MBFE-DETR：多尺度边界特征增强下的无人机目标检测算法

doi:10.3778/j.issn.1002-8331.2503-0307

摘要/Abstract

摘要： 针对无人机视角下背景复杂、小目标比例较高且样本不平衡等问题，提出一种基于改进RT-DETR的无人机目标检测算法MBFE-DETR。设计一种基于C2f和单头自注意力模块的轻量化主干网络，降低模型参数量的同时提升网络的特征提取能力。提出多尺度边界特征增强协同网络MBFECN，通过其特有的多尺度边界特征增强机制和高效特征融合策略，解决了原模型在保持小目标边界细节方面的不足。引入Focaler-MPDIoU考虑框的位置匹配关系，同时通过线性区间映射重构原有IoU损失，使模型在复杂场景下的定位效果更好。针对样本不平衡的问题，采用新的分类损失函数ESVLoss，对分类损失值进行分段加权调整，并结合指数移动平均机制对权重进行动态平滑更新，使模型更具适应性。实验结果表明，在VisDrone2019-DET和DOTAv1.0数据集上，MBFE-DETR算法的mAP50分别提升3.9和2.9个百分点，同时参数量减少了21.6%。

关键词: 无人机目标检测, RT-DETR, 单头自注意力, 边界特征增强

Abstract: Aiming at problems such as complex backgrounds, high proportion of small targets, and sample imbalance in drone perspective views, an improved drone object detection algorithm based on RT-DETR called MBFE-DETR is proposed. Firstly, a lightweight backbone network based on C2f and single-head self-attention modules is designed, reducing model parameters while enhancing feature extraction capabilities. Secondly, a multi-scale boundary feature enhancement collaborative network (MBFECN) is proposed, which addresses the original model’s deficiencies in preserving small target boundary details through its unique multi-scale boundary feature enhancement mechanism and efficient feature fusion strategy. Then, Focaler-MPDIoU is introduced to consider the positional matching relationship between bounding boxes, while reconstructing the original IoU loss through linear interval mapping, resulting in better localization performance in complex scenes. Finally, to address sample imbalance, a new classification loss function called ESVLoss is adopted, which applies segmented weighted adjustments to classification loss values and combines an exponential moving average mechanism to dynamically update weights smoothly, making the model more adaptive. Experimental results show that on the VisDrone2019-DET and DOTAv1.0 datasets, the MBFE-DETR algorithm improves mAP50 by 3.9 and 2.9 percentage points respectively, while reducing parameters by 21.6%.

Key words: UAV object detection, RT-DETR, single-head self-attention, boundary feature enhancement

张晞, 赖惠成, 姜迪, 汤静雯, 高古学, 袁婷婷, 聂源. MBFE-DETR：多尺度边界特征增强下的无人机目标检测算法[J]. 计算机工程与应用, 2025, 61(17): 89-101.

ZHANG Xi, LAI Huicheng, JIANG Di, TANG Jingwen, GAO Guxue, YUAN Tingting, NIE Yuan. MBFE-DETR： Multi-Scale Boundary Feature Enhancement for Drone Target Detection Algorithm[J]. Computer Engineering and Applications, 2025, 61(17): 89-101.

