The image tested for this study is a multi-temporal
Canadian Radarsat image. The developed procedure achieves
better edge positioning, higher edge detection resolution, and
at the same time reduces the speckle caused by noise. This
directional filter has been applied to detect the edges of rice
fields for rice monitoring project—monitoring southern
China’s rice growth status and yield estimation Using SAR
images—which is a project of 2002 supported by China’s
National high technology Bureau. Firstly, we used an σ-filter
to reduce the isolated noise around edges. Then a directional
filter or filter bank were applied to detect edges. Finally a
nonlinear operator was used to threshold its magnitude and
produce the edge map of SAR image. The proposed scheme
achieves positive results of extracting linear features, reducing
the speckle noise effectively, and meeting the need of
practical radar remote sensing application in rice monitoring
and yield estimation