Abstract
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 closed-form, followed by a graph cut of the superpixel adjacency graph. It generalizes naturally to multi-label partitions that can handle multiple motions.
Keywords
Computer visionArtificial intelligenceComputer scienceSegmentationMotion (physics)GraphImage segmentationPattern recognition (psychology)Theoretical computer science
Affiliated Institutions
Related Publications
Normalized cuts and image segmentation
We propose a novel approach for solving the perceptual grouping problem in vision. Rather than focusing on local features and their consistencies in the image data, our approach...
Lower Bounds for the Partitioning of Graphs
Let a k-partition of a graph be a division of the vertices into k disjoint subsets containing m <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.or...
Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture
In this paper we address three different computer vision tasks using a single basic architecture: depth prediction, surface normal estimation, and semantic labeling. We use a mu...
A Variational Method in Image Recovery
This paper is concerned with a classical denoising and deblurring problem in image recovery. Our approach is based on a variational method. By using the Legendre--Fenchel transf...
A general framework for object detection
This paper presents a general trainable framework for object detection in static images of cluttered scenes. The detection technique we develop is based on a wavelet representat...
Publication Info
- Year
- 2009
- Type
- article
- Volume
- 5302
- Pages
- 727-734
- Citations
- 33
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
33
OpenAlex
Cite This
Alper Ayvacı,
Stefano Soatto
(2009).
Motion segmentation with occlusions on the superpixel graph.
, 5302
, 727-734.
https://doi.org/10.1109/iccvw.2009.5457630
Identifiers
- DOI
- 10.1109/iccvw.2009.5457630