Share Email Print
cover

Proceedings Paper

Object-based multispectral image fusion method using deep learning
Author(s): Hyunsung Jang; Namkoo Ha; Yoonmo Yeon; Kuyong Kwon; Sungho Gil; Seungha Lee; Sungsoon Park; Hyungjoo Jung; Kwanghoon Sohn
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The goal of multispectral image fusion is to integrate complementary information from multispectral sensors to enhance human visual perception and object detection. Additionally, there are also cases when only the object needs to be emphasized with minimal background interference. This paper presents an object-based fusion method using deep learning to accomplish this objective. The proposed method uses information regarding the region of an object to perform fusion on the object. As we cannot provide labels for fusion results at the learning stage, we propose an unsupervised learning method. The proposed method simultaneously provides appropriate image information from the background and target for surveillance and reconnaissance.

Paper Details

Date Published: 19 September 2019
PDF: 6 pages
Proc. SPIE 11169, Artificial Intelligence and Machine Learning in Defense Applications, 111690O (19 September 2019);
Show Author Affiliations
Hyunsung Jang, LIG Nex1 Co., Ltd. (Korea, Republic of)
Yonsei Univ. (Korea, Republic of)
Namkoo Ha, LIG Nex1 Co., Ltd. (Korea, Republic of)
Yoonmo Yeon, LIG Nex1 Co., Ltd. (Korea, Republic of)
Kuyong Kwon, LIG Nex1 Co., Ltd. (Korea, Republic of)
Sungho Gil, LIG Nex1 Co., Ltd. (Korea, Republic of)
Seungha Lee, LIG Nex1 Co., Ltd. (Korea, Republic of)
Sungsoon Park, LIG Nex1 Co., Ltd. (Korea, Republic of)
Hyungjoo Jung, Yonsei Univ. (Korea, Republic of)
Kwanghoon Sohn, Yonsei Univ. (Korea, Republic of)


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