Real-time stereo matching on CUDA using Fourier descriptors and dynamic programming

Computation of stereoscopic depth and disparity map extraction are dynamic research topics. A large variety of algorithms has been developed, among which we cite feature matching, moment extraction, and image representation using descriptors to determine a disparity map. This paper proposes a new me...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Computational visual media (Beijing) Jg. 5; H. 1; S. 59 - 71
Hauptverfasser: Hallek, Mohamed, Smach, Fethi, Atri, Mohamed
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Beijing Tsinghua University Press 01.03.2019
Springer Nature B.V
SpringerOpen
Schlagworte:
Algorithms
Artificial Intelligence
Computer Graphics
Computer Science
Cost function
CUDA
Dynamic programming
Euclidean geometry
Feature extraction
generalized Fourier descriptors
Geometric transformation
Image Processing and Computer Vision
Matching
Optimization
Real time
Representations
Research Article
Smoothness
stereo matching
Stereoscopy
User Interfaces and Human Computer Interaction
generalized Fourier descriptors
CUDA
dynamic programming
stereo matching
ISSN:2096-0433, 2096-0662
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Computation of stereoscopic depth and disparity map extraction are dynamic research topics. A large variety of algorithms has been developed, among which we cite feature matching, moment extraction, and image representation using descriptors to determine a disparity map. This paper proposes a new method for stereo matching based on Fourier descriptors. The robustness of these descriptors under photometric and geometric transformations provides a better representation of a template or a local region in the image. In our work, we specifically use generalized Fourier descriptors to compute a robust cost function. Then, a box filter is applied for cost aggregation to enforce a smoothness constraint between neighboring pixels. Optimization and disparity calculation are done using dynamic programming, with a cost based on similarity between generalized Fourier descriptors using Euclidean distance. This local cost function is used to optimize correspondences. Our stereo matching algorithm is evaluated using the Middlebury stereo benchmark; our approach has been implemented on parallel high-performance graphics hardware using CUDA to accelerate our algorithm, giving a real-time implementation.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2096-0433
2096-0662
DOI:10.1007/s41095-019-0133-4