A Branch-and-Bound Approach to Correspondence and Grouping Problems

Data correspondence/grouping under an unknown parametric model is a fundamental topic in computer vision. Finding feature correspondences between two images is probably the most popular application of this research field, and is the main motivation of our work. It is a key ingredient for a wide rang...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE Transactions on Pattern Analysis and Machine Intelligence Ročník 35; číslo 7; s. 1565 - 1576
Hlavní autori: Bazin, J., Hongdong Li, In So Kweon, Demonceaux, C., Vasseur, P., Ikeuchi, K.
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Los Alamitos, CA IEEE 01.07.2013
Institute of Electrical and Electronics Engineers (IEEE)
IEEE Computer Society
Institute of Electrical and Electronics Engineers
Predmet:
[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]
Algorithms
Applied sciences
Artificial intelligence
bilinearities
Branch and bounds
branch-and-bound
Branch-and-bound approaches
Computer Science
Computer science; control theory; systems
Computer vision
Computer Vision and Pattern Recognition
Computer vision problems
Educational institutions
Electronic mail
Exact sciences and technology
Feature extraction
Geometry
global optimization
Heuristic metho bilinearities
Keywords: Appearance similarities
Mixed integer programming
Optimization
Pattern matching
Pattern recognition. Digital image processing. Computational geometry
Quadratic constraint
Three-dimensional reconstruction
Computer vision
Image texture
bilinearities
Global optimum
Mixed integer programming
Grouping
Correspondence principle
Modeling
Image reconstruction
global optimization
quadratic constraint
branch-and-bound
Implicit enumeration method
Heuristic method
Pattern extraction
Geometry
Educational institutions
Feature extraction
Electronic mail
Pattern matching
Optimization
ISSN:0162-8828, 1939-3539, 2160-9292, 1939-3539
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Data correspondence/grouping under an unknown parametric model is a fundamental topic in computer vision. Finding feature correspondences between two images is probably the most popular application of this research field, and is the main motivation of our work. It is a key ingredient for a wide range of vision tasks, including three-dimensional reconstruction and object recognition. Existing feature correspondence methods are based on either local appearance similarity or global geometric consistency or a combination of both in some heuristic manner. None of these methods is fully satisfactory, especially in the presence of repetitive image textures or mismatches. In this paper, we present a new algorithm that combines the benefits of both appearance-based and geometry-based methods and mathematically guarantees a global optimization. Our algorithm accepts the two sets of features extracted from two images as input, and outputs the feature correspondences with the largest number of inliers, which verify both the appearance similarity and geometric constraints. Specifically, we formulate the problem as a mixed integer program and solve it efficiently by a series of linear programs via a branch-and-bound procedure. We subsequently generalize our framework in the context of data correspondence/grouping under an unknown parametric model and show it can be applied to certain classes of computer vision problems. Our algorithm has been validated successfully on synthesized data and challenging real images.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0162-8828
1939-3539
2160-9292
1939-3539
DOI:10.1109/TPAMI.2012.264