Imaging Components, Systems, and Processing

Single image depth estimation based on convolutional neural network and sparse connected conditional random field

[+] Author Affiliations
Leqing Zhu, Xun Wang, Huiyan Wang

Zhejiang Gongshang University, School of Computer Science and Information Engineering, No. 18 Xuezheng Street, Hangzhou 310018, China

Dadong Wang

Quantitative Imaging Research Team, Commonwealth Scientific and Industrial Research Organization Data61, P.O. Box 76, Epping, New South Wales 1710, Australia

Opt. Eng. 55(10), 103101 (Oct 07, 2016). doi:10.1117/1.OE.55.10.103101
History: Received July 5, 2016; Accepted September 14, 2016
Text Size: A A A

Abstract.  Deep convolutional neural networks (DCNNs) have attracted significant interest in the computer vision community in the recent years and have exhibited high performance in resolving many computer vision problems, such as image classification. We address the pixel-level depth prediction from a single image by combining DCNN and sparse connected conditional random field (CRF). Owing to the invariance properties of DCNNs that make them suitable for high-level tasks, their outputs are generally not localized enough for detailed pixel-level regression. A multiscale DCNN and sparse connected CRF are combined to overcome this localization weakness. We have evaluated our framework using the well-known NYU V2 depth dataset, and the results show that the proposed method can improve the depth prediction accuracy both qualitatively and quantitatively, as compared to previous works. This finding shows the potential use of the proposed method in three-dimensional (3-D) modeling or 3-D video production from the given two-dimensional (2-D) images or 2-D videos.

Figures in this Article
© 2016 Society of Photo-Optical Instrumentation Engineers

Citation

Leqing Zhu ; Xun Wang ; Dadong Wang and Huiyan Wang
"Single image depth estimation based on convolutional neural network and sparse connected conditional random field", Opt. Eng. 55(10), 103101 (Oct 07, 2016). ; http://dx.doi.org/10.1117/1.OE.55.10.103101


Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging & repositioning the boxes below.

Related Book Chapters

Topic Collections

PubMed Articles
Advertisement
  • Don't have an account?
  • Subscribe to the SPIE Digital Library
  • Create a FREE account to sign up for Digital Library content alerts and gain access to institutional subscriptions remotely.
Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).
Access This Proceeding
Sign in or Create a personal account to Buy this article ($15 for members, $18 for non-members).
Access This Chapter

Access to SPIE eBooks is limited to subscribing institutions and is not available as part of a personal subscription. Print or electronic versions of individual SPIE books may be purchased via SPIE.org.