In this paper we evaluated several typical matching costs including CENSUS, mutual information (MI) and the normalized cross correlation using the ISPRS Stereo Matching Benchmark datasets for DSM generation by stereo matching. Two kinds of global optimization algorithms including semi-global matching (SGM) and graph cuts (GC) were used as optimization method. We used a sub-pixel method to obtain more accurate MI lookup table and a sub-pixel method was also used when computing cost by MI lookup table. MI itself is sensitive to partial radiation differences. So we used a kind of cost combined MI and CENSUS. After DSM generation, the deviation data between the generated DSM and Lidar was statistics out to compute the mean deviation (Mean), the median deviation (Med), the standard deviation (Stdev), the normalized median absolute deviation (NMAD), the percentage of deviation in tolerance etc., which were used to evaluate the accuracy of DSM generated from different cost.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
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.