Paper
9 December 2015 Evaluation of matching cost on the ISPRS stereo matching benchmark
Qingxing Yue, Xinming Tang, Xiaoming Gao
Author Affiliations +
Proceedings Volume 9808, International Conference on Intelligent Earth Observing and Applications 2015; 980821 (2015) https://doi.org/10.1117/12.2209218
Event: International Conference on Intelligent Earth Observing and Applications, 2015, Guilin, China
Abstract
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.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Qingxing Yue, Xinming Tang, and Xiaoming Gao "Evaluation of matching cost on the ISPRS stereo matching benchmark", Proc. SPIE 9808, International Conference on Intelligent Earth Observing and Applications 2015, 980821 (9 December 2015); https://doi.org/10.1117/12.2209218
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Lanthanum

Image resolution

LIDAR

Optimization (mathematics)

High resolution satellite images

Tolerancing

Digital imaging

Back to Top