TY - GEN
T1 - A Geographically Weighted Total Composite Error Analysis for Soft Classification
AU - Tsutsumida, Narumasa
AU - Yoshida, Takahiro
AU - Murakami, Daisuke
AU - Nakaya, Tomoki
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/9/26
Y1 - 2020/9/26
N2 - Errors in land cover classification are often spatially heterogeneous even though a soft classification model such as spectral unmixing is implemented to mitigate a mixed pixel problem. The estimated land covers are fractions of targeted classes with the restriction of the sum to one and being non-negative. To assess the classification with considering a spatial heterogeneity, we propose a geographically weighted total composite error analysis. By using the USGS global reference database, we assessed errors of spectral unmixing classification of ALOS AVNIR-2 data into 4 land cover classes. Results yield a spatial surface of local errors by the Aitchison distance and address that the error magnitude across space is associated with the complexity of land covers.
AB - Errors in land cover classification are often spatially heterogeneous even though a soft classification model such as spectral unmixing is implemented to mitigate a mixed pixel problem. The estimated land covers are fractions of targeted classes with the restriction of the sum to one and being non-negative. To assess the classification with considering a spatial heterogeneity, we propose a geographically weighted total composite error analysis. By using the USGS global reference database, we assessed errors of spectral unmixing classification of ALOS AVNIR-2 data into 4 land cover classes. Results yield a spatial surface of local errors by the Aitchison distance and address that the error magnitude across space is associated with the complexity of land covers.
KW - Error assessment
KW - soft classification
KW - spatial compositional data
KW - spatial heterogeneity
KW - validation
UR - http://www.scopus.com/inward/record.url?scp=85102006419&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85102006419&partnerID=8YFLogxK
U2 - 10.1109/IGARSS39084.2020.9323939
DO - 10.1109/IGARSS39084.2020.9323939
M3 - Conference contribution
AN - SCOPUS:85102006419
T3 - International Geoscience and Remote Sensing Symposium (IGARSS)
SP - 874
EP - 876
BT - 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020
Y2 - 26 September 2020 through 2 October 2020
ER -