Use of satellite image for constructing the unmanned aerial vehicle image matching framework

Yanwei Sun; Hao Li; Li Sun

doi:10.1117/1.JRS.11.016023

6 February 2017 Use of satellite image for constructing the unmanned aerial vehicle image matching framework

Yanwei Sun, Hao Li, Li Sun

Author Affiliations +

Funded by: Natural Science Foundation of China

Journal of Applied Remote Sensing, Vol. 11, Issue 1, 016023 (February 2017). https://doi.org/10.1117/1.JRS.11.016023

Abstract

Although unmanned aerial vehicles (UAV) can provide images with high resolution in a portable and easy way, the matching algorithms such as scale-invariant feature transform and speeded-up robust features (SURF) are often time-consuming. To reduce the time of image matching processes, a fast and low-cost method is proposed for constructing the UAV image matching framework using a satellite image. In this context, the satellite image is used as the base map of UAV images. To find the matching points between UAV and satellite images, a simplified version of SURF is designed to detect interest points. The simplified version of the SURF method uses only one octave of scale spaces to build filter response maps, and each octave is subdivided into four levels of scale spaces. Meanwhile, template matching is used to remove incorrectly matched points. The experimental results show that the method of this paper is robust and can deal with images acquired by small-sized UAVs without a position and orientation system. The method can calculate the rough overlap regions, which are then employed to narrow down the searching space. This will improve the speed of matching greatly, especially for an unordered database of images.

Citation Download Citation

Yanwei Sun, Hao Li, and Li Sun "Use of satellite image for constructing the unmanned aerial vehicle image matching framework," Journal of Applied Remote Sensing 11(1), 016023 (6 February 2017). https://doi.org/10.1117/1.JRS.11.016023

Received: 5 May 2016; Accepted: 16 January 2017; Published: 6 February 2017

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