Motion segmentation via robust subspace separation in the presence of outlying, incomplete, or corrupted trajectories

Rao, Shankar; Tron, Roberto; Vidal, René; Ma, Yi

doi:10.1109/cvpr.2008.4587437

Cited by 191 publications

(146 citation statements)

References 22 publications

Supporting

Mentioning

143

Contrasting

Unclassified

Order By: Relevance

“…Apart from the numbers of the proposed technique we also report numbers for Generalized PCA (GPCA), Local Subspace Affinity (LSA) [18], and RANSAC using the code provided with the Hopkins dataset [8]. We also show results for the factorization method in [19], which can deal with either incomplete or corrupted trajectories (ALC). When running these methods, we use the same trajectories as for our own method.…”

Section: Dataset and Evaluation Methodsmentioning

confidence: 99%

“…This is nicely exploited by multi-body factorization methods [17,18,19,20]. These methods are particularly well suited to distinguish the 3D motion of rigid objects by exploiting the properties of an affine camera model.…”

Section: Related Workmentioning

confidence: 99%

“…On the other hand, they have two drawbacks: (1) factorization is generally quite sensitive to non-Gaussian noise, so few tracking errors can spoil the result; (2) it requires all trajectories to have the same length, so partial occlusion and disocclusion can actually not be handled. Recent works suggest ways to deal with these problems [19,20], but as the problems are inherent to factorization, this can only be successful up to a certain degree. For instance, it is still required that a sufficiently large subset of trajectories exists for the whole time line of the shot.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Object Segmentation by Long Term Analysis of Point Trajectories

Brox

Malik

2010

Lecture Notes in Computer Science

600

837

View full text Add to dashboard Cite

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.

show abstract

Section: Dataset and Evaluation Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Object Segmentation by Long Term Analysis of Point Trajectories

Brox

Malik

2010

Lecture Notes in Computer Science

600

837

View full text Add to dashboard Cite

show abstract

“…First, they assume that all trajectories are visible over all frames which severely limits their application to short video sequences. A few recent methods [13,6] have tried to overcome this limitation by assuming that only some trajectories span the whole sequence, but as the problem is inherent to factorization this can be successful only to a certain degree. Second, they assume that the objects are rigid, which limits their applica-bility.…”

Section: Introductionmentioning

confidence: 99%

Online Moving Camera Background Subtraction

Elqursh

Elgammal

2012

Computer Vision – ECCV 2012

View full text Add to dashboard Cite

Abstract. Recently several methods for background subtraction from moving camera were proposed. They use bottom up cues to segment video frames into foreground and background regions. Due to this lack of explicit models, they can easily fail to detect a foreground object when such cues are ambiguous in certain parts of the video. This becomes even more challenging when videos need to be processed online. We present a method that enables learning of pixel-based models for foreground and background regions and, in addition, segments each frame in an online framework. The method uses long term trajectories along with a Bayesian ltering framework to estimate motion and appearance models. We compare our method to previous approaches and show results on challenging video sequences. IntroductionOne may argue that the ultimate goal of computer vision is to learn and perceive the environment in the same way children learn. Without access to presegmented visual input, infants learn how to segment objects from background using low level cues. Inspired by this evidence, signi cant e ort in the computer vision community has focused on bottom up segmentation of images and videos. This has become ever more important with the proliferation of videos captured by moving cameras. Our goal is to develop an algorithm for foreground/background segmentation from freely moving camera in a online framework that is able to deal with arbitrary long sequences. Traditional video segmentation comes in di erent avors depending on the application, but falls short of achieving this goal. In background subtraction, moving foreground objects are segmented by learning a model of the background with the assumption of a static scene and camera. Motion segmentation methods attempt to segment sparse point trajectories based on coherency of motion. However, they lack a model of the appearance of foreground or background. Video object segmentation attempts to segment an object of interest from the video with no model of the scene background. On the other hand, there are several segmentation techniques that attempt to extend traditional image segmentation to the temporal domain. Such techniques are typically limited to segmenting a short window of time.It is frequently the case that low-level cues may be ambiguous if one only considers a short window of frames. Existing approaches either ignore this problem or resort to processing the whole video o ine. O ine methods can typically 2 Ali Elqursh, and Ahmed Elgmmal produce good results on short sequences but the complexity increases rapidly as more frames need to be processed. The key to solving this problem is to recognize that to handle long sequences in an online way one has to learn and maintain models for the background and foreground regions. Such models serve the purpose of compactly accumulating the evidence over a large number frames and are essential for high level vision tasks.The contribution of this paper is a novel online method that learns appearance and motion models of the scene (backgroun...

show abstract

“…Using the polynomials, we provide a solution to segment the inlying image features into corresponding motions. Finally, a comparison is conducted to quantitatively measure the performance of RAS with several established algorithms for motion segmentation (Torr and Zisserman 2000;Schindler and Suter 2005;Subbarao and Meer 2006;Rao et al 2008). The implementation of the algorithm and the benchmark scripts are available at http://perception.csl.illinois.edu/ras/.…”

Section: Introductionmentioning

confidence: 99%

Robust Algebraic Segmentation of Mixed Rigid-Body and Planar Motions from Two Views

et al. 2010

Self Cite

View full text Add to dashboard Cite

This paper studies segmentation of multiple rigidbody motions in a 3-D dynamic scene under perspective camera projection. We consider dynamic scenes that contain both 3-D rigid-body structures and 2-D planar structures. Based on the well-known epipolar and homography constraints between two views, we propose a hybrid perspective constraint (HPC) to unify the representation of rigidbody and planar motions. Given a mixture of K hybrid perspective constraints, we propose an algebraic process to partition image correspondences to the individual 3-D motions, called Robust Algebraic Segmentation (RAS). Particularly, we prove that the joint distribution of image correspondences is uniquely determined by a set of (2K)-th degree polynomials, a global signature for the union of K motions of possibly mixed type. The first and second deriva- tives of these polynomials provide a means to recover the association of the individual image samples to their respective motions. Finally, using robust statistics, we show that the polynomials can be robustly estimated in the presence of moderate image noise and outliers. We conduct extensive simulations and real experiments to validate the performance of the new algorithm. The results demonstrate that RAS achieves notably higher accuracy than most existing robust motion-segmentation methods, including random sample consensus (RANSAC) and its variations. The implementation of the algorithm is also two to three times faster than the existing methods. The implementation of the algorithm and the benchmark scripts are available at http:// perception.csl.illinois.edu/ras/.

show abstract

Motion segmentation via robust subspace separation in the presence of outlying, incomplete, or corrupted trajectories

Cited by 191 publications

References 22 publications

Object Segmentation by Long Term Analysis of Point Trajectories

Object Segmentation by Long Term Analysis of Point Trajectories

Online Moving Camera Background Subtraction

Robust Algebraic Segmentation of Mixed Rigid-Body and Planar Motions from Two Views

Contact Info

Product

Resources

About