Stereo and kinect fusion for continuous 3D reconstruction and visual odometry

Author

Yilmaz, Ozgur ; Karakus, F.

Author_Institution

Dept. of Comput. Eng., Turgut Ozal Univ., Ankara, Turkey

fYear

2013

fDate

7-9 Nov. 2013

Firstpage

115

Lastpage

118

Abstract

Robust and accurate 3D reconstruction of the scene is essential for many robotic and computer vision applications. We are proposing a system solution that can accurately reconstruct the scene both indoor and outdoor, in real-time. The system utilizes both active and passive visual sensors in conjunction with peripheral hardware for communication, and suggests a significant accuracy improvement over state-of-the-art SLAM algorithms via stereo visual odometry integration.

Keywords

SLAM (robots); computer vision; distance measurement; image fusion; image reconstruction; image sensors; stereo image processing; Kinect fusion; SLAM algorithms; active visual sensors; computer vision applications; continuous 3D reconstruction; indoor scene; outdoor scene; passive visual sensors; peripheral hardware; robotic applications; stereo fusion; stereo visual odometry integration; Cameras; Image reconstruction; Iterative closest point algorithm; Real-time systems; Stereo vision; Three-dimensional displays; Visualization; ICP; Kinect; SLAM; Stereo; Visual Odometry;

fLanguage

English

Publisher

ieee

Conference_Titel

Electronics, Computer and Computation (ICECCO), 2013 International Conference on

Conference_Location

Ankara

Type

conf

DOI

10.1109/ICECCO.2013.6718242

Filename

6718242