Adaptive support-weight approach for correspondence search

Adaptive support-weight approach for correspondence search

We present a new window-based method for correspondence search using varying support-weights. We adjust the support-weights of the pixels in a given support window based on color similarity and geometric proximity to reduce the image ambiguity. Our method outperforms other local methods on standard...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence 2006-04, Vol.28 (4), p.650-656
Hauptverfasser: Yoon, Kuk-Jin, Kweon, In So
Format: Artikel
Sprache:eng
Schlagworte:
3D/stereo scene analysis
Algorithms
Applied sciences
Artificial Intelligence
Benchmarks
Biomimetics - methods
Color
Colored noise
Colorimetry - methods
Computer science
control theory
systems
Costs
Exact sciences and technology
Feedback
Humans
Image analysis
Image Enhancement - methods
Image Interpretation, Computer-Assisted - methods
Image segmentation
Imaging, Three-Dimensional - methods
Intelligence
Layout
Pattern analysis
Pattern Recognition, Automated - methods
Pattern recognition. Digital image processing. Computational geometry
Performance evaluation
Photogrammetry - methods
Pixel
Power measurement
Searching
Shape
Signal Processing, Computer-Assisted
Similarity
Stereo
Testing
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We present a new window-based method for correspondence search using varying support-weights. We adjust the support-weights of the pixels in a given support window based on color similarity and geometric proximity to reduce the image ambiguity. Our method outperforms other local methods on standard stereo benchmarks.
ISSN:0162-8828
1939-3539
DOI:10.1109/TPAMI.2006.70