期刊
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
卷 15, 期 -, 页码 4297-4306出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSTARS.2022.3177235
关键词
Feature extraction; Transformers; Head; Data mining; Task analysis; Decoding; Biological system modeling; Change detection (CD); cropland; deep learning (DL); remote sensing; transformer
类别
资金
- National Natural Science Foundation of China [61976234]
- Fundamental Research Funds for the Central Universities, Sun Yat-sen University [22qntd2001]
Nonagriculturalization incidents are serious threats to local agricultural ecosystem and global food security. The proposed MSCANet combines the merits of CNN and transformer to fulfill efficient and effective cropland change detection. The article also provides a new cropland change detection dataset.
Nonagriculturalization incidents are serious threats to local agricultural ecosystem and global food security. Remote sensing change detection (CD) can provide an effective approach for in-time detection and prevention of such incidents. However, existing CD methods are difficult to deal with the large intraclass differences of cropland changes in high-resolution images. In addition, traditional CNN based models are plagued by the loss of long-range context information, and the high computational complexity brought by deep layers. Therefore, in this article, we propose a CNN-transformer network with multiscale context aggregation (MSCANet), which combines the merits of CNN and transformer to fulfill efficient and effective cropland CD. In the MSCANet, a CNN-based feature extractor is first utilized to capture hierarchical features, then a transformer-based MSCA is designed to encode and aggregate context information. Finally, a multibranch prediction head with three CNN classifiers is applied to obtain change maps, to enhance the supervision for deep layers. Besides, for the lack of CD dataset with fine-grained cropland change of interest, we also provide a new cropland change detection dataset, which contains 600 pairs of 512 x 512 bi-temporal images with the spatial resolution of 0.5-2m. Comparative experiments with several CD models prove the effectiveness of the MSCANet, with the highest F1 of 64.67% on the high-resolution semantic CD dataset, and of 71.29% on CLCD.
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