论文部分内容阅读
针对目前国内利用卫星遥感数据的光谱特征及其植被指数对香梨识别提取方法鲜有研究的现状,探讨研究了Landsat8_OLI数据对不同树龄香梨的识别提取方法和实际应用。以库尔勒市中部的英下乡和沙依东园艺场为试验区域。采用多时相Landsat8_OLI数据。通过分析试验区内典型地物的光谱特征和植被指数的变化规律以及作物物候历的不同,选择不同树龄香梨树林遥感识别的最佳时相,利用决策树方法构建了不同树龄香梨树林的识别提取模型,实现了香梨种植面积的有效提取。结果表明:1香梨成林(种植5a以上的香梨树林)遥感提取效果较为满意,精度为93.51%,而香梨幼林由于受多种因素的影响,其提取精度只有78.79%,有待进一步研究;2 Landsat8_OLI数据具有较高的时空分辨率,是遥感识别提取库尔勒香梨的潜力数据源。
In view of the current domestic use of satellite remote sensing data of spectral characteristics and vegetation index of fragrant pear recognition extraction methods rarely existing research, study Landsat8_OLI data of different age pear identification methods and practical applications. In the Korla City, the British countryside and Shayidong horticultural field as the test area. Multi-phase Landsat8_OLI data. By analyzing the spectral characteristics of typical landforms and the variation law of vegetation index and the difference of crop phenology, the optimal time-phase of remote sensing identification of fragrant pear trees with different age was selected, and the tree structure of fragrant pear trees with different ages was constructed Recognition extraction model to achieve the effective extraction of fragrant pear planting area. The results showed that: 1 Fragrant pear forest (more than 5a planting pear) remote sensing extraction more satisfactory results, accuracy of 93.51%, and pear young due to many factors, the extraction accuracy of only 78.79%, pending further study ; 2 Landsat8_OLI data has high temporal and spatial resolution and is a potential data source for remote sensing identification of Korla fragrant pear.