z-logo
open-access-imgOpen Access
Foreground Segmentation and High-Resolution Depth Map Generation Using a Time-of-Flight Depth Camera
Author(s) -
YunSuk Kang,
YoSung Ho
Publication year - 2012
Publication title -
the journal of korean institute of communications and information sciences
Language(s) - English
Resource type - Journals
eISSN - 2287-3880
pISSN - 1226-4717
DOI - 10.7840/kics.2012.37c.9.751
Subject(s) - artificial intelligence , computer vision , depth map , image warping , computer science , preprocessor , segmentation , time of flight , distortion (music) , image (mathematics) , physics , optics , amplifier , computer network , bandwidth (computing)
In this paper, we propose a foreground extraction and depth map generation method using a time-of-flight (TOF) depth camera. Although, the TOF depth camera captures the scene's depth information in real-time, it has a built-in noise and distortion. Therefore, we perform several preprocessing steps such as image enhancement, segmentation, and 3D warping, and then use the TOF depth data to generate the depth-discontinuity regions. Then, we extract the foreground object and generate the depth map as of the color image. The experimental results show that the proposed method efficiently generates the depth map even for the object boundary and textureless regions. * : , yunsuk@gist.ac.kr, ° : , hoyo@gist.ac.kr, :KICS2012-07-303, :2012 7 4, :2012 9 5 I. 3 , . (multi-view image) , , , [1] . '12-09 Vol.37C No.09 752 . , . , . . (stereo matching) [2] . (disparity) , , , . , . Time-of-Flight (TOF) . , . , , . [3-6] . , , . , . , , . II. TOF TOF . Mesa Imaging SR4000 1 . , 0.3m, 5.0m, 54 . SR4000 1 , 8bit (depth image) (intensity image) , 176x144 . (illumination cover) (optical filter) (depth image) (intensity image) 1. Fig. 1. Depth camera and captured image , . [3, 4], [5] , [6], . , . III. . 2 . , . , , / 753 . 2. Fig. 2. Proposed depth map generation method 3.1. . . 1(b) , [7] . (camera calibration) [8] . (intrinsic) 3 (orientation) , (translation) , (projection matrix) . 3 (warping) . 3.2. . , . , , . . , , . . 3 Canny . . 3. Fig. 3. Depth camera image and edge information 3 . 3 . 4 , 3 , 3 . 4. 3 Fig. 4. 3D warping of depth image , 3 , , , . . , , 5 . 5(a) 5(b) , . 5(a) '12-09 Vol.37C No.09 754 . Grab-cut [9] . , , 5(a) 6(a) , Grab-cut . 6(b) . . (a) (b) 5. Fig. 5. Depth discontinuity region generation (a) (b) 6. Grab-cut Fig. 6. Foreground object segmentation using Grab-cut 3.3 6 . 7 3 . . . 7. 3 Fig. 7. 3D warping of depth camera image 6(b) , . 7 3 . d(x+i, y+j) d(x, y) (1) , , . (1) n 0 . d(x+i, y+j) . c(x, y) . k . if (2) , .

The content you want is available to Zendy users.

Already have an account? Click here to sign in.
Having issues? You can contact us here
Accelerating Research

Address

John Eccles House
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom