Submit to Special Issue Submit Abstract to Special Issue Review for Remote Sensing Propose a Special Issue

Journal Menu

Journal Browser

Multi-Sensor Fusion for UAV Remote Sensing: Deep Learning-Driven Target Detection in Complex Environments

Editors
Special Issue Information
Keywords
Benefits of Publishing in a Special Issue
Published Papers

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

Deadline for manuscript submissions: 31 October 2026 | Viewed by 2020

Share This Special Issue

Editors

Prof. Dr. Yong Jia

E-Mail Website
Guest Editor

School of Mechanical and Electrical Engineering, Chengdu University of Technology, Chengdu 610059, China
Interests: radar detection in urban environments; radar based human sensing; emitter recognition; signal and data processing
Special Issues, Collections and Topics in MDPI journals

Prof. Dr. Shisheng Guo

E-Mail Website
Guest Editor

School of Information and Communication Engineering, University of Electronic Science and Technology of China (UESTC), Chengdu 611731, China
Interests: radar-based target tracking; UWB radar target detection
Special Issues, Collections and Topics in MDPI journals

Dr. Yongping Song

E-Mail
Guest Editor

the College of Electronic Science, National University of Defense Technology, Changsha, China
Interests: SAR; radar signal processing

Special Issue Information

Dear Colleagues,

Unmanned Aerial Vehicle (UAV) remote sensing has emerged as a transformative technology in wide-spread applications including environmental monitoring, disaster response and security surveillance, due to the unparalleled flexibility, high spatial resolution, cost-efficiency and so on. However, the complex environments characterized by variable illumination, obstacle occlusion and cluttered background pose significant challenges to the target detection task for traditional single-modal UAV remote sensing systems. Specifically, single-modal sensing (e.g., optical, thermal, radar, or LiDAR) often suffers from inherent limitations. For instance, optical sensors are susceptible to illumination changes and occlusion, thermal sensors lack spatial detail, and radar/LiDAR may struggle with fine-grained target discrimination. In this context, multi-sensor fusion (MSF) has become a critical solution to complement the strengths and mitigate the weaknesses of individual sensors, enabling more robust and reliable data acquisition. Meanwhile, the rapid advancement of deep learning (DL) techniques such as convolutional neural networks, transformer models, and point cloud processing frameworks has revolutionized feature extraction and target recognition, providing powerful tools to model complex relationships in fused multi-modal data. The synergy between MSF and DL has thus become a pivotal research direction, addressing the urgent need for accurate, real-time target detection in complex UAV remote sensing scenarios and driving innovations in both academic research and practical applications.

This Special Issue aims to showcase cutting-edge research on multi-sensor fusion for UAV remote sensing, with a specific focus on deep learning-driven target detection in complex environments. This Special Issue aligns closely with the scope of journals focusing on remote sensing, sensor technology, artificial intelligence, and aerospace engineering, as it bridges the gap between multi-sensor system design, deep learning algorithm development, and real-world UAV applications. By integrating insights from multiple disciplines, this Special Issue will provide a comprehensive platform for researchers and practitioners to share innovations, discuss critical issues, and advance the state-of-the-art in intelligent target detection for UAV remote sensing in complex environments.

This Special Issue seeks to bring together original research articles, reviews, and technical notes that explore novel methodologies, validate practical applications, and address key challenges in this interdisciplinary field. Topics of interest include, but are not limited to, multi-modal data fusion strategies, DL-based feature learning for heterogeneous sensor data, target detection models optimized for UAV platforms, non-line-of-sight (NLOS) target detection and application-specific solutions (e.g., disaster monitoring and post-disaster assessment, crop monitoring, ecological environment monitoring, military surveillance or infrastructure inspection).

