Share Email Print
cover

Proceedings Paper

Detecting and classifying small objects in thermal imagery using a deep neural network
Author(s): Fredrik Hemström; Fredrik Nässtrom M.D.; Jörgen Karlholm
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In recent years the rise of deep learning neural networks has shown great results in image classification. Most of the previous work focuses on classification of fairly large objects in visual imagery. This paper presents a method of detecting and classifying small objects in thermal imagery using a deep learning method based on a RetinaNet network. The result shows that a deep neural network with a relative small set of labelled images can be trained to classify objects in thermal imagery. Objects from classes with the most training examples (cars, trucks and persons) can with relative high confidence be classified given an object size of 32×32 pixels or smaller.

Paper Details

Date Published: 19 September 2019
PDF: 7 pages
Proc. SPIE 11169, Artificial Intelligence and Machine Learning in Defense Applications, 1116908 (19 September 2019);
Show Author Affiliations
Fredrik Hemström, FOI-Swedish Defence Research Agency (Sweden)
Fredrik Nässtrom M.D., FOI-Swedish Defence Research Agency (Sweden)
Jörgen Karlholm, FOI-Swedish Defence Research Agency (Sweden)


Published in SPIE Proceedings Vol. 11169:
Artificial Intelligence and Machine Learning in Defense Applications
Judith Dijk, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray