作者: Ross Hayward , Rodney Walker , Yuee Liu , Zhengrong Li
DOI:
关键词:
摘要: This paper reports on the empirical comparison of seven machine learning algorithms in texture classification with application to vegetation management power line corridors. Aiming at classifying tree species corridors, object-based method is employed. Individual crowns are segmented as basic units and three classic features extracted input algorithms. Several widely used performance metrics evaluate The experimental results demonstrate that depends matrix, characteristics datasets feature used.