Identification of pests and diseases of Dalbergia hainanensis based on EVI time series and classification of decision tree
Identification of pests and diseases of Dalbergia hainanensis based on EVI time series and classification of decision tree
复制标题
DOI：
10.1088/1755-1315/69/1/012162
复制
发表时间：
2017-06
期刊：
影响因子：
--
通讯作者：
Q. Luo;Wu Xin;Qiming Xiong
中科院分区：
文献类型：
--
作者：
Q. Luo;Wu Xin;Qiming Xiong
在植被遥感信息提取过程中，没有考虑物候特征和遥感分析算法性能不高的问题。针对这一问题，提出了基于EVI时间序列的遥感植被信息提取方法和多源分支相似性决策树分类方法。首先，为了提高识别精度的时间序列稳定性，在时间序列拟合跨度范围的基础上提取植被的季节特征。其次，通过自适应选择路径或构件预测概率参数来判别决策树的相似性。作为一个指标，它是评估任务关联程度，决定是否进行多源决策树迁移，并保证迁移的速度。最终，海南黄檀商品林病虫害分类识别准确率可达87%-98%，明显优于该地区MODIS覆盖准确率80%-96%。因此，可以验证所提出的方法的有效性。
In the process of vegetation remote sensing information extraction, the problem of phenological features and low performance of remote sensing analysis algorithm is not considered. To solve this problem, the method of remote sensing vegetation information based on EVI time-series and the classification of decision-tree of multi-source branch similarity is promoted. Firstly, to improve the time-series stability of recognition accuracy, the seasonal feature of vegetation is extracted based on the fitting span range of time-series. Secondly, the decision-tree similarity is distinguished by adaptive selection path or probability parameter of component prediction. As an index, it is to evaluate the degree of task association, decide whether to perform migration of multi-source decision tree, and ensure the speed of migration. Finally, the accuracy of classification and recognition of pests and diseases can reach 87%--98% of commercial forest in Dalbergia hainanensis, which is significantly better than that of MODIS coverage accuracy of 80%--96% in this area. Therefore, the validity of the proposed method can be verified.