Recent Advances in Deep Learning-Based High-Resolution Image Processing and Analysis

Dear Colleagues,

The advent of advanced sensors and imaging techniques has led to an exponential growth in the volume of high-resolution remote sensing images. The rich information contained in these images has made them indispensable in domains such as urban planning, precision agriculture, environmental monitoring, and disaster risk reduction. However, to fully harness their potential, there is a critical need for efficient and robust image processing and analysis techniques.

As remote sensing data continue to grow in complexity and scale, the development of innovative methods for image classification, segmentation, and change detection becomes essential. These advances will not only enhance decision-making processes but also support the sustainable management of resources, climate monitoring, and rapid response to natural disasters. The integration of machine learning, artificial intelligence, and big data analytics is increasingly shaping the landscape of remote sensing research and pushing the boundaries of what is possible.

This Special Issue aims to highlight the latest developments and innovations in the field of high-resolution satellite or aerial images, covering a broad spectrum of topics on deep learning-based image processing and analysis methods. The contributions will focus on advanced classification, detection, and fusion techniques that enable precise scene-level, object-level, and pixel-level land surface understanding. The integration of recent deep learning techniques, for example, large pre-trained multi-modality models and earth observation tasks, such as land cover classification, change detection, and object detection, will be a key highlight, showcasing how these techniques are revolutionizing the analysis of high-resolution remote sensing images in the realm of geosciences. Furthermore, the Issue will also explore novel applications demonstrating the practical impact of recent advances in high-resolution image analysis, underscoring the transformative potential of these technologies in addressing real-world challenges.

The scope includes, but is not limited to, the following:

• Large multi-modality models for earth observation tasks;
• generalizable deep learning methods for high-resolution image classification, object detection, and change detection;
• the transfer of computer vision models for robust high-resolution image interpretation;
• efficient deep learning architectures for large-scale high-resolution image analysis;
• semi-supervised and unsupervised methods for image segmentation and change detection;
• multi-source remote sensing image fusion and image registration methods;
• remote sensing foundation models and their applications;
• large vision language models for the understanding of remote sensing images;
• large-scale high-resolution remote sensing image datasets;
• generative models in remote sensing;
• remote sensing image super-resolution;
• image denoising;
• explainable AI in remote sensing.

Dr. Chenxiao Zhang
Dr. Zhuo Zheng
Dr. Nour Aburaed
Guest Editors

Hongruixuan Chen
Guest Editor Assistant
Affiliation: Graduate School of Frontier Sciences, The University of Tokyo
Email: [email protected]
Webpage: https://chrx97.com/
Interests: Remote Sensing, Deep Learning, Domain Adaptation, Change Detection, Damage Assessment

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.

• high-resolution images
• deep learning
• image classification
• change detection
• object detection
• image processing and analysis
• foundation model
• image generation