A Dynamic Portrait Segmentation by Merging Colors and Depth Information

다국어 초록 (Multilingual Abstract)

In this paper, we proposed a new method to improve the dynamic portrait segmentation in Kinect which always causes the problem of incomplete image segmentation of portrait due to the loss of the depth. This problem can be solved by using the color information to reinforce the areas where the depth is uncertain. We can segment the portrait’s foreground more completely using the proposed method. First, the depth information can be divided into foreground, background, uncertain areas to produce a judging area for the foreground’s uncertain areas. Secondly, the volunteer image will be segmented by Sobel edge detection, watershed and other steps in color information then be treated as the characteristic value of color area to calculate the mean value and standard deviation respectively.
Finally, we chose the best image from these processing by comparing the color feature of the foreground edge and the judging area. The results show that we can completely segment out the portrait image as well as reduce its error rate significantly.

참고문헌 (Reference)

1 L. Vincent, "Watersheds in digital spaces : an efficient algorithm based on immersion simulations" 13 (13): 583-598, 1991

2 O. Juan, "Trimap segmentation for fast and user-friendly alpha matting" 3752 (3752): 186-197, 2005

3 A. Levin, "Spectral matting" 30 (30): 1699-1712, 2008

4 J. MacQueen, "Some methods for classification and analysis of multivariate observations" 281-297, 1967

5 C. Julià, "Shape-based image segmentation through photometric stereo" 115 (115): 91-104, 2011

6 A. Ratnaweera, "Self-organizing hierarchical particle swarm optimizer with time-varying acceleration coefficients" 8 (8): 240-255, 2004

7 J. -W. Hsieh, "Segmentation of human body parts using deformable triangulation" 40 (40): 596-610, 2010

8 J. Tong, "Scanning 3D full human bodies using Kinects" 18 (18): 643-650, 2012

9 C. -Y. Lee, "Saliencydirected color image segmentation using modified particle swarm optimization" 92 (92): 1-18, 2012

10 P. Henry, "RGB-D mapping : using Kinect-style depth cameras for dense 3D modeling of indoor environments" 31 (31): 647-663, 2012

11 H. Gonzalez-Jorge, "Metrological evaluation of Microsoft Kinect and Asus Xtion sensors" 46 (46): 1800-1806, 2013

12 P. -Y Chen, "Lower limb power rehabilitation(LLPR)using interactive video game for improvement of balance function in older people" 14 (14): 677-682, 2012

13 W. Luo, "Global salient information maximization for saliency detection" 27 (27): 238-248, 2012

14 C. -D. Mutto, "Fusion of geometry and color Information for scene segmentation" 6 (6): 505-521, 2012

15 Z. Liu, "Automatic segmentation of focused objects from images with low depth of field" 31 (31): 572-581, 2010

16 M. Zollhofer, "Automatic reconstruction of personalized avatars from 3D face scans" 22 (22): 195-202, 2011

17 C. -W. Cho, "A vision-based analysis system for gait recognition in patients with Parkinson’s disease" 36 (36): 7033-7039, 2009

18 C. -D. Mutto, "A probabilistic approach to ToF and stereo data fusion" 177-202, 2010

19 K. Khongkraphan, "A novel reconstruction and tracking of 3D-articulated human body from 2D point correspondences of a monocular image sequence" E94-D (E94-D): 1090-1098, 2011