Recovering Occlusion Boundaries from an Image

Occlusion reasoning is a fundamental problem in computer vision. In this paper, we propose an algorithm to recover the occlusion boundaries and depth ordering of free-standing structures in the scene. Rather than viewing the problem as one of pure image processing, our approach employs cues from an...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:International journal of computer vision Ročník 91; číslo 3; s. 328 - 346
Hlavní autori: Hoiem, Derek, Efros, Alexei A., Hebert, Martial
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Boston Springer US 01.02.2011
Springer
Springer Nature B.V
Predmet:
Algorithms
Applied sciences
Artificial Intelligence
Boundaries
Computer Imaging
Computer Science
Computer science; control theory; systems
Computer vision
Datasets
Exact sciences and technology
Experiments
Image Processing and Computer Vision
Image processing equipment industry
Labeling
Learning and adaptive systems
Machine vision
Mathematical models
Occlusion
Order disorder
Pattern Recognition
Pattern Recognition and Graphics
Pattern recognition. Digital image processing. Computational geometry
Segmentation
Vegetation
Vision
Image segmentation
Scene understanding
Occlusion boundaries
3D reconstruction
Image interpretation
Depth from image
Edge detection
Figure/ground labeling
Occlusion
Image processing
Iterative method
Conditional probability
Modeling
Image reconstruction
Classification
Internal structure
Ordering
Data structure
Learning algorithm
Computer vision
Refinement method
Grouping
Scene analysis
Tridimensional image
Occultation
ISSN:0920-5691, 1573-1405
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Occlusion reasoning is a fundamental problem in computer vision. In this paper, we propose an algorithm to recover the occlusion boundaries and depth ordering of free-standing structures in the scene. Rather than viewing the problem as one of pure image processing, our approach employs cues from an estimated surface layout and applies Gestalt grouping principles using a conditional random field (CRF) model. We propose a hierarchical segmentation process, based on agglomerative merging, that re-estimates boundary strength as the segmentation progresses. Our experiments on the Geometric Context dataset validate our choices for features, our iterative refinement of classifiers, and our CRF model. In experiments on the Berkeley Segmentation Dataset, PASCAL VOC 2008, and LabelMe, we also show that the trained algorithm generalizes to other datasets and can be used as an object boundary predictor with figure/ground labels.
Bibliografia:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-2
content type line 23
ISSN:0920-5691
1573-1405
DOI:10.1007/s11263-010-0400-4