Implementation of 3D object reconstruction using a pair of Kinect cameras

Author

Dong-Won Shin ; Yo-Sung Ho

Author_Institution

Sch. of Inf. & Commun., Gwangju Inst. of Sci. & Technol., Gwangju, South Korea

fYear

2014

fDate

9-12 Dec. 2014

Firstpage

1

Lastpage

4

Abstract

In this paper, we propose a process of 3D object reconstruction using a pair of Kinect cameras. After we refine raw depth images from two Kinect cameras using a joint bilateral filter, we find intrinsic and extrinsic parameters by camera calibration. Then, we apply 3D warping to obtain a point cloud model in the 3D space and acquire a smooth surface model of the 3D object. In order to accelerate a processing speed, we employ a CUDA framework for GPU parallel processing. We reconstruct depth data in the integrated 3D space and obtain a 3D object model at 5 fps.

Keywords

calibration; cameras; graphics processing units; image reconstruction; parallel architectures; parallel processing; 3D object reconstruction; 3D warping; CUDA framework; GPU parallel processing; camera calibration; depth data reconstruction; extrinsic parameter; intrinsic parameter; joint bilateral filter; kinect camera calibration; point cloud model; raw depth image; smooth surface model; Calibration; Cameras; Graphics processing units; Image reconstruction; Solid modeling; Telecommunications; Three-dimensional displays;

fLanguage

English

Publisher

ieee

Conference_Titel

Asia-Pacific Signal and Information Processing Association, 2014 Annual Summit and Conference (APSIPA)

Conference_Location

Siem Reap

Type

conf

DOI

10.1109/APSIPA.2014.7041651

Filename

7041651