Next Article in Journal
FLDSensing: Remote Sensing Flood Inundation Mapping with FLDPLN
Previous Article in Journal
Challenges and Opportunities in Predicting Future Beach Evolution: A Review of Processes, Remote Sensing, and Modeling Approaches
Previous Article in Special Issue
PolSAR-SFCGN: An End-to-End PolSAR Superpixel Fully Convolutional Generation Network
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

A Progressive Target-Aware Network for Drone-Based Person Detection Using RGB-T Images

by
Zhipeng He
1,2,
Boya Zhao
2,
Yuanfeng Wu
2,*,
Yuyang Jiang
2,3 and
Qingzhan Zhao
4
1
School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100049, China
2
Key Laboratory of Computational Optical Imaging Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
3
School of Optoelectronics, University of Chinese Academy of Sciences, Beijing 100049, China
4
Department of Computer Science and Technology, Shihezi University, Shihezi 832000, China
*
Author to whom correspondence should be addressed.
Remote Sens. 2025, 17(19), 3361; https://doi.org/10.3390/rs17193361 (registering DOI)
Submission received: 14 August 2025 / Revised: 24 September 2025 / Accepted: 2 October 2025 / Published: 4 October 2025

Abstract

Drone-based target detection using visible and thermal (RGB-T) images is critical in disaster rescue, intelligent transportation, and wildlife monitoring. However, persons typically occupy fewer pixels and exhibit more varied postures than vehicles or large animals, making them difficult to detect in unmanned aerial vehicle (UAV) remote sensing images with complex backgrounds. We propose a novel progressive target-aware network (PTANet) for person detection using RGB-T images. A global adaptive feature fusion module (GAFFM) is designed to fuse the texture and thermal features of persons. A progressive focusing strategy is used. Specifically, we incorporate a person segmentation auxiliary branch (PSAB) during training to enhance target discrimination, while a cross-modality background mask (CMBM) is applied in the inference phase to suppress irrelevant background regions. Extensive experiments demonstrate that the proposed PTANet achieves high accuracy and generalization performance, reaching 79.5%, 47.8%, and 97.3% mean average precision (mAP)@50 on three drone-based person detection benchmarks (VTUAV-det, RGBTDronePerson, and VTSaR), with only 4.72 M parameters. PTANet deployed on an embedded edge device with TensorRT acceleration and quantization achieves an inference speed of 11.177 ms (640 × 640 pixels), indicating its promising potential for real-time onboard person detection. The source code is publicly available on GitHub.
Keywords: UAV remote sensing imagery; person detection; cross-modality; global adaptive feature fusion; progressive target-aware network UAV remote sensing imagery; person detection; cross-modality; global adaptive feature fusion; progressive target-aware network

Share and Cite

MDPI and ACS Style

He, Z.; Zhao, B.; Wu, Y.; Jiang, Y.; Zhao, Q. A Progressive Target-Aware Network for Drone-Based Person Detection Using RGB-T Images. Remote Sens. 2025, 17, 3361. https://doi.org/10.3390/rs17193361

AMA Style

He Z, Zhao B, Wu Y, Jiang Y, Zhao Q. A Progressive Target-Aware Network for Drone-Based Person Detection Using RGB-T Images. Remote Sensing. 2025; 17(19):3361. https://doi.org/10.3390/rs17193361

Chicago/Turabian Style

He, Zhipeng, Boya Zhao, Yuanfeng Wu, Yuyang Jiang, and Qingzhan Zhao. 2025. "A Progressive Target-Aware Network for Drone-Based Person Detection Using RGB-T Images" Remote Sensing 17, no. 19: 3361. https://doi.org/10.3390/rs17193361

APA Style

He, Z., Zhao, B., Wu, Y., Jiang, Y., & Zhao, Q. (2025). A Progressive Target-Aware Network for Drone-Based Person Detection Using RGB-T Images. Remote Sensing, 17(19), 3361. https://doi.org/10.3390/rs17193361

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop