DocumentCode :
3472481
Title :
Depth-supported real-time video segmentation with the Kinect
Author :
Abramov, Alexey ; Pauwels, Karl ; Papon, Jeremie ; Wörgötter, Florentin ; Dellen, Babette
Author_Institution :
III Phys. Inst., Georg-August Univ., Gottingen, Germany
fYear :
2012
fDate :
9-11 Jan. 2012
Firstpage :
457
Lastpage :
464
Abstract :
We present a real-time technique for the spatiotemporal segmentation of color/depth movies. Images are segmented using a parallel Metropolis algorithm implemented on a GPU utilizing both color and depth information, acquired with the Microsoft Kinect. Segments represent the equilibrium states of a Potts model, where tracking of segments is achieved by warping obtained segment labels to the next frame using real-time optical flow, which reduces the number of iterations required for the Metropolis method to encounter the new equilibrium state. By including depth information into the framework, true objects boundaries can be found more easily, improving also the temporal coherency of the method. The algorithm has been tested for videos of medium resolutions showing human manipulations of objects. The framework provides an inexpensive visual front end for visual preprocessing of videos in industrial settings and robot labs which can potentially be used in various applications.
Keywords :
graphics processing units; image colour analysis; image segmentation; image sequences; iterative methods; video signal processing; GPU; Microsoft Kinect; Potts model; color-depth movies; depth supported real time video segmentation; human manipulations; industrial settings; iterations; obtained segment label warping; parallel Metropolis algorithm; real time optical flow; robot labs; spatiotemporal segmentation; Calibration; Cameras; Image color analysis; Image segmentation; Kernel; Optical imaging; Streaming media;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Applications of Computer Vision (WACV), 2012 IEEE Workshop on
Conference_Location :
Breckenridge, CO
ISSN :
1550-5790
Print_ISBN :
978-1-4673-0233-3
Electronic_ISBN :
1550-5790
Type :
conf
DOI :
10.1109/WACV.2012.6163000
Filename :
6163000
Link To Document :
بازگشت