of Xiao and Shah =-=[51]-=-. 1. Detect interest points in I 2. Perturb each interest point 3. Find the matching points in I ′ 4. For i = 1:Ns Pick tuples of correspondences Estimate the warp Store inlier count 5. Prune the list...

Powered by: Apache Solr
  • About CiteSeerX
  • Submit and Index Documents
  • Privacy Policy
  • Help
  • Data
  • Source
  • Contact Us

Developed at and hosted by The College of Information Sciences and Technology

© 2007-2018 The Pennsylvania State University