Advanced Deep Learning Techniques for Information Extraction and Analysis of Remote Sensing Imagery

Dear Colleagues,

Remote sensing images are captured through sensors mounted on aircraft and satellites, detecting electromagnetic radiation at different wavelengths, such as visible and LiDAR, reflected or emitted from the Earth's surface or atmosphere. This technology provides critical information about the physical properties and characteristics of observed areas. As a result, remote sensing images have found widespread applications in agriculture, environmental monitoring, disaster response, urban planning, and geological exploration. The rapid advancements in remote sensing technology for Earth observation have led to rapid growth in the scale, dimensions, resolution, and complexity of remote sensing data, demanding the more effective utilization of advanced deep learning techniques to extract and analyze meaningful information.

However, despite the significant breakthroughs achieved by using deep learning for the extraction and analysis of remote sensing data, thoroughly analyzing the semantic content of each remote sensing image is still confounded by significant challenges, e.g., the generalization capacity is limited in few-shot or zero-shot settings, the matching and fusion of multimodal images present significant difficulties, high computing and manual labeling costs, etc. To address these challenges, the community must continue to develop advanced technologies such as self-supervised learning, reinforcement learning, and large-scale foundational modeling to alleviate existing technical bottlenecks and further promote the broad application of remote sensing images.

This Special Issue encourages researchers to submit papers focused on leveraging advanced deep learning techniques to enhance the extraction and analysis of remote sensing information. We particularly welcome research on the latest advancements in theoretical methods and applied technologies, offering cutting-edge insights across various domains of remote sensing, including but not limited to the following topics:

• Unsupervised, semi-supervised, weakly supervised, and self-supervised remote sensing image information extraction and analysis;
• Few-shot or zero-shot remote sensing image representation;
• Remote sensing image feature interpretation;
• Remote sensing target detection;
• Remote sensing image matching;
• Multimodal remote sensing image fusion;
• Remote sensing image segmentation;
• Acceleration or compression of remote sensing image analysis models;
• Other topics related to remote sensing image analysis applications.

This Special Issue will promote the use of advanced deep learning techniques to enhance the extraction and analysis of remote sensing information. This topic is included in the scope of Remote Sensing and is a popular research direction in the journal.

This Special Issue welcomes contributions related to the following topics:

• Unsupervised, semi-supervised, weakly supervised, and self-supervised remote sensing image information extraction and analysis;
• Few-shot or zero-shot remote sensing image representation;
• Remote sensing image feature interpretation;
• Remote sensing target detection;
• Remote sensing image matching;
• Multimodal remote sensing image fusion;
• Remote sensing image segmentation;
• Acceleration or compression of remote sensing image analysis models;
• Other topics related to remote sensing image analysis applications.

Dr. Hao Zhu
Prof. Dr. Biao Hou
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• image fusion
• image segmentation
• object detection
• model acceleration or compression
• image matching