作者:Boonprong, S (Boonprong, Sornkitja)[ 1,2 ] ; Cao, CX (Cao, Chunxiang)[ 2 ] ; Chen, W (Chen, Wei)[ 2 ] ; Ni, XL (Ni, Xiliang)[ 2 ] ; Xu, M (Xu, Min)[ 2 ] ; Acharya, BK (Acharya, Bipin Kumar)[ 1,2 ]

ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION

卷: 7  期: 7

文献号: 274

DOI: 10.3390/ijgi7070274

出版年:JUL 2018

摘要

Remotely sensed data are often adversely affected by many types of noise, which influences the classification result. Supervised machine-learning (ML) classifiers such as random forest (RF), support vector machine (SVM), and back-propagation neural network (BPNN) are broadly reported to improve robustness against noise. However, only a few comparative studies that may help investigate this robustness have been reported. An important contribution, going beyond previous studies, is that we perform the analyses by employing the most well-known and broadly implemented packages of the three classifiers and control their settings to represent users' actual applications. This facilitates an understanding of the extent to which the noise types and levels in remotely sensed data impact classification accuracy using ML classifiers. By using those implementations, we classified the land cover data from a satellite image that was separately afflicted by seven-level zero-mean Gaussian, salt-pepper, and speckle noise. The modeling data and features were strictly controlled. Finally, we discussed how each noise type affects the accuracy obtained from each classifier and the robustness of the classifiers to noise in the data. This may enhance our understanding of the relationship between noises, the supervised ML classifiers, and remotely sensed data.

通讯作者地址: Cao, CX (通讯作者)

Chinese Acad Sci, State Key Lab Remote Sensing Sci, Inst Remote Sensing & Digital Earth, Beijing 100101, Peoples R China.

地址:

[ 1 ] Univ Chinese Acad Sci, Beijing 100094, Peoples R China

[ 2 ] Chinese Acad Sci, State Key Lab Remote Sensing Sci, Inst Remote Sensing & Digital Earth, Beijing 100101, Peoples R China