跨尺度特征融合的无人机小目标检测算法

doi:10.3778/j.issn.1002-8331.2412-0332

摘要/Abstract

摘要： 针对目前无人机小目标检测任务中存在的多尺度、目标小、复杂背景干扰、易受遮挡等问题，提出一种复合特征融合与跨尺度优化的YOLOv11n改进模型，在骨干网络中提出MPCA(multiscale perceptual cascade attention）机制改进卷积模块，解决传统卷积特征表达能力不足的同时，在较低计算成本下显著提升网络的特征提取能力；提出全新的EMSFPN（efficient multi-scale FPN）结构改进颈部网络，使不同层级的特征得以相互融合。在改进颈部网络模型的基础上，增加具有丰富小目标语义信息的特征层；使用SBA（selective boundary aggregation）模块对多分辨率特征进行交互融合，提升模型的多尺度处理能力；引用Inner-IoU损失函数的思想改进Wise-IoU函数，用Inner-WIoU替代原损失函数，提升对小目标的定位精度，优化损失值计算。改进后YOLOv11n算法在VisDrone2019数据集上相对原始模型参数量减少9.8%，mAP50显著提升了9.1个百分点，性能超过YOLOv11s，在实现模型轻量化的同时，大幅度提升了性能。

关键词: YOLOv11n, 无人机（UAV）, 小目标检测, 多尺度特征融合, Inner-WIoU

Abstract: Aiming at the existing problems of multi-scale, small target, complex background interference and easy occlusion in UAV small target detection tasks, an improved YOLOv11n model based on composite feature fusion and cross-scale optimization is proposed. In the backbone network, a multiscale perceptual cascade attention (MPCA) mechanism is proposed to improve the convolutional module, which addresses the lack of traditional convolutional feature expression ability, and significantly improves the feature extraction ability of the network at a lower computing cost. A new efficient multi-scale FPN (EMSFPN) structure is proposed to improve the neck network, enabling mutual integration of features from different levels. On the basis of improving the neck network model, a feature layer with rich semantic information of small targets is added. The selective boundary aggregation (SBA) module is used for interactive fusion of multi-resolution features to improve the multi-scale processing capability of the model. The Inner-IoU loss function is introduced to enhance the Wise-IoU function by replacing the original loss function with Inner-WIoU, improving the positioning accuracy of small targets, and optimizing the calculation of loss value. The improved YOLOv11n algorithm has a 9.8% reduction in the number of parameters compared with the original model on the VisDrone2019 data set, and a significant 9.1 percentage points improvement in mAP50. The performance exceeds that of YOLOv11s, and the performance is greatly improved while the model is lightweight.

Key words: YOLOv11n, unmanned aerial vehicle (UAV), small target detection, multi-scale feature fusion, Inner-WIoU

罗显志, 汪航. 跨尺度特征融合的无人机小目标检测算法[J]. 计算机工程与应用, 2025, 61(14): 135-147.

LUO Xianzhi, WANG Hang. Small Target Detection Algorithm for UAV Based on Cross-Scale Feature Fusion[J]. Computer Engineering and Applications, 2025, 61(14): 135-147.

