Object Detection in Remote Sensing Imagery

Dear Colleagues,

The rapid growth in cities around the world has created an urgent need for better ways to monitor and manage urban environments. Remote sensing imagery, with its broad coverage and frequent revisits, offers a valuable source of information for understanding how cities evolve and interact with their surroundings. Turning these massive image datasets into useful insights, however, depends on reliable object detection—the automatic identification of buildings, vehicles, vegetation, and other key features. In recent years, deep learning has greatly improved detection performance in very-high-resolution imagery. Yet many challenges remain, including how to deal with multi-scale objects, complex backgrounds, and the shortage of high-quality annotations. Although this Special Issue focuses mainly on urban applications, we also welcome studies dealing with non-urban areas such as agricultural regions, forests, or disaster zones. Broader perspectives can help develop models that generalize across different environments and data sources.

This Special Issue aims to bring together the latest progress in object detection techniques and their applications in remote sensing. We encourage submissions that connect algorithmic innovation with practical use, showing how advanced methods can address real-world needs. Topics may include new deep learning and transformer architectures, interpretable AI models, and large-scale evaluation frameworks. We are particularly interested in emerging directions such as foundation models, geospatial large models, and open benchmark datasets, which are reshaping the landscape of remote sensing research. The theme fits well within Remote Sensing’s scope, advancing both theory and practice in the intelligent analysis of our changing environment.

1. Novel deep learning and transformer architectures for object detection in very-high-resolution (VHR) imagery.
2. Multi-scale, weakly supervised, few-shot, and zero-shot learning strategies for complex or data-scarce scenes.
3. Domain adaptation, transfer learning, and generalization across sensors and geographic regions.
4. Lightweight and efficient detection models for real-time or edge/onboard processing.
5. Integration of foundation models and geospatial large models for remote-sensing object detection and mapping.
6. Cross-modal and multi-source fusion of optical, SAR, LiDAR, and GIS data for improved feature extraction and detection.
7. Temporal and multi-view object detection for change analysis and dynamic scene understanding.
8. Uncertainty estimation, interpretability, and explainable AI frameworks for robust and transparent detection models.
9. Development of open benchmark datasets, reproducible workflows, and standardized evaluation protocols in remote-sensing object detection.
10. Urban mapping, infrastructure monitoring, and informal settlement detection based on object-level analysis.
11. Disaster detection and damage assessment for emergency response and resilience evaluation.
12. Agricultural, environmental, and socioeconomic monitoring using object-based indicators derived from remote-sensing imagery.

Dr. Dandan Ma
Dr. Zhiyu Jiang
Dr. Le Dong
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 250 words) can be sent to the Editorial Office for assessment.

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.

• object detection remote sensing
• deep learning
• foundation models
• transformer networks
• VHR imagery
• data fusion
• urban monitoring
• disaster and environmental assessment