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

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.

Object-based classification approach for greenhouse mapping using Landsat-8 imagery

Suburban greenhouses with intensive agricultural productivity have increasingly influenced the daily diet and vegetable supply in Chinese cities.With their enormous input of fertilizers and pesticides,greenhouses have considerably changed the local soil quality and environmental risk factors.The ability to obtain timely and accurate information regarding the spatial distribution of greenhouses could make an important contribution to local agricultural management and soil protection.This paper attempts to present a practical framework for extracting suburban greenhouses,integrating remote sensing data from Landsat-8 and object-oriented classification.Inheritance classification was implemented,and various properties,including texture and neighborhood features in addition to spectral information,were investigated through the popular random forest technique for feature selection prior to SVM classification to improve the mapping accuracy.The results demonstrated that object-based classification incorporating non-spectral features yielded a significant improvement compared with the classification results obtained using only the spectral information in traditional per-pixel classification.Both the producer’s and user’s accuracy were higher than 85%for greenhouse identification.Although it remained a challenge to completely distinguish greenhouses from sparse plants,the final greenhouse map indicated that the proposed object-based classification scheme,providing multiple feature selections and multi-scale analysis,yielded worthwhile information when applied to a continuous series of the freely available Landsat-8 imagery data.