Hybrid-DETR: A Differentiated Module-Based Model for Object Detection in Remote Sensing Images
Open Access
- 20 December 2024
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 13 (24) , 5014
Abstract
Currently, embedded unmanned aerial vehicle (UAV) systems face significant challenges in balancing detection accuracy and computational efficiency when processing remote sensing images with complex backgrounds, small objects, and occlusions. This paper proposes the Hybrid-DETR model based on a real-time end-to-end Detection Transformer (RT-DETR), featuring a novel HybridNet backbone network that implements a differentiated hybrid structure through lightweight RepConv Cross-stage Partial Efficient Layer Aggregation Network (RCSPELAN) modules and the Heat-Transfer Cross-stage Fusion (HTCF) modules, effectively balancing feature extraction efficiency and global perception capabilities. Additionally, we introduce a Small-Object Detection Module (SODM) and an EIFI module to enhance the detection capability of small objects in complex scenarios, while employing the Focaler-Shape-IoU loss function to optimize bounding box regression. Experimental results on the VisDrone2019 dataset demonstrate that Hybrid-DETR achieves mAP50 and mAP50:95 scores of 52.2% and 33.3%, respectively, representing improvements of 5.2% and 4.3% compared to RT-DETR-R18, while reducing model parameters by 29.33%. The effectiveness and robustness of our improved method are further validated on multiple challenging datasets, including AI-TOD and HIT-UAV.Keywords
Funding Information
- Key Research and Development Plan Project of Heilongjiang (JD2023SJ19, LH2023F034, HJK2024B002)
- Natural Science Foundation of Heilongjiang Province (JD2023SJ19, LH2023F034, HJK2024B002)
- Science and Technology Project of Heilongjiang Provincial Department of Transportation (JD2023SJ19, LH2023F034, HJK2024B002)
This publication has 35 references indexed in Scilit:
- Rock fracture identification algorithm based on the confidence score and non-maximum suppressionBulletin of Engineering Geology and the Environment, 2024
- HIT-UAV: A high-altitude infrared thermal dataset for Unmanned Aerial Vehicle-based object detectionScientific Data, 2023
- Military technology and revolutions in warfare: priming the drone debateDefense & Security Analysis, 2023
- Farmland Obstacle Detection from the Perspective of UAVs Based on Non-local Deformable DETRAgriculture, 2022
- Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmarkISPRS Journal of Photogrammetry and Remote Sensing, 2022
- Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance SegmentationIEEE Transactions on Cybernetics, 2021
- MS-Faster R-CNN: Multi-Stream Backbone for Improved Faster R-CNN Object Detection and Aerial Tracking from UAV ImagesRemote Sensing, 2021
- Extended Feature Pyramid Network for Small Object DetectionIEEE Transactions on Multimedia, 2021
- Amateur Drone Monitoring: State-of-the-Art Architectures, Key Enabling Technologies, and Future Research DirectionsIEEE Wireless Communications, 2018
- Car Detection from Low-Altitude UAV Imagery with the Faster R-CNNJournal of Advanced Transportation, 2017