Real-data performance evaluation of Unreal Engine synthetic IR data

Christian C. Nadell; Gregory P. Spell; Mark Jeiran; Kimberly E. Manser

doi:10.1117/12.2665012

13 June 2023 Real-data performance evaluation of Unreal Engine synthetic IR data

Christian C. Nadell, Gregory P. Spell, Mark Jeiran, Kimberly E. Manser

Proceedings Volume 12529, Synthetic Data for Artificial Intelligence and Machine Learning: Tools, Techniques, and Applications; 1252904 (2023) https://doi.org/10.1117/12.2665012
Event: SPIE Defense + Commercial Sensing, 2023, Orlando, Florida, United States

Abstract

In order to achieve state of the art classification and detection performance with modern deep learning approaches, large amounts of labeled data are required. In the infrared (IR) domain, the required quantity of data can be prohibitively expensive and time-consuming to acquire. This makes the generation of synthetic data an attractive alternative. The well-known Unreal Engine (UE) software enables multispectral simulation addon packages to obtain a degree of physical realism, providing a possible avenue for generating such data. However, significant technical challenges remain to design a synthetic IR dataset—varying class, position, object size, and many other factors is critical to achieving a training dataset useful for object detection and classification. In this work we explore these critical axes of variation using standard CNN architectures, evaluating a large UE training set on a real IR validation set, and provide guidelines for variation in many of these critical dimensions for multiple machine learning problems.

Conference Presentation

Citation Download Citation

Christian C. Nadell, Gregory P. Spell, Mark Jeiran, and Kimberly E. Manser "Real-data performance evaluation of Unreal Engine synthetic IR data", Proc. SPIE 12529, Synthetic Data for Artificial Intelligence and Machine Learning: Tools, Techniques, and Applications, 1252904 (13 June 2023); https://doi.org/10.1117/12.2665012

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