期刊
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
卷 14, 期 -, 页码 4816-4831出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSTARS.2021.3077545
关键词
Buildings; Feature extraction; Training; Task analysis; Semantics; Remote sensing; Spatial resolution; Attention mechanism; end-to-end change detection (CD); fully convolutional network (FCN); high resolution; remote sensing (RS) images
类别
资金
- National Natural Science Foundation of China [61725501]
- National Key Research and Development Program of China [2019YFA0706002]
- High Performance Computing Resources at Beihang University
In this article, an attention-guided end-to-end change detection network (AGCDetNet) is proposed to enhance the feature representation of change information in high-resolution remote sensing images. Through spatial attention and channel attention, AGCDetNet achieves accuracy improvements and outperforms several state-of-the-art change detection methods in terms of accuracy and robustness according to experimental results on public datasets.
While deep learning-based methods have gained considerable improvements in remote sensing (RS) image change detection (CD), scale variations and pseudochanges hinder most supervised methods' performance. The CD networks derived from other fields can be fronted with false alarms and miss detections in high-resolution RS images due to the weak feature representation ability. In this article, an attention-guided end-to-end change detection network (AGCDetNet) is proposed based on the fully convolutional network and attention mechanism. AGCDetNet learns to enhance the feature representation of change information and achieve accuracy improvements using spatial attention and channel attention. A spatial attention module (SPAM) promotes the discrimination between the changed objects and the background by adding the learned spatial attention to the deep features. Channelwise attention-guided interference filtering unit (CIFU)/atrous spatial pyramid pooling (CG-ASPP) module enhances the representation of multilevel features and multiscale context, respectively. Extensive experiments have been conducted on several public datasets for performance evaluation, including LEVIR-CD, WHU, Season-Varying, WV2, and ZY3. Experiment results demonstrate that AGCDetNet outperforms several state-of-the-art methods of accuracy and robustness. Specifically, AGCDetNet achieves the best F1-score on two datasets, i.e., LEVIR-CD (0.9076) and Season-Varying (0.9654).
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