In unmanned aerial vehicle (UAV) aerial photography tasks, the core challenge for achieving precision detection in complex environments lies in effectively suppressing inter-modal interference while efficiently fusing cross-modal complementary features. To address this challenge, this paper proposes PCMA-Net, a dual-modal fusion algorithm for small object detection in UAV imagery. First, a parallel attention and gated recalibration module is designed. By capturing detailed features through a parallel dual-path architecture and employing dynamic gated masking for secondary feature refinement, this module suppresses complex background artifacts and enhances the model's discriminative power for small objects in complex backgrounds. Second, a cross-modal attention interaction module is constructed. By pre-modeling the response distribution to focus on salient regions, it utilizes bidirectional cross-attention to achieve pixel-level dynamic alignment of heterogeneous features, thereby resolving feature mismatch and submergence issues. Finally, we propose dual-branch attention guided convolution, which utilizes channel splitting and task-aware weight generation to achieve global context modeling with minimal overhead, thereby improving inference efficiency on embedded platforms. Experimental results on the DroneVehicle dataset demonstrate that the proposed method outperforms the baseline and state-of-the-art fusion algorithms by 1.9% and 1.7% in mAP@0.5, respectively. Furthermore, on the VEDAI dataset, PCMA-Net exceeds the baseline by 5.6% in mAP@0.5 and achieves state-of-the-art performance across most specific categories. Notably, PCMA-Net achieves a detection speed of 45.1 FPS, fully meeting the real-time requirements for UAV-based deployment.
[1] CHENG J, DENG C, SU Y, et al.Methods and datasets on semantic segmentation for Unmanned Aerial Vehicle remote sensing images: A review[J].ISPRS Journal of Photogrammetry and Remote Sensing, 2024, 211(000):1-34
[2] LENG J, YE Y, MO M ,et al. Recent Advances for Aerial Object Detection: A Survey[J].ACM Computing Surveys, 2024, 56(12):1-36.
[3] 吴一全,童康.基于深度学习的无人机航拍图像小目标检测研究进展[J].航空学报,2025,46,(3):174-200.WU YQ，TONG K. Research advances on deep learning-based small object detection in UAV aerial images［J］.Acta Aeronautica et Astronautica Sinica，2025，46（3）：030848（in Chinese）.
[4] TELIKANI A, SARKAR A, DU B, et al. Autonomous Aerial Vehicles-Aided Intelligent Transportation Systems: Vision, Challenges, and Opportunities[J].IEEE Commu-nications Surveys & Tutorials,2025,27,(6):3772-3819.
[5] IJAZ H, AHMAD R, AHMED R, et al. A UAV-Assisted Edge Framework for Real-Time Disaster Manage-ment[J].IEEE Transactions on Geoscience and Remote Sensing,2023,61,1-1.
[6] FANG Z X, SAVKIN, ANDREY V. Strategies for Opti-mized UAV Surveillance in Various Tasks and Scenarios: A Review[J].Drones,2024,8,(5).
[7] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and se-mantic segmentation[C].//27th IEEE Conference on Com-puter Vision and Pattern Recognition (CVPR). Pisca-taway： IEEE Press，2014:580-587.
[8] GIRSHICK R. Fast R-CNN[C].//IEEE International Con-ference on Computer Vision（ICCV）. Piscataway： IEEE Press，2015:1440-1448.
[9] REN S, HE K, GIRSHICK R ,et al. Faster R-CNN: To-wards Real-Time Object Detection with Region Proposal Networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39,(6):1137-1149.
[10] REDMON J, DIVVALA S, GIRSHICK R, et al. You Only Look Once: Unified, Real-Time Object Detec-tion[C].//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway： IEEE Press，2016:779-788.
[11] REDMON J，FARHADI A. YOLOv3：An incremental improvement［EB/OL］：arXiv preprint：1804.02767，2018.
[12] JOCHER G, CHAURASIA A, QIU J. Ultralytics YOLO (Version 8.0.0)[EB/OL]. 2023：Available: https://github.com/ultralytics/ultralytics
[13] LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single Shot MultiBox Detector[C].//14th European Conference on Computer Vision (ECCV). Cham：Springer.2016:21-37.
[14] CARION N, MASSA F, SYNNAEVE G, et al. End-to-End Object Detection with Transformers[C].//16th Euro-pean Conference on Computer Vision(ECCV). Cham：Springer.2020:213-229.
[15] LIN T Y，DOLLáR P，GIRSHICK R，et al. Feature pyramid networks for object detection［C］2017 IEEE Conference on Computer Vision and Pattern Recognition（CVPR）. Piscataway：IEEE Press，2017：936-944.
[16] LIN T Y，GOYAL P，GIRSHICK R，et al. Focal loss for dense object detection［C］∥2017 IEEE Internation-al Conference on Computer Vision（ICCV）.Piscataway：IEEE Press，2017：2999-3007
[17] DING J，XUE N，LONG Y，et al. Learning RoI transformer for oriented object detection in aerial images［C］∥2019 IEEE/CVF Conference on Computer Vsion and Pattern Recognition（CVPR）. Piscataway: IEEE Press，2019：2844-2853.
