Semiparallel deep neural network hybrid architecture: first application on depth from monocular camera

Shabab Bazrafkan; Hossein Javidnia; Joseph Lemley; Peter Corcoran

doi:10.1117/1.JEI.27.4.043041

7 August 2018 Semiparallel deep neural network hybrid architecture: first application on depth from monocular camera

Shabab Bazrafkan, Hossein Javidnia, Joseph Lemley, Peter Corcoran

Author Affiliations +

Funded by: Science Foundation Ireland (SFI), Irish Research Council for Science, Engineering and Technology

Journal of Electronic Imaging, Vol. 27, Issue 4, 043041 (August 2018). https://doi.org/10.1117/1.JEI.27.4.043041

Abstract

Deep neural networks have been applied to a wide range of problems in recent years. Convolutional neural network is applied to the problem of determining the depth from a single camera image (monocular depth). Eight different networks are designed to perform depth estimation, each of them suitable for a feature level. Networks with different pooling sizes determine different feature levels. After designing a set of networks, these models may be combined into a single network topology using graph optimization techniques. This “semiparallel deep neural network (SPDNN)” eliminates duplicated common network layers and can be further optimized by retraining to achieve an improved model compared to the individual topologies. Four SPDNN models are trained and have been evaluated at two stages on the KITTI dataset. The ground truth images in the first part of the experiment are provided by the benchmark, and for the second part, the ground truth images are the depth map results from applying a state-of-the-art stereo matching method. The results of this evaluation demonstrate that using postprocessing techniques to refine the target of the network increases the accuracy of depth estimation on individual mono images. The second evaluation shows that using segmentation data alongside the original data as the input can improve the depth estimation results to a point where performance is comparable with stereo depth estimation. The computational time is also discussed in this study.

Citation Download Citation

Shabab Bazrafkan, Hossein Javidnia, Joseph Lemley, and Peter Corcoran "Semiparallel deep neural network hybrid architecture: first application on depth from monocular camera," Journal of Electronic Imaging 27(4), 043041 (7 August 2018). https://doi.org/10.1117/1.JEI.27.4.043041

Received: 18 April 2018; Accepted: 17 July 2018; Published: 7 August 2018

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE