17 January 1997 Selection of texture features for crop discrimination using SAR imagery
Author Affiliations +
This paper presents a methodology for selecting texture measures to maximize the discrimination of agricultural land use classes in SAR images. The images were acquired during the first flight of the Shuttle Imaging Radar-C experiment, in April 1994. L and C band SAR data at HH, HV and VV polarizations, both in ground range and slant range and in two different passes were analyzed. The kappa statistic was used to identify meaningful texture measures to discriminate seven classes. The results show that the classifications of land use based only on tonal averages produced a kappa coefficient only slightly higher than 0.50. A kappa threshold of 0.90 was reached with the simultaneous inclusion of 15 texture measures for the six images.
© (1997) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Joao Vianei Soares, Joao Vianei Soares, Camilo Daleles Renno, Camilo Daleles Renno, } "Selection of texture features for crop discrimination using SAR imagery", Proc. SPIE 2959, Remote Sensing of Vegetation and Sea, (17 January 1997); doi: 10.1117/12.264265; https://doi.org/10.1117/12.264265


Optimal polarimetric processing of SAR imagery
Proceedings of SPIE (October 01 1990)
SAR imagery classification: the fractal approach
Proceedings of SPIE (December 30 1994)
Optimum texture analysis of SAR images
Proceedings of SPIE (June 09 1994)
Agricultural applications from remotely sensed radar imagery
Proceedings of SPIE (September 24 1999)

Back to Top