DHANet: Dual-Stream Hierarchical Interaction Networks for Multimodal Drone Object Detection
- 11 June 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-13
Abstract
Drone-based remote sensing has become pivotal for high-resolution dynamic monitoring. However, the differences between day and night modes will trigger a mismatch in multi-scale object features under extreme lighting conditions. In this paper, we propose a dual-stream hierarchical interaction network for multimodal drone object detection, called DHANet, which enhances the distinguishability between multi-scale objects and background for each modality. Specifically, DHANet is designed with a Modality-Adaptive Asymmetric Attention Module (M-AAM) that enhances object-level semantic representations through global and local attention mechanisms. The M-AAM employs global context attention and local positional attention to replace conventional multi-scale context extraction, thereby effectively integrating spatial-channel information of objects. Furthermore, the network is equipped with a Multimodal Scale-Attentive Convolution (M-SC) module that dynamically generates modality-specific feature aggregation weights. This design enables global cross-modality information fusion while reducing computational complexity. Experimental results on two multimodal remote sensing benchmark datasets (DroneVehicle and VEDAI) and two natural datasets (LLVIP and FLIR) demonstrate the robustness and generalizability of DHANet. The codes will be openly and freely available at https://github.com/Victoria-xin1009/-IEEE TGRS DHANet for the sake of reproducibility.Keywords
Funding Information
- Natural Science Foundation of Beijing Municipality (L222041)
- Fundamental Research Funds for the Central Universities (2024RC06, 24820232023YQTD01)
- Key Laboratory of Target Cognition and Application Technology (2023-CXPT-LC-005)
This publication has 36 references indexed in Scilit:
- Multimodal self-supervised learning for remote sensing data land cover classificationPattern Recognition, 2024
- Cross-city matters: A multimodal remote sensing benchmark dataset for cross-city semantic segmentation using high-resolution domain adaptation networksRemote Sensing of Environment, 2023
- Translation, Scale and Rotation: Cross-Modal Alignment Meets RGB-Infrared Vehicle Detection2022
- DIVFusion: Darkness-free infrared and visible image fusionInformation Fusion, 2022
- Locality guided cross-modal feature aggregation and pixel-level fusion for multispectral pedestrian detectionInformation Fusion, 2022
- Cross-modality attentive feature fusion for object detection in multispectral remote sensing imageryPattern Recognition, 2022
- Arbitrary-Oriented Object Detection with Circular Smooth Label2020
- Vehicle detection of multi-source remote sensing data using active fine-tuning networkISPRS Journal of Photogrammetry and Remote Sensing, 2020
- Cross-modality interactive attention network for multispectral pedestrian detectionInformation Fusion, 2019
- Feature Pyramid Networks for Object Detection2017