DocumentCode :
2449041
Title :
A new method for calibrating depth and color camera pair based on Kinect
Author :
Liu, Weihua ; Fan, Yangyu ; Zhong, Zhang ; Lei, Tao
fYear :
2012
fDate :
16-18 July 2012
Firstpage :
212
Lastpage :
217
Abstract :
In this paper, we present a method that can calibrates color camera and depth camera of Kinect simultaneously, and finally get the relative pose between them. The calibration process for color camera and depth camera is designed by taking advantage of two different method respectively. As we know, the depth information can be acquired readily from the depth image, however, under the consideration of the fuzzy boundary and the overlapping of object in depth image, we choose using one-dimensional object for calibrating depth camera and propose a nonlinear method to optimize its intrinsic parameter. As for color camera calibration, we design a cross shape object for calibration and validation. Both methods are strongly robust to noise and much easier to implement. The experiment result shows a better accuracy in comparison with the proprietary calibration procedure of the manufacturer.
Keywords :
calibration; cameras; fuzzy set theory; image colour analysis; interactive systems; optimisation; pose estimation; Kinect; color camera calibration; cross-shape object design; depth camera calibration; depth image; fuzzy boundary; intrinsic parameter optimization; nonlinear method; one-dimensional object; relative pose; Calibration; Cameras; Equations; Image color analysis; Mathematical model; Shape; Transmission line matrix methods;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Audio, Language and Image Processing (ICALIP), 2012 International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4673-0173-2
Type :
conf
DOI :
10.1109/ICALIP.2012.6376614
Filename :
6376614
Link To Document :
بازگشت