Title :
GPS/IMU based SIFT-matching for aerial romote sensing images
Author :
Ji, Shunping ; Ma, Dan
Author_Institution :
Sch. of Remote Sensing & Inf. Eng., Wuhan Univ., Wuhan, China
Abstract :
The paper presents a new automatic matching method for aerial imagery based on SIFT with image exterior orientation (EO) elements obtained by GPS/IMU system. Firstly, the image EO elements are used to establish the epipolar equations for constraining y-parallax and to predict the initial x-parallax with approximate elevation. Secondly, the SIFT extraction strategy based on pyramid and slicing method are presented for the sake of large capacity of aerial imagery. Thirdly, the GPS/IMU epipolar equations are used to constrain the searching range in matching step and then the least square matching method are used to improve the matching accuracy to sub-pixel level. At last, the gross error detection method base on varying weight is used to eliminate the miss-matching features.
Keywords :
Global Positioning System; geophysical image processing; least squares approximations; remote sensing; GPS-IMU system; SIFT-matching; aerial remote sensing images; automatic matching method; epipolar equations; gross error detection method; image exterior orientation; least square matching method; matching accuracy; Computer vision; Equations; Forestry; Global Positioning System; Image matching; Information science; Remote sensing; GPS/IMU; SIFT; aerial imagery; epipolar equation; image matching;
Conference_Titel :
Remote Sensing, Environment and Transportation Engineering (RSETE), 2011 International Conference on
Conference_Location :
Nanjing
Print_ISBN :
978-1-4244-9172-8
DOI :
10.1109/RSETE.2011.5964508
