Please use this identifier to cite or link to this item: http://localhost/handle/Hannan/588996
Title: Extending the Pairwise Separability Index for Multicrop Identification Using Time-Series MODIS Images
Authors: Qiong Hu;Wenbin Wu;Qian Song;Qiangyi Yu;Miao Lu;Peng Yang;Huajun Tang;Yuqiao Long
subject: Crop identification|separability index (SI)|extension approaches|moderate resolution imaging spectroradiometer (MODIS)|feature interpretability
Year: 2016
Publisher: IEEE
Abstract: 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 (SI<sub>ave</sub> and SI<sub>min</sub>) 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 SI<sub>ave</sub> 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 SI<sub>min</sub> method. Due to the higher temporal autocorrelation, the optimal features for crop classification that are selected by the SI<sub>ave</sub> approach exhibit greater information redundancy across the time domain than those that are selected by the SI<sub>min</sub> approach, which largely explains the relatively low classification accuracy achieved using the SI<sub>ave</sub> approach. These comparison results between SI<sub>min</sub> and SI<sub>ave</sub> 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.
URI: http://localhost/handle/Hannan/172669
http://localhost/handle/Hannan/588996
ISSN: 0196-2892
1558-0644
volume: 54
issue: 11
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7524696.pdf2.81 MBAdobe PDFThumbnail
Preview File
Title: Extending the Pairwise Separability Index for Multicrop Identification Using Time-Series MODIS Images
Authors: Qiong Hu;Wenbin Wu;Qian Song;Qiangyi Yu;Miao Lu;Peng Yang;Huajun Tang;Yuqiao Long
subject: Crop identification|separability index (SI)|extension approaches|moderate resolution imaging spectroradiometer (MODIS)|feature interpretability
Year: 2016
Publisher: IEEE
Abstract: 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 (SI<sub>ave</sub> and SI<sub>min</sub>) 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 SI<sub>ave</sub> 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 SI<sub>min</sub> method. Due to the higher temporal autocorrelation, the optimal features for crop classification that are selected by the SI<sub>ave</sub> approach exhibit greater information redundancy across the time domain than those that are selected by the SI<sub>min</sub> approach, which largely explains the relatively low classification accuracy achieved using the SI<sub>ave</sub> approach. These comparison results between SI<sub>min</sub> and SI<sub>ave</sub> 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.
URI: http://localhost/handle/Hannan/172669
http://localhost/handle/Hannan/588996
ISSN: 0196-2892
1558-0644
volume: 54
issue: 11
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7524696.pdf2.81 MBAdobe PDFThumbnail
Preview File
Title: Extending the Pairwise Separability Index for Multicrop Identification Using Time-Series MODIS Images
Authors: Qiong Hu;Wenbin Wu;Qian Song;Qiangyi Yu;Miao Lu;Peng Yang;Huajun Tang;Yuqiao Long
subject: Crop identification|separability index (SI)|extension approaches|moderate resolution imaging spectroradiometer (MODIS)|feature interpretability
Year: 2016
Publisher: IEEE
Abstract: 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 (SI<sub>ave</sub> and SI<sub>min</sub>) 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 SI<sub>ave</sub> 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 SI<sub>min</sub> method. Due to the higher temporal autocorrelation, the optimal features for crop classification that are selected by the SI<sub>ave</sub> approach exhibit greater information redundancy across the time domain than those that are selected by the SI<sub>min</sub> approach, which largely explains the relatively low classification accuracy achieved using the SI<sub>ave</sub> approach. These comparison results between SI<sub>min</sub> and SI<sub>ave</sub> 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.
URI: http://localhost/handle/Hannan/172669
http://localhost/handle/Hannan/588996
ISSN: 0196-2892
1558-0644
volume: 54
issue: 11
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7524696.pdf2.81 MBAdobe PDFThumbnail
Preview File