Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/57461
Title: Spatio-temporal depth recovery of dynamic scenes with multiple handheld cameras
Authors: Jiang, H.
Zhang, G.
Tan, P. 
Bao, H.
Keywords: Bilayer segmentation
Dynamic scene
Spatio-temporal depth recovery
Issue Date: Feb-2013
Source: Jiang, H.,Zhang, G.,Tan, P.,Bao, H. (2013-02). Spatio-temporal depth recovery of dynamic scenes with multiple handheld cameras. Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics 25 (2) : 137-145. ScholarBank@NUS Repository.
Abstract: Most previous dynamic depth recovery methods require many synchronous cameras to achieve good depth estimation, which is inflexible in practice. In this paper, a novel dynamic dense depth recovery method is proposed to automatically recover high-quality dense depth information from the synchronized videos taken by two or three handheld cameras. Initial depth maps are computed by matching the synchronized frames in the same time instance. Then a novel bilayer segmentation method for freely moving cameras is employed to classify the pixels of each frame into static and dynamic ones, so that their depths can be more effectively optimized with different spatio-temporal coherence constraints. Especially, an iterative optimization framework based on multiple frames is proposed, which iteratively performs depth optimization and bilayer segmentation to finally achieve a set of temporally consistent segmentation and depth maps. A variety of dynamic scene examples demonstrate the effectiveness and robustness of the proposed method.
Source Title: Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics
URI: http://scholarbank.nus.edu.sg/handle/10635/57461
ISSN: 10039775
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

64
checked on Dec 8, 2017

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.