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.
|Title of host publication||Artificial Intelligence and Machine Learning in Defense Applications|
|Publication status||Published - 2019|
|Event||Artificial Intelligence and Machine Learning in Defense Applications 2019 - Strasbourg, France|
Duration: 2019 Sep 10 → 2019 Sep 12
|Name||Proceedings of SPIE - The International Society for Optical Engineering|
|Conference||Artificial Intelligence and Machine Learning in Defense Applications 2019|
|Period||19/9/10 → 19/9/12|
Bibliographical noteFunding Information:
This research was supported by the Target Detection and Tracking using the Deep Learning RZ04CM-001) and the SWIR/LWIR Image Fusion project (No. Y17-030) of LIG Nex1 Co., Ltd.
© 2019 SPIE.
All Science Journal Classification (ASJC) codes
- Electronic, Optical and Magnetic Materials
- Condensed Matter Physics
- Computer Science Applications
- Applied Mathematics
- Electrical and Electronic Engineering