remotesensing-logo

Journal Browser

Journal Browser

Object Detection in Remote Sensing Images Based on Artificial Intelligence

A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "AI Remote Sensing".

Deadline for manuscript submissions: 29 December 2025 | Viewed by 1263

Special Issue Editors


E-Mail Website
Guest Editor
School of Astronautics, Harbin Institute of Technology (HIT), Harbin 150001, China
Interests: optical remote sensing image; automatic target detection and recognition; multi-source feature fusion; image interpretation application; artificial intelligence

E-Mail Website
Guest Editor
School of Astronautics, Harbin Institute of Technology (HIT), Harbin 150001, China
Interests: optical remote sensing image; automatic target detection and recognition; new system imaging; image acquisition and processing

E-Mail Website
Guest Editor
Department of Electronic Engineering, Tsinghua University (THU), Beijing 100084, China
Interests: optical remote sensing image; multimodal remote sensing; data fusion; foundation models; object detection; semantic segmentation

E-Mail Website
Guest Editor
Department of Geography, the University of Hong Kong, Hong Kong SAR, China.
Interests: hyperspectral image processing; deep learning; Image interpretation
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

The rapid advancement of remote sensing technologies, including high-resolution satellites, unmanned aerial vehicles (UAVs), and aerial sensors, has generated an unprecedented volume of geospatial data. Extracting meaningful information from this vast resource is critical for applications such as environmental monitoring, urban planning, disaster management, and agriculture. Object detection in remote sensing images (RSIs) plays a pivotal role in automating the identification and localization of objects (e.g., vehicles, buildings, ships, aircraft) within complex, large-scale scenes. However, the unique challenges of RSIs—such as varying scales, arbitrary orientations, dense arrangements, occlusions, and diverse background clutter—significantly hinder the performance of traditional computer vision methods.

Recent breakthroughs in artificial intelligence (AI), particularly deep learning (DL), have revolutionized object detection in RSIs. Techniques like convolutional neural networks (CNNs), transformer-based architectures, and hybrid models have demonstrated remarkable capabilities in addressing domain-specific challenges, enabling higher accuracy, robustness, and efficiency. Despite these advances, critical gaps remain, including the need for lightweight models for edge deployment, generalization across heterogeneous datasets, interpretability of AI decisions, and handling of low-resolution or weakly annotated data. Furthermore, emerging trends such as multimodal data fusion and few-shot learning demand deeper exploration.

This Special Issue seeks to compile cutting-edge research on AI-driven object detection in RSIs, emphasizing novel algorithms, benchmark datasets, and real-world applications. By fostering interdisciplinary collaboration, we aim to accelerate progress in this field, bridging the gap between theoretical innovation and practical implementation to meet the growing demands of global remote sensing communities.

(1) Advanced deep learning architectures for RSI object detection.
(2) Robust target detection methods under complex conditions such as dense target arrangement, occlusion, and background interference.
(3) Multi-modal data fusion detection models, such as optical, LiDAR, SAR, hyperspectral, multispectral and infrared.
(4) Weakly supervised, semi-supervised, or unsupervised object detection frameworks for scenarios with scarce annotations.
(5) Lightweight detection models for satellites, UAVs (Unmanned Aerial Vehicles), and other edge devices.
(6) New datasets and benchmarks for specific detection tasks.

Dr. Jianming Hu
Dr. Xiyang Zhi
Dr. Yong-Qiang Mao
Dr. Longfei Ren
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.

Keywords

  • remote sensing images
  • object detection
  • artificial intelligence
  • multimodal data fusion
  • frontier applications

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (2 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

21 pages, 7001 KB  
Article
CGNet: Remote Sensing Instance Segmentation Method Using Contrastive Language–Image Pretraining and Gated Recurrent Units
by Hui Zhang, Zhao Tian, Zhong Chen, Tianhang Liu, Xueru Xu, Junsong Leng and Xinyuan Qi
Remote Sens. 2025, 17(19), 3305; https://doi.org/10.3390/rs17193305 - 26 Sep 2025
Abstract
Instance segmentation in remote sensing imagery is a significant application area within computer vision, holding considerable value in fields such as land planning and aerospace. The target scales of remote sensing images are often small, the contours of different categories of targets can [...] Read more.
Instance segmentation in remote sensing imagery is a significant application area within computer vision, holding considerable value in fields such as land planning and aerospace. The target scales of remote sensing images are often small, the contours of different categories of targets can be remarkably similar, and the background information is complex, containing more noise interference. Therefore, it is essential for the network model to utilize the background and internal instance information more effectively. Considering all the above, to fully adapt to the characteristics of remote sensing images, a network named CGNet, which combines an enhanced backbone with a contour–mask branch, is proposed. This network employs gated recurrent units for the iteration of contour and mask branches and adopts the attention head for branch fusion. Additionally, to address the common issues of missed and misdetections in target detection, a supervised backbone network using contrastive pretraining for feature supplementation is introduced. The proposed method has been experimentally validated in the NWPU VHR-10 and SSDD datasets, achieving average precision metrics of 68.1% and 67.4%, respectively, which are 0.9% and 3.2% higher than those of the suboptimal methods. Full article
Show Figures

Figure 1

25 pages, 4796 KB  
Article
Vision-Language Guided Semantic Diffusion Sampling for Small Object Detection in Remote Sensing Imagery
by Jian Ma, Mingming Bian, Fan Fan, Hui Kuang, Lei Liu, Zhibing Wang, Ting Li and Running Zhang
Remote Sens. 2025, 17(18), 3203; https://doi.org/10.3390/rs17183203 - 17 Sep 2025
Viewed by 503
Abstract
Synthetic aperture radar (SAR), with its all-weather and all-day active imaging capability, has become indispensable for geoscientific analysis and socio-economic applications. Despite advances in deep learning–based object detection, the rapid and accurate detection of small objects in SAR imagery remains a major challenge [...] Read more.
Synthetic aperture radar (SAR), with its all-weather and all-day active imaging capability, has become indispensable for geoscientific analysis and socio-economic applications. Despite advances in deep learning–based object detection, the rapid and accurate detection of small objects in SAR imagery remains a major challenge due to their extremely limited pixel representation, blurred boundaries in dense distributions, and the imbalance of positive–negative samples during training. Recently, vision–language models such as Contrastive Language-Image Pre-Training (CLIP) have attracted widespread research interest for their powerful cross-modal semantic modeling capabilities. Nevertheless, their potential to guide precise localization and detection of small objects in SAR imagery has not yet been fully exploited. To overcome these limitations, we propose the CLIP-Driven Adaptive Tiny Object Detection Diffusion Network (CDATOD-Diff). This framework introduces a CLIP image–text encoding-guided dynamic sampling strategy that leverages cross-modal semantic priors to alleviate the scarcity of effective positive samples. Furthermore, a generative diffusion-based module reformulates the sampling process through iterative denoising, enhancing contextual awareness. To address regression instability, we design a Balanced Corner–IoU (BC-IoU) loss, which decouples corner localization from scale variation and reduces sensitivity to minor positional errors, thereby stabilizing bounding box predictions. Extensive experiments conducted on multiple SAR and optical remote sensing datasets demonstrate that CDATOD-Diff achieves state-of-the-art performance, delivering significant improvements in detection robustness and localization accuracy under challenging small-object scenarios with complex backgrounds and dense distributions. Full article
Show Figures

Figure 1

Back to TopTop