高光谱成像
计算机科学
模式识别(心理学)
人工智能
残余物
棱锥(几何)
变更检测
判别式
卷积神经网络
图像分辨率
核(代数)
空间分析
特征(语言学)
卷积(计算机科学)
特征提取
遥感
计算机视觉
作者
Yufei Yang,Jiahui Qu,Song Xiao,Wenqian Dong,Yunsong Li,Qian Du
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing
[Institute of Electrical and Electronics Engineers]
日期:2022-01-01
卷期号:: 1-1
标识
DOI:10.1109/tgrs.2022.3161386
摘要
Change detection plays an important role in Earth surface observation and has been extensively investigated over recent decades. A hyperspectral image (HSI) with high spectral resolution provides abundant ground object information, which is expected by finer change detection. The existing convolutional neural network (CNN) based methods extract image feature with a fixed kernel, which is incompetent to cope with complicated object details at diverse scales in HSI. In this paper, we propose a deep multiscale pyramid network enhanced with spatial-spectral residual attention (DMPs2raN) for HSI change detection, which has strong capability to mine multilevel as well as multiscale spatial-spectral features, improving the performance in complex changed regions. There are two key characteristics: (i) the multiscale spatial-spectral features are extracted by the multiscale pyramid convolution, and enhanced by spatial-spectral residual attention module (S2RAM) of each scale; (ii) the multilevel features are obtained by aggregating the multiscale features level by level. As a result of this design, the proposed DMPs2raN learns more discriminative features with both strong semantic information and rich spatial-spectral information. Experiments carried out on three datasets demonstrate competitive performance of the proposed method in both qualitative and quantitative analysis.
科研通智能强力驱动
Strongly Powered by AbleSci AI