文献类型： 外文期刊

作者： Hu, Qiong ¹ ; Wu, Wenbin ¹ ; Song, Qian ¹ ; Yu, Qiangyi ¹ ; Lu, Miao ¹ ; Yang, Peng ¹ ; Tang, Huajun ¹ ; Long, Yuqiao ¹ ;

作者机构： 1.Chinese Acad Agr Sci, Inst Agr Resources & Reg Planning, Minist Agr, Key Lab Agriinformat, Beijing 100081, Peoples R China

2.Heilongjiang Acad Agr Sci, Remot

关键词： Crop identification;extension approaches;feature interpretability;moderate resolution imaging spectroradiometer (MODIS);separability index (SI)

期刊名称：IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING （ 影响因子：5.6； 五年影响因子：6.086 ）

ISSN：

年卷期：

页码：

收录情况： SCI

摘要： The pairwise separability index (SI) has been demonstrated as an effective indicator for capturing crucial phenological differences between two plant species. However, its application to crop types, which have more obvious phenological characteristics than natural vegetation, has received less attention, and extending the pairwise SI to multiple crops for feature selection still remains a challenge. This paper presented two SI extension approaches (SIave and SImin) to select the optimal spectro-temporal features for multiple crops, and investigated their classification performance using Heilongjiang Province, China, as a study area. Feature interpretability and classification accuracy of different crops were evaluated for the two approaches. The results showed that the SIave approach generally has relatively high feature interpretability due to its better description of crucial phenological characteristics of different crops. Those crops with high separability are insensitive to the extension approach and have similar classification accuracy for the two approaches, whereas those crops with poor separability show good performance with the SImin method. Due to the higher temporal autocorrelation, the optimal features for crop classification that are selected by the SIave approach exhibit greater information redundancy across the time domain than those that are selected by the SImin approach, which largely explains the relatively low classification accuracy achieved using the SIave approach. These comparison results between SI min and SIave approaches also indicate that time-series images with high temporal resolution do not necessarily produce high classification accuracy, regardless of their ability to describe the seasonal characteristics of crops.