参考文献

[1] OSCO L P, MARCATO J J, MARQUES R A P, et al. A review on deep learning in UAV remote sensing[J]. International Journal of Applied Earth Observation and Geoinformation, 2021, 102: 102456.
[2] ZHU P, WEN L, DU D, et al. Detection and tracking meet drones challenge[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(11): 7380-7399.
[3] MARVASTI-ZADEH S M, CHENG L, GHANEI-YAKHDAN H, et al. Deep learning for visual tracking: a comprehensive survey[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(5): 3943-3968.
[4] DONG H C, LI Y, LIU R. A detection algorithm based on improved cascade R-CNN for UAV aerial images[C]//Proceedings of the IEEE 3rd International Conference on Electronic Technology, Communication and Information. Piscataway: IEEE, 2023: 700-704.
[5] BISIO I, HALEEM H, GARIBOTTO C, et al. Performance evaluation and analysis of drone-based vehicle detection techniques from deep learning perspective[J]. IEEE Internet of Things Journal, 2022, 9(13): 10920-10935.
[6] SAEED Z, YOUSAF M H, AHMED R, et al. On?board small-scale object detection for unmanned aerial vehicles (UAVs)[J]. Drones, 2023, 7(5): 310.
[7] HOSHINO W, SEO J, YAMAZAKI Y. A study for detecting disaster victims using multi-copter drone with a thermographic camera and image object recognition by SSD[C]//Proceedings of the IEEE/ASME International Conference on Advanced Intelligent Mechatronics. Piscataway: IEEE, 2021: 162-167.
[8] BETTI SORBELLI F, PALAZZETTI L, PINOTTI C M. YOLO-based detection of Halyomorpha Halys in orchards using RGB cameras and drones[J]. Computers and Electronics in Agriculture, 2023, 213: 108228.
[9] TERVEN J, CóRDOVA-ESPARZA D M, ROMERO-GONZáLEZ J A. A comprehensive review of YOLO architectures in computer vision: from YOLOv1 to YOLOv8 and YOLO-NAS[J]. Machine Learning and Knowledge Extraction, 2023, 5(4): 1680-1716.
[10] LI Y T, FAN Q S, HUANG H S, et al. A modified YOLOv8 detection network for UAV aerial image recognition[J]. Drones, 2023, 7(5): 304.
[11] XIONG X R, HE M T, LI T Y, et al. Adaptive feature fusion and improved attention mechanism-based small object detection for UAV target tracking[J]. IEEE Internet of Things Journal, 2024, 11(12): 21239-21249.
[12] 何湘杰, 宋晓宁. YOLOv4-Tiny的改进轻量级目标检测算法[J]. 计算机科学与探索, 2024, 18(1): 138-150.
HE X J, SONG X N. Improved YOLOv4-tiny lightweight target detection algorithm[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(1): 138-150.
[13] 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]. Acta Aeronautica ET Astronautica Sinica, 2024, 45(14): 90-101.
[14] 孙佳宇, 徐民俊, 张俊鹏, 等. 优化改进YOLOv8无人机视角下目标检测算法[J]. 计算机工程与应用, 2025, 61(1): 109-120.
SUN J Y, XU M J, ZHANG J P, et al. Optimized and improved YOLOv8 target detection algorithm from UAV perspective[J]. Computer Engineering and Applications, 2025, 61(1): 109-120.
[15] 梁秀满, 贾梓涵, 刘振东, 等. 改进YOLOv8n的无人机航拍图像检测算法[J]. 电光与控制, 2025, 32(1): 34-40.
LIANG X M, JIA Z H, LIU Z D, et al. Improved YOLOv8n drone aerial image detection algorithm[J]. Electro-Optical & Control, 2025, 32(1): 34-40.
[16] 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 object detection from perspective of drones[J]. Computer Engineering and Applications, 2024, 60(9): 142-150.
[17] 廖宁生, 曹天秀, 刘科言, 等. 复合特征与多尺度融合的无人机小目标检测算法[J]. 计算机工程与应用, 2025, 61(3): 111-120.
LIAO N S, CAO T X, LIU K Y, et al. Small target detection algorithm for UAV based on composite feature and multi-scale fusion[J]. Computer Engineering and Applications, 2025, 61(3): 111-120.
[18] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: optimal speed and accuracy of object detection[J]. arXiv:2004.10934, 2020.
[19] JIANG B R, LUO R X, MAO J Y, et al. Acquisition of localization confidence for accurate object detection[C]//Proceedings of the European Conference on Computer Vision. Cham: Springer International Publishing, 2018: 816-832.
[20] 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.
[21] PARK N, KIM S. How do vision transformers work?[J]. arXiv:2202.06709, 2022.
[22] DAI T, WANG J P, GUO H, et al. FreqFormer: frequency-aware transformer for lightweight image super-resolution[C]//Proceedings of the 33rd International Joint Conference on Artificial Intelligence, 2024: 731-739.
[23] 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.
[24] RAHMAN M M, MUNIR M, MARCULESCU R. EMCAD: efficient multi-scale convolutional attention decoding for medical image segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2024: 11769-11779.
[25] MARK S, ANDREW H, ZHU M L, et al. MobileNetV2: inverted residuals and linear bottlenecks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018: 4510-4520.
[26] CHEN J, MAI H S, LUO L B, et al. Effective feature fusion network in BIFPN for small object detection[C]//Proceedings of the IEEE International Conference on Image Processing. Piscataway: IEEE, 2021: 699-703.
[27] TANG F L, XU Z X, HUANG Q M, et al. DuAT: dual-aggregation transformer network for medical image segmentation[C]//Proceedings of the Pattern Recognition and Computer Vision. Singapore: Springer Nature Singapore, 2024: 343-356.
[28] FAN D P, JI G P, ZHOU T, et al. PraNet: parallel reverse attention network for polyp segmentation[J]. arXiv:2006. 11392, 2020.
[29] ZHENG Z H, WANG P, LIU W, et al. Distance-IoU loss: faster and better learning for bounding box regression[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020: 12993-13000.
[30] 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.
[31] ZHANG Y F, REN W Q, ZHANG Z, et al. Focal and efficient IoU loss for accurate bounding box regression[J]. Neurocomputing, 2022, 506: 146-157.
[32] ZHANG H, XU C, ZHANG S J. Inner-IoU: more effective intersection over union loss with auxiliary bounding box[J]. arXiv:2311.02877, 2023.
[33] TONG Z J, CHEN Y H, XU Z W, et al. Wise-IoU: bounding box regression loss with dynamic focusing mechanism[J]. arXiv:2301.10051, 2023.
[34] 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.
[35] 张智, 易华挥, 郑锦. 聚焦小目标的航拍图像目标检测算法[J]. 电子学报, 2023, 51(4): 944-955.
ZHANG Z, YI H H, ZHENG J. Focusing on small objects detector in aerial images[J]. Acta Electonica Sinica, 2023, 51(4): 944-955.
[36] FARAJI H, CHEN B C. Drone-YOLO: improved YOLO for small object detection in UAV[C]//Proceedings of the 8th International Conference on Image, Vision and Computing. Piscataway: IEEE, 2023: 93-100.
[37] 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: 3974-3983.