Injecting spectral indices to transferable convolutional neural network under imbalanced and noisy labels for Landsat image classification  

作　　者：Xuemei Zhao Jun Wu Haijian Wang Xingyu Gao Longlong Zhao 

机构地区：[1]School of Electronic Engineering and Automation,Guilin University of Electronic Technology,Guangxi,People's Republic of China [2]Guangxi Key Laboratory of Manufacturing System & Advanced Manufacturing Technology,School of Mechanical and Electrical Engineering,Guilin University of Electronic Technology,Guangxi,People's Republic of China [3]Center for Geospatial Information,Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences,Beijing,People's Republic of China

出　　处：《International Journal of Digital Earth》2022年第1期437-462,共26页国际数字地球学报（英文）

基　　金：supported by National Natural Science Foundation of China[41801233,41761087];Ningbo Science and Technology Innovation Project[2020Z019];Natural Science Foundation of Guangxi Province[2020GXNSFBA159012].

摘　　要：Stable and continuous remote sensing land-cover mapping is important for agriculture,ecosystems,and land management.Convolutional neural networks(CNNs)are promising methods for achieving this goal.However,the large number of high-quality training samples required to train a CNN is difficult to acquire.In practice,imbalanced and noisy labels originating from existing land-cover maps can be used as alternatives.Experiments have shown that the inconsistency in the training samples has a significant impact on the performance of the CNN.To overcome this drawback,a method is proposed to inject highly consistent information into the network,to learn general and transferable features to alleviate the impact of imperfect training samples.Spectral indices are important features that can provide consistent information.These indices can be fused with CNN feature maps which utilize information entropy to choose the most appropriate CNN layer,to compensate for the inconsistency caused by the imbalanced,noisy labels.The proposed transferable CNN,tested with imbalanced and noisy labels for inter-regional Landsat time-series,not only is superior in terms of accuracy for land-cover mapping but also demonstrates excellent transferability between regions in both time series and cross-regional Landsat image classification.

关 键 词：Landsat image classification imbalanced and noisy label convolutional neural network(CNN) transferability feature fusion information entropy 

分 类 号：TP7[自动化与计算机技术—检测技术与自动化装置] TP183[自动化与计算机技术—控制科学与工程]