Remote sensing is widely applied to provide information of areas with limited ground access with applications such as to assess the destruction from natural disasters and to plan relief and recovery operations. However, the data collection of aerial digital images is constrained by bad weather, atmospheric conditions, and unstable camera or camcorder. Therefore, how to recover the information from the low-quality remote sensing images and how to enhance the image quality becomes very important for many visual understanding tasks, such like feature detection, object segmentation, and object recognition. The quality of remote sensing imagery can be improved through meaningful combination of the employed images captured from different sensors or from different conditions through information fusion. Here we particularly address information fusion to remote sensing images under multi-resolution analysis in the employed image sequences. The image fusion is to recover complete information by integrating multiple images captured from the same scene. Through image fusion, a new image with high-resolution or more perceptive for human and machine is created from a time series of low-quality images based on image registration between different video frames.

Date Published: 26 April 2010
PDF: 9 pages
Proc. SPIE 7668, Airborne Intelligence, Surveillance, Reconnaissance (ISR) Systems and Applications VII, 76680R (26 April 2010); doi: 10.1117/12.849925

Published in SPIE Proceedings Vol. 7668:
Airborne Intelligence, Surveillance, Reconnaissance (ISR) Systems and Applications VII
Daniel J. Henry, Editor(s)