Land-use classification applicable to rural landscapes of Southeast Asia using very high spatial resolution satellite imagery

监测湿润热带农业景观的土地利用/覆盖变化对于建立可持续农村发展至关重要。然而，马赛克景观特有的时空复杂性使得单日期、中分辨率遥感影像难以获得准确的土地利用/覆被图。在本研究中，我们尝试利用纹理度量来改进基于单一日期QuickBird图像的面向对象分类。GLCM纹理测度，尤其是熵测度，无论水稻生长阶段如何，都提高了稻田划分的分类精度。CART模型得出的分类规则集直观易懂：将整幅图像分为绿色或非绿色纹理同质或异质土地利用/覆被类，这似乎描述了农业景观各种土地利用/覆被特征的基本性质。

Monitoring land use/cover changes in humid tropical agricultural landscapes is crucial to establish sustainable rural developments. However, the characteristic spatio-temporal complexity of mosaic landscapes makes it difficult to obtain accurate land use/cover maps using single-dated and moderate-resolution remotely sensed images. In this study, we attempted to classify land use/cover by utilizing texture measures to improve object-oriented classification based on a single-dated QuickBird image. GLCM texture measures, especially entropy, improved classification accuracy in delineating paddy rice fields irrespective of the stage of rice growth. The classification rule set derived from the CART modelling was intuitively understandable: a whole image was divided into green or non-green texturally homogeneous or heterogeneous land use/cover classes, which seems to describe the fundamental nature of the characteristics of various land use/covers of agricultural landscapes.