Title :
Robust enhancement of depth images from Kinect sensor
Author :
Tariqul Islam, A.B.M. ; Scheel, Christian ; Pajarola, Renato ; Staadt, Oliver
Author_Institution :
Visual Comput. Lab., Univ. of Rostock, Rostock, Germany
Abstract :
We propose a new method to fill missing or invalid values in depth images generated from the Kinect depth sensor. To fill the missing depth values, we use a robust least median of squares (LMedS) approach. We apply our method for telepresence environments, where Kinects are used very often for reconstructing the captured scene in 3D. We introduce a modified 1D LMedS approach for efficient traversal of consecutive image frames. Our approach solves the unstable nature of depth values in static scenes that is perceived as flickering. We obtain very good result both for static and moving objects inside a scene.
Keywords :
image enhancement; image sensors; Kinect depth sensor; captured scene reconstruction; consecutive image frames; flickering; modified 1D LMedS approach; robust depth image enhancement; robust least median of square approach; telepresence environments; Cameras; Color; Electronic mail; Indexes; Noise; Robustness; Three-dimensional displays; I.3.7 [Computer Graphics]: Three-Dimensional Graphics and Realism — [Virtual Reality]; I.4.3 [Image Processing and Computer Vision]: Enhancement;
Conference_Titel :
Virtual Reality (VR), 2015 IEEE
Conference_Location :
Arles
DOI :
10.1109/VR.2015.7223363