参考文献

[1] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2014: 580-587.
[2] GIRSHICK R. Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision. Piscataway: IEEE, 2015: 1440-1448.
[3] REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(6): 1137-1149.
[4] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recogn-ition. Piscataway: IEEE, 2016: 779-788.
[5] LI C Y, LI L, JIANG H L, et al. YOLOv6: a single-stage object detection framework for industrial applications[J]. arXiv:2209.02976, 2022.
[6] GE Z, LIU S, WANG F, et al. YOLOX: exceeding YOLO series in 2021[J]. arXiv:2107.08430, 2021.
[7] WANG C Y, BOCHKOVSKIY A, LIAO H M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2023: 7464-7475.
[8] WANG C Y, YEH I H, LIAO H P. YOLOv9: learning what you want to learn using programmable gradient information[J]. arXiv:2402.13616, 2024.
[9] WANG A, CHEN H, LIU L H, et al. YOLOv10: real-time end-to-end object detection[J]. arXiv:2405.14458, 2024.
[10] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proceedings of the European Conference on Computer Vision. Cham: Springer International Publishing, 2016: 21-37.
[11] TAN M X, PANG R M, LE Q V. EfficientDet: scalable and efficient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 10778-10787.
[12] ZHANG S F, WEN L Y, BIAN X, et al. Single-shot refinement neural network for object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 4203-4212.
[13] SAHIN O, OZER S. YOLODrone: improved YOLO architecture for object detection in drone images[C]//Proceedings of the 44th International Conference on Telecommunications and Signal Processing. Piscataway: IEEE, 2021: 361-365.
[14] 李成豪, 张静, 胡莉, 等. 基于多尺度感受野融合的小目标检测算法[J]. 计算机工程与应用, 2022, 58(12): 177-182.
LI C H, ZHANG J, HU L, et al. Small object detection algorithm based on multiscale receptive field fusion[J]. Computer Engineering and Applications, 2022, 58(12): 177-182.
[15] 聂源, 赖惠成, 高古学. 改进YOLOv7+Bytetrack的小目标检测与追踪[J]. 计算机工程与应用, 2024, 60 (12): 189-202.
NIE Y, LAI H C, GAO G X. Improved YOLOv7+Bytetrack small target detection and tracking[J]. Computer Engineering and Applications, , 2024, 60 (12): 189-202.
[16] 汤静雯, 赖惠成, 王同官. 远距离情形下的改进YOLOv8行人检测算法[J]. 计算机工程, 2025, 51(4): 303-313.
TANG J W, LAI H C, WANG T G. Improved YOLOv8 pedestrian detection algorithm for long-distance person[J]. Computer Engineering, 2025, 51(4): 303-313.
[17] TANG J W, LAI H C, GAO G X, et al. PFEL-Net: a lightweight network to enhance feature for multi-scale pedestrian detection[J]. Journal of King Saud University-Computer and Information Sciences, 2024, 36(8): 102198.
[18] WANG H, LIU J, ZHAO J, et al. Precision and speed: LSOD-YOLO for lightweight small object detection[J]. Expert Systems With Applications, 2025, 269: 126440.
[19] 李峻宇, 刘乾坤, 付莹. 融合注意力机制的红外小目标检测[J]. 航空学报, 2024, 45(14): 90-101.
LI J Y, LIU Q K, FU Y. Infrared small target detection based on attention mechanism[J]. China Industrial Economics, 2024, 45(14): 90-101.
[20] 张浩晨, 张竹林, 史瑞岩, 等. YOLO-CDC: 优化改进YOLOv8的车辆目标检测算法[J]. 计算机工程与应用, 2025, 61(13): 124-137.
ZHANG H C, ZHANG Z L, SHI R Y, et al. YOLO-CDC: improved YOLOv8 multi-scale vehicle object detection alg-orithm[J]. Computer Engineering and Applications, 2025, 61(13): 124-137.
[21] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017: 6000-6010.
[22] CARION N, MASSA F, SYNNAEVE G, et al. End-to-end object detection with transformers[C]//Proceedings of the European Conference on Computer Vision. Cham: Springer International Publishing, 2020: 213-229.
[23] ZHU X Z, SU W J, LU L W, et al. Deformable DETR: deformable transformers for end-to-end object detection[J]. arXiv:2010.04159, 2020.
[24] LI F, ZHANG H, LIU S L, et al. DN-DETR: accelerate DETR training by introducing query DeNoising[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2022: 13609-13617.
[25] ZHAO Y A, LV W Y, XU S L, et al. DETRs beat YOLOs on real-time object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2024: 16965-16974.
