期刊
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
卷 19, 期 -, 页码 -出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LGRS.2021.3098774
关键词
Remote sensing; Convolution; Feature extraction; Training; Task analysis; Loss measurement; Convolutional neural networks; Change detection (CD); combined loss function; high-resolution remote sensing images (HRSIs); multiscale fully convolutional neural network (MFCN)
类别
资金
- National Key Research and Development Program of China [2019YFB2102904]
- National Natural Science Foundation of China (NSFC) [41701394]
This study proposes a method based on a multiscale fully convolutional neural network that effectively extracts detailed features of ground objects and addresses the issue of unbalanced samples, with experiments showing better performance in change detection tasks.
In the task of change detection (CD), high-resolution remote sensing images (HRSIs) can provide rich ground object information. However, the interference from noise and complex background information can also bring some challenges to CD. In recent years, deep learning methods represented by convolutional neural networks (CNNs) have achieved good CD results. However, the existing methods have difficulty in detecting the detailed change information of the ground objects effectively. The imbalance of positive and negative samples can also seriously affect the CD results. In this letter, to solve the above problems, we propose a method based on a multiscale fully convolutional neural network (MFCN), which uses multiscale convolution kernels to extract the detailed features of the ground object features. A loss function combining weighted binary cross-entropy (WBCE) loss and dice coefficient loss is also proposed, so that the model can be trained from unbalanced samples. The proposed method was compared with six state-of-the-art CD methods on the DigitalGlobe dataset. The experiments showed that the proposed method can achieve a higher F1-score, and the detection effect of the detailed changes was better than that of the other methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据