A texture orientation estimator for discriminating between forests, orchards, vineyards, and tilled fields

We present a novel orientation estimator suitable for texton-based textures with one or two orientations. We successfully apply it to the problem of discriminating between forests, orchards, vineyards, tilled fields, and untilled fields in high-resolution aerial images.

[1]  Timothy A. Warner,et al.  Spatial Classification of Orchards and Vineyards with High Spatial Resolution Panchromatic Imagery , 2005 .

[2]  Pierre Baylou,et al.  Local multiple orientation estimation: isotropic and recursive oriented network , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[3]  David Zhang,et al.  Scale-orientation histogram for texture image retrieval , 2003, Pattern Recognit..

[4]  Edwin R. Hancock,et al.  Texture recognition through modal analysis of spectral peak patterns , 2002, Object recognition supported by user interaction for service robots.

[5]  Pierre Baylou,et al.  Orientation difference statistics for texture description , 2002, Object recognition supported by user interaction for service robots.