NDVI-Based Lacunarity Texture for Improving Identification of Torreya Using Object-Oriented Method  

作　　者：HAN Ning WU Jing Amir Reza Shah Tahmassebi XU Hong-wei WANG Ke 

机构地区：[1]Institute of Remote Sensing and Information System Application, College of Environment and Resource Science, Zhejiang University, Hangzhou 310029, P.R. China [2]School of Environment and Resource, Zhejiang Agriculture and Forestry University, Hangzhou 311300, P.R.China

出　　处：《Agricultural Sciences in China》2011年第9期1431-1444,共14页中国农业科学（英文版）

基　　金：supported by the National Natural Science Foundation of China (30671212)

摘　　要：Normalized Difference Vegetation Index （NDVI） is a very useful feature for differentiating vegetation and non-vegetation in remote sensed imagery. In the light of the function of NDVI and the spatial patterns of the vegetation landscapes, we proposed the lacunarity texture derived from NDVI to characterize the spatial patterns of vegetation landscapes concerning the ＂gappiness＂ or ＂emptiness＂ characteristics. The NDVI-based lacunarity texture was incorporated into object-oriented classification for improving the identification of vegetation categories, especially Torreya which was the targeted tree species in the present research. A three-level hierarchical network of image objects was defined and the proposed texture was integrated as potential sources of information in the rules base. A knowledge base of rules created by classifier C5.0 indicated that the texture could potentially be applied in object-oriented classification. It was found that the addition of such texture improved the identification of every vegetation category. The results demonstrated that the texture could characterize the spatial patterns of vegetation structures, which could be a promising approach for vegetation identification.Normalized Difference Vegetation Index （NDVI） is a very useful feature for differentiating vegetation and non-vegetation in remote sensed imagery. In the light of the function of NDVI and the spatial patterns of the vegetation landscapes, we proposed the lacunarity texture derived from NDVI to characterize the spatial patterns of vegetation landscapes concerning the ＂gappiness＂ or ＂emptiness＂ characteristics. The NDVI-based lacunarity texture was incorporated into object-oriented classification for improving the identification of vegetation categories, especially Torreya which was the targeted tree species in the present research. A three-level hierarchical network of image objects was defined and the proposed texture was integrated as potential sources of information in the rules base. A knowledge base of rules created by classifier C5.0 indicated that the texture could potentially be applied in object-oriented classification. It was found that the addition of such texture improved the identification of every vegetation category. The results demonstrated that the texture could characterize the spatial patterns of vegetation structures, which could be a promising approach for vegetation identification.

关 键 词：Torreya NDVI LACUNARITY class hierarchy object-oriented method decision tree spatial pattern 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置] TP391.41[自动化与计算机技术—控制科学与工程]