Skip to main content

About this Research Topic

Manuscript Submission Deadline 11 January 2023

In recent years, remote sensing image interpretation has attracted much more attention. Many supervised learning methods have been proposed. However, these methods usually require a large number of high-quality training samples. Moreover, their performance heavily relies on the quality of the labeled samples. In real-world applications, it is computationally expensive and time-consuming to annotate large-scale remote sensing images with high-quality labels, leading to the fact that the number of training samples is very limited. In some cases, only coarse-grained labels are available, resulting in a multi-label classification problem. In addition, the manually labeled samples may be wrong and that causes a noisy label problem. Therefore, remote sensing image interpretation still faces several problems, including incomplete, inexact, and inaccurate samples, which seriously limit the development and application of remote sensing technologies.

This Research Topic focuses on weakly supervised learning for remote sensing image interpretation. It will foster newly advanced methods for remote sensing image interpretation. This Research Topic mainly includes remote sensing image processing, image classification, object detection, multi-source, and multi-temporal image interpretation, and related applications, such as precision agriculture, urban investigation, and disaster monitoring.

We welcome submissions based on but not limited to:
• Remote sensing image processing (denoising, dehazing, shadow removal, etc.);
• Remote sensing image classification with weak supervision (scarce sample, multi-label classification, noisy label, etc.);
• Remote sensing object detection (object detection, anomaly detection, camouflage target detection, etc.);
• Multi-source and multi-temporal image interpretation (hyperspectral image, multispectral image, SAR, LiDAR data, etc.);
• Weakly supervised learning theory and its application in remote sensing images;
• Quality evaluation for remote sensing image interpretation;
• Co-training and multi-task learning in remote sensing images;
• Earth observation applications in remote sensing images (precision agriculture, urban investigation, disaster monitoring, 3D measurements by lidar of the land cover features, etc.).

Keywords: Remote sensing image, image classification, object detection, weakly supervised learning, earth observation applications


Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.

In recent years, remote sensing image interpretation has attracted much more attention. Many supervised learning methods have been proposed. However, these methods usually require a large number of high-quality training samples. Moreover, their performance heavily relies on the quality of the labeled samples. In real-world applications, it is computationally expensive and time-consuming to annotate large-scale remote sensing images with high-quality labels, leading to the fact that the number of training samples is very limited. In some cases, only coarse-grained labels are available, resulting in a multi-label classification problem. In addition, the manually labeled samples may be wrong and that causes a noisy label problem. Therefore, remote sensing image interpretation still faces several problems, including incomplete, inexact, and inaccurate samples, which seriously limit the development and application of remote sensing technologies.

This Research Topic focuses on weakly supervised learning for remote sensing image interpretation. It will foster newly advanced methods for remote sensing image interpretation. This Research Topic mainly includes remote sensing image processing, image classification, object detection, multi-source, and multi-temporal image interpretation, and related applications, such as precision agriculture, urban investigation, and disaster monitoring.

We welcome submissions based on but not limited to:
• Remote sensing image processing (denoising, dehazing, shadow removal, etc.);
• Remote sensing image classification with weak supervision (scarce sample, multi-label classification, noisy label, etc.);
• Remote sensing object detection (object detection, anomaly detection, camouflage target detection, etc.);
• Multi-source and multi-temporal image interpretation (hyperspectral image, multispectral image, SAR, LiDAR data, etc.);
• Weakly supervised learning theory and its application in remote sensing images;
• Quality evaluation for remote sensing image interpretation;
• Co-training and multi-task learning in remote sensing images;
• Earth observation applications in remote sensing images (precision agriculture, urban investigation, disaster monitoring, 3D measurements by lidar of the land cover features, etc.).

Keywords: Remote sensing image, image classification, object detection, weakly supervised learning, earth observation applications


Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.

Topic Editors

Loading..

Topic Coordinators

Loading..

Articles

Sort by:

Loading..

Authors

Loading..

views

total views views downloads topic views

}
 
Top countries
Top referring sites
Loading..

Share on

About Frontiers Research Topics

With their unique mixes of varied contributions from Original Research to Review Articles, Research Topics unify the most influential researchers, the latest key findings and historical advances in a hot research area! Find out more on how to host your own Frontiers Research Topic or contribute to one as an author.