Optimized training of deep neural network for image analysis using synthetic objects and augmented reality

Thomas Lu; Alexander Huyen; Luan Nguyen; Joseph Osborne; Sarah Eldin; Kyoungsik Yun

doi:10.1117/12.2522198

13 May 2019 Optimized training of deep neural network for image analysis using synthetic objects and augmented reality

Thomas Lu, Alexander Huyen, Luan Nguyen, Joseph Osborne, Sarah Eldin, Kyoungsik Yun

Proceedings Volume 10995, Pattern Recognition and Tracking XXX; 109950I (2019) https://doi.org/10.1117/12.2522198
Event: SPIE Defense + Commercial Sensing, 2019, Baltimore, MD, United States

Abstract

Acquiring large amounts of data for training and testing Deep Learning (DL) models is time consuming and costly. The development of a process to generate synthetic objects and scenes using 3D graphics software is presented. By programming the path and environment in a 3D graphical engine, complex objects and scenes can be generated for the purpose of training and testing a Deep Neural Network (DNN) model in specific vision tasks. An automatic process has been developed to label and segment objects in synthetic images and generate their corresponding ground truth files. Performances of DNNs trained with synthetic data have been shown to outperform DNNs trained with real data.

Conference Presentation

Citation Download Citation

Thomas Lu, Alexander Huyen, Luan Nguyen, Joseph Osborne, Sarah Eldin, and Kyoungsik Yun "Optimized training of deep neural network for image analysis using synthetic objects and augmented reality", Proc. SPIE 10995, Pattern Recognition and Tracking XXX, 109950I (13 May 2019); https://doi.org/10.1117/12.2522198

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

Includes PDF, HTML & Video, when available