Automatic detection of linear woody vegetation in agricultural areas [Tarim alanlarinda doǧrusal odunsu bitki gruplarinin otomatik sezimi]

Abstract

Automatic mapping and monitoring of agricultural landscapes is an important research problem. In this paper, we present a method for automatic mapping of linear strips of woody vegetation in very high-resolution imagery. The method combines spectral, textural and object shape information using hierarchical feature extraction and decision making steps. Experiments on Quickbird imagery from different sites show promising detection performance. ©2009 IEEE.