Prof. Dr. Yong Jia
Prof. Dr. Shisheng Guo
Dr. Yongping Song
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-anonymized 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

UAV remote sensing
multi-sensor fusion
deep learning
complex environments
target detection
multimodal data registration

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)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

33 pages, 21482 KB

Open AccessArticle

Infrared–Visible Multi-Sensor Fusion for UAV Photovoltaic Defect Detection Under Real-World Weak Misalignment

by Yuting Wang, Zhengnan Hu, Xubin Peng, Chenhao Sun and Zhiwei Jia

Remote Sens. 2026, 18(15), 2607; https://doi.org/10.3390/rs18152607 - 5 Aug 2026

Viewed by 239

Abstract

For large-scale photovoltaic plant inspection, UAV-based infrared–visible real-time detection can combine thermal abnormality information with appearance and structural cues. This is useful for improving inspection and maintenance efficiency. However, in real UAV inspection, differences in sensor resolution, field of view, and flight attitude can cause weak misalignment between the two modalities. Since complex image registration is difficult to perform before real-time inference, this misalignment can affect cross-modal feature fusion and defect localization. To address this problem, this paper proposes Frequency-Aware Fusion YOLO (FAF-YOLO) for dual-modal photovoltaic defect detection. We also build a real-scene infrared–visible dual-modal photovoltaic defect dataset, named DM-PV, which covers six defect categories related to thermal anomalies and external environmental interference. FAF-YOLO is based on a dual-branch YOLO detection framework. The C3k2-DPRG module is used to enhance defect boundaries, local details, and neighborhood context. The Frequency-aware Selective Fusion (FSF) module models low-frequency structural information and high-frequency detail responses separately, which reduces edge ghosting and background mis-fusion caused by weak misalignment. A Multi-Scale Differentiated Decoupled Head is then used to handle scale-specific prediction and improve small-defect localization and regional-anomaly discrimination. Experimental results show that FAF-YOLO achieves 92.5% Precision, 86.7% Recall, 91.7%

{mAP}_{50}

, and 61.4%

{mAP}_{50 : 95}

on the DM-PV dataset. It outperforms several mainstream dual-modal detection methods and has lower parameters and computational complexity. Further tests for real-time inspection show that the proposed method keeps more stable performance under weak misalignment perturbations. It also reaches an inference speed of 33 FPS on the Jetson Orin Nano edge platform, which verifies its effectiveness and deployability for UAV-based real-time photovoltaic inspection. Full article

(This article belongs to the Special Issue Multi-Sensor Fusion for UAV Remote Sensing: Deep Learning-Driven Target Detection in Complex Environments)

► Show Figures

Figure 1

18 pages, 37858 KB

Open AccessArticle

Seeing Through Sparse Foliage: Quality–Occlusion-Guided RGB–Thermal Fusion for Drone-Based Person Detection

by Ziming Gui, Shaobo Liu, Dong Yang, Tongyuan Zou, Haoran Zhu and Wen Yang

Remote Sens. 2026, 18(5), 774; https://doi.org/10.3390/rs18050774 - 4 Mar 2026

Viewed by 1061

Abstract

Drone-based RGBT person detection facilitates critical applications such as search and rescue, owing to its high maneuverability and inherent capability to mitigate visual occlusion. However, despite the complementary nature of RGBT systems, existing detectors often overlook the specific impact of occlusion during the fusion process, leading to feature contamination and subsequent detection failures. In this work, we address this limitation by formally defining two categories of occlusion: “soft occlusion,” where targets remain partially visible in at least one modality, and “hard occlusion,” which involves complete obstruction. To tackle these challenges, we propose Unveiling Occluded Targets (UOT), a novel multi-modal fusion framework that implements a Quality–Occlusion Arbitration (QOA) mechanism. By leveraging both quality-related and occlusion-related cues, UOT dynamically arbitrates the fusion process to maximize information recovery from the clearer modality. Extensive experiments on the RGBTDronePerson and VTUAV-det datasets demonstrate significant improvements, achieving an

m A P_{50}^{a l l}

of 53.42% and an

m A P_{50}^{t i n y}

of 54.70% in densely occluded scenes. Qualitative analysis further confirms UOT’s robustness in reliably identifying targets obstructed by sparse foliage. Full article