[18] HAN J M, DING J, XUE N, et al. ReDet: A Rotation-equivariant Detector for Aerial Object Detec-tion[C].//IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway： IEEE Press，2021:2785-2794.
[19] 于傲泽，魏维伟，王平，等． 基于分块复合注意力的无人机小目标检测算法［J］．航空学报，2024，45（14）：629148．YUA Z，WEI W W，WANG P，et al. Small target detection algorithm for UAV based on patch-wise co-attention［J］.Acta Aeronautica et As-tronautica Sinica，2024，45（14）：629148（in Chi-nese）.
[20] 李子豪，王正平，贺云涛． 基于自适应协同注意力机制的航拍密集小目标检测算法［J］．航空学报，2023，44（13）：327944．LI Z H，WANG Z P，HE Y T. Aerial-photography dense small target detection algo-rithm based on adaptive cooperative attention mechanism［J］.Acta Aeronautica et Astronautica Sinica，2023，44（13）：327944（in Chinese）.
[21] 刘延芳,佘佳宇,袁秋帆等.无人机遥感图像实时小目标检测方法[J].航空学报,2024,45,(14):53-72.LIU YF， SHE J Y，YUAN Q F，et al. Real-time small target de-tection networks for UAV remote sensing［J］.Acta Aeronautica et Astronautica Sinica，2024，45（14）：630119（in Chinese）.
[22] XIAO Y, XU T F, XIN Y, et al. FBRT-YOLO: Faster and Better for Real-Time Aerial Image Detection[C].//39th AAAI Conference on Artificial Intelligence.2025:8673-8681.
[23] LI C L, YANG T J N, ZHU S J, et al. Density Map Guided Object Detection in Aerial Images[C].//IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway： IEEE Press，2020:737-746.
[24] ZHANG Y, YE M, ZHU G Y, et al. FFCA-YOLO for Small Object Detection in Remote Sensing Imag-es[J].IEEE Transactions on Geoscience and Remote Sens-ing,2024,62:1-14.
[25] HU L, YUAN J W, CHENG B L, et al. CSFPR-RTDETR: Real-Time Small Object Detection Network for UAV Images Based on Cross-Spatial-Frequency Domain and Position Relation[J].IEEE Transactions on Geosci-ence and Remote Sensing,2025,63:3601828.
[26] TANG L F, YUAN J T, ZHANG H, et al. PIAFusion: A progressive infrared and visible image fusion network based on illumination aware[J].Information Fu-sion,2022,83-84,79-92.
[27] 常凯旋,黄建华,孙希延等.基于双模态图像融合的无人机光学小目标检测算法[J].激光与光电子学进展,2025,62,(4):269-283. CHANG K X,HUANG J H, SUN X Y，et al. Optical Small Target Detection Method by Drone Based on Dual-Modal Image Fusion［J］.Laser & Optoelectronics Progress, 2025,62,(4): 269-283（in Chinese）.
[28] FANG Q Y, HAN D P, WANG Z K. Cross-Modality Fusion Transformer for Multispectral Object Detec-tion[DB/OL].arXiv preprint.2111.00273,2021.
[29] ZENG Y Q, LIANG T F, JIN Y, et al. MMI-Det: Explor-ing Multi-Modal Integration for Visible and Infrared Ob-ject Detection[J].IEEE Transactions on Circuits and Sys-tems for Video Technology,2024,34,(11):11198-11213.
[30] YUAN M X, WEI X X.C2Former: Calibrated and Com-plementary Transformer for RGB-Infrared Object Detec-tion[J].IEEE Transactions on Geoscience and Remote Sensing, 2024, 62:1-12.
[31] GUO J J, GAO C Q, LIU F C, et al. DPDETR: Decou-pled Position Detection Transformer for Infrared-Visible Object Detection[DB/OL].arXiv pre-print.2408.06123.2025.
[32] DONG W H, ZHU H D, LIN S H , et al. Fusion-Mamba for Cross-Modality Object Detection[J].IEEE Transac-tions on Multimedia,2025,27,7392-7406.
[33] ZHOU M H, LI T Y, QIAO C F, et al. DMM: Disparity-Guided Multispectral Mamba for Oriented Object Detec-tion in Remote Sensing[J].IEEE Transactions on Geosci-ence and Remote Sensing,2025,63:3578309.
[34] YU C S, SHIN Y A. A Cross-Modality Feature Adaptive Interaction Approach for RGB-Infrared Object Detection in Aerial Imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2026,64:3657379.
[35] ZHU P, SUN Y, WEN L, et al. Drone Based RGBT Ve-hicle Detection and Counting: A Challenge[DB/OL].arXiv preprint.2003.02437.2020.
[36] RAZAKARIVONY S, JURIE F. Vehicle detection in aerial imagery : A small target detection bench-mark[J].Journal of Visual Communication and Image Representation,2016,34:187-203.
CJA