Dynamic Programming and Graph Algorithms in Computer Vision

Optimization is a powerful paradigm for expressing and solving problems in a wide range of areas, and has been successfully applied to many vision problems. Discrete optimization techniques are especially interesting since, by carefully exploiting problem structure, they often provide nontrivial gua...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence Jg. 33; H. 4; S. 721 - 740
Hauptverfasser: Felzenszwalb, P F, Zabih, R
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Los Alamitos, CA IEEE 01.04.2011
IEEE Computer Society
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Algorithmics. Computability. Computer arithmetics
Algorithms
Application software
Applied sciences
Artificial intelligence
Combinatorial algorithms
Computer science
Computer science; control theory; systems
Computer Simulation
Computer vision
computing methodologies
Dynamic programming
Exact sciences and technology
Graphs
Image Enhancement - methods
Image Processing, Computer-Assisted - methods
Information retrieval. Graph
Intelligence
Interactive
Layout
Object segmentation
Optimization
Optimization methods
Pattern analysis
Pattern recognition. Digital image processing. Computational geometry
Probability
Stereo vision
Theoretical computing
Vision
vision and scene understanding
Vision, Ocular - physiology
Computer vision
Stereo image processing
Image interpretation
Combinatorial problem
computing methodologies
Modeling
Optimization
Image segmentation
Combinatorial algorithms
Scene analysis
vision and scene understanding
Problem solving
Discrete programming
Stereopsis
Artificial intelligence
ISSN:0162-8828, 1939-3539, 1939-3539
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Optimization is a powerful paradigm for expressing and solving problems in a wide range of areas, and has been successfully applied to many vision problems. Discrete optimization techniques are especially interesting since, by carefully exploiting problem structure, they often provide nontrivial guarantees concerning solution quality. In this paper, we review dynamic programming and graph algorithms, and discuss representative examples of how these discrete optimization techniques have been applied to some classical vision problems. We focus on the low-level vision problem of stereo, the mid-level problem of interactive object segmentation, and the high-level problem of model-based recognition.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ObjectType-Review-3
ISSN:0162-8828
1939-3539
1939-3539
DOI:10.1109/TPAMI.2010.135