[26] MUZAMMUL M, ALGARNI A, GHADI Y Y, et al. Enhan-cing UAV aerial image analysis: integrating advanced SAHI techniques with real-time detection models on the VisDrone dataset[J]. IEEE Access, 2024, 12: 21621-21633.
[27] AKYON F C, ONUR ALTINUC S, TEMIZEL A. Slicing aided hyper inference and fine-tuning for small object dete-ction[C]//Proceedings of the IEEE International Conference on Image Processing. Piscataway: IEEE, 2022: 966-970.
[28] 张储, 徐伟悦, 杨如雪, 等. 一种基于优化后的RT-DETR模型的红花目标检测方法和装置: 202410039910[P]. 2024-04-09.
ZHANG C, XU W Y, YANG R X, et al. A method and device for detecting red flower targets based on an optimized RT-DETR model: 202410039910[P]. 2024-04-09.
[29] 李亦涵, 张秀再, 沈涛. 一种改进RT-DETR算法的遥感图像目标检测方法及系统: 202410609716[P]. 2024-06-14.
LI Y H, ZHANG X Z, SHEN T. An improved RT-DETR algorithm for remote sensing image object detection method and system: 202410609716[P]. 2024-06-14.
[30] ZHANG X, SONG Y, SONG T, et al. AKConv: convolutional kernel with arbitrary sampled shapes and arbitrary number of parameters[J]. arXiv:2311.11587, 2023.
[31] 胡佳乐, 周敏, 申飞. 面向无人机小目标的RTDETR改进检测算法[J]. 计算机工程与应用, 2024, 60(20): 198-206.
HU J L, ZHOU M, SHEN F. Improved detection algorithm of RTDETR for UAV small target[J]. Computer Engineering and Applications, 2024, 60(20): 198-206.
[32] YUN S, RO Y. SHViT: single-head vision transformer with memory efficient macro design[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recogn-ition. Piscataway: IEEE, 2024: 5756-5767.
[33] WANG C Y, MARK LIAO H Y, WU Y H, et al. CSPNet: a new backbone that can enhance learning capability of CNN[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Piscataway: IEEE, 2020: 1571-1580.
[34] REZATOFIGHI H, TSOI N, GWAK J, et al. Generalized intersection over union: a metric and a loss for bounding box regression[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 658-666.
[35] ZHENG Z, WANG P, REN D, et al. Enhancing geometric factors in model learning and inference for object detection and instance segmentation[J]. IEEE Transactions on Cybernetics, 2022, 52(8): 8574-8586.
[36] ZHANG H, ZHANG S J. Focaler-IoU: more focused intersection over union loss[J]. arXiv:2401.01525, 2024.
[37] MA S, XU Y. MPDIoU: a loss for efficient and accurate bounding box regression[J]. arXiv:2307.07662, 2023.
[38] YU Z P, HUANG H B, CHEN W J, et al. YOLO-FaceV2: a scale and occlusion aware face detector[J]. Pattern Recogn-ition, 2024, 155: 110714.
[39] ZHU P F, DU D W, WEN L Y, et al. VisDrone-VID2019: the vision meets drone object detection in video challenge results[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision Workshop. Piscataway: IEEE, 2019: 227-235.
[40] XIA G S, BAI X, DING J, et al. DOTA: a large-scale dataset for object detection in aerial images[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018.
[41] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 2999-3007.
[42] LIU Z, LIN Y T, CAO Y, et al. Swin Transformer: hierarchical vision transformer using shifted windows[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 9992-10002.
[43] 尹泽宇, 杨波, 陈金令, 等. 基于STD-DETR的轻量化小目标检测算法[J]. 激光与光电子学进展, 2025, 62(8): 146-156.
YIN Z Y, YANG B, CHEN J L, et al. Lightweight small object detection algorithm based on STD-DETR[J]. Laser & Optoelectronics Progress, 2025, 62(8): 146-156.
[44] 向毅伟, 蒋瑜, 王琪凯, 等. 多尺度特征优化的实时Transformer在无人机航拍中的研究[J]. 计算机工程与应用, 2025, 61(9): 221-229.
XIANG Y W, JIANG Y, WANG K Q, et al. Research on real-time transformer for multi-scale feature optimization in drone aerial imaging[J]. Computer Engineering and Applications, 2025, 61(9): 221-229.
[45] 江旺玉, 王乐, 姚叶鹏, 等. 多尺度特征聚合扩散和边缘信息增强的小目标检测算法[J]. 计算机工程与应用, 2025, 61(7): 105-116.
JIANG W Y, WANG L, YAO Y P, et al. Small target detection algorithm based on multi-scale feature aggregation diffusion and edge information enhancement[J]. Computer Engineering and Applications, 2025, 61(7): 105-116.
[46] 潘玮, 韦超, 钱春雨, 等. 面向无人机视角下小目标检测的YOLOv8s改进模型[J]. 计算机工程与应用, 2024, 60(9): 142-150.
PAN W, WEI C, QIAN C Y, et al. Improved YOLOv8s model for small target detection from UAV perspective[J]. Computer Engineering and Applications, 2024, 60(9): 142-150.