A region-level graph labeling approach to motion-based segmentation

Gelgon, Marc; Bouthémy, Patrick

doi:10.1109/cvpr.1997.609374

Cited by 35 publications

(16 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Past approaches have investigated the use of Markov Random Fields (MRF) in handling discontinuities in the optical flow [19], [20], [21], [22]. While these methods give some good results, they rely heavily on a proper spatial segmentation early in the algorithm, which will not be realistic in many cases.…”

Section: Related Workmentioning

confidence: 99%

A voting-based computational framework for visual motion analysis and interpretation

Nicolescu

Medioni

2005

IEEE Trans. Pattern Anal. Machine Intell.

View full text Add to dashboard Cite

Abstract-Most approaches for motion analysis and interpretation rely on restrictive parametric models and involve iterative methods which depend heavily on initial conditions and are subject to instability. Further difficulties are encountered in image regions where motion is not smooth-typically around motion boundaries. This work addresses the problem of visual motion analysis and interpretation by formulating it as an inference of motion layers from a noisy and possibly sparse point set in a 4D space. The core of the method is based on a layered 4D representation of data and a voting scheme for affinity propagation. The inherent problem caused by the ambiguity of 2D to 3D interpretation is usually handled by adding additional constraints, such as rigidity. However, enforcing such a global constraint has been problematic in the combined presence of noise and multiple independent motions. By decoupling the processes of matching, outlier rejection, segmentation, and interpretation, we extract accurate motion layers based on the smoothness of image motion, then locally enforce rigidity for each layer in order to infer its 3D structure and motion. The proposed framework is noniterative and consistently handles both smooth moving regions and motion discontinuities without using any prior knowledge of the motion model.

show abstract

Section: Related Workmentioning

confidence: 99%

A voting-based computational framework for visual motion analysis and interpretation

Nicolescu

Medioni

2005

IEEE Trans. Pattern Anal. Machine Intell.

View full text Add to dashboard Cite

show abstract

“…They assume if a compact region moves differently from the global background motion, it mostly likely belongs to a moving object. Motion-based methods [8,12,21,9,3] usually take the detected moving pixels as seeds, and cluster pixels into layers with consistent motions (and consistent color and depth). When motion information is sparse and incomplete, they cannot work robustly.…”

Section: Introductionmentioning

confidence: 99%

Learning color and locality cues for moving object detection and segmentation

Liu

Gleicher

2009

2009 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…For this purpose, dominant motion and cross-correlation are widely used. Our system implements the method of [4] which uses the dominant motion to detect and track independently moving objects; otherwise, static objects are manually selected and tracked.…”

Section: Description Of the Frameworkmentioning

confidence: 99%

“…To enable high level searching, browsing and navigation, this implicit structure needs to be made explicit [6]. For this purpose, cut detection [1] and object acquisition [4] are performed first. A classification strategy of these objects into homogeneous classes will create links in the video stream, allowing for instance to jump to the next shot where the same person appears.…”

Section: Introductionmentioning

confidence: 99%