基于仿真数据迁移学习的固定翼无人机检测

doi:10.16182/j.issn1004731x.joss.22-0024

系统仿真学报 ›› 2023, Vol. 35 ›› Issue (5): 998-1007.doi: 10.16182/j.issn1004731x.joss.22-0024

基于仿真数据迁移学习的固定翼无人机检测

付玉¹^,²(), 张垚¹^,²(), 赵萌¹^,², 王绵沼¹^,², 郑江鹏¹^,², 贾晨¹^,², 陈胜勇¹^,²

^1.学习型智能系统教育部工程研究中心，天津 300384
^2.天津理工大学计算机科学与工程学院，天津 300384

收稿日期:2022-01-11 修回日期:2022-02-22 出版日期:2023-05-30 发布日期:2023-05-22
通讯作者: 张垚 E-mail:fuyucv@stud.tjut.edu.cn;zytju221@tju.edu.cn
第一作者简介:付玉(1998-)，女，硕士，研究方向为计算机视觉。E-mail：fuyucv@stud.tjut.edu.cn
基金资助:
国家自然科学基金(61906133)

Fixed-Wing UAV Detection Based on Simulated Data Transfer Learning

Yu Fu¹^,²(), Yao Zhang¹^,²(), Meng Zhao¹^,², Mianzhao Wang¹^,², Jiangpeng Zheng¹^,², Chen Jia¹^,², Shengyong Chen¹^,²

^1.Engineering Research Center of Learning-Based Intelligent System, Ministry of Education, Tianjin 300384, China
^2.School of Computer Science and Engineering, Tianjin University of Technology, Tianjin 300384, China

Received:2022-01-11 Revised:2022-02-22 Online:2023-05-30 Published:2023-05-22
Contact: Yao Zhang E-mail:fuyucv@stud.tjut.edu.cn;zytju221@tju.edu.cn

摘要/Abstract

摘要：

数据在视觉检测任务中发挥重要作用，针对足够数量的真实固定翼无人机数据难以获取的问题，构建了一个包含大量仿真和少量真实的固定翼无人机数据集，采用权重迁移的思想，通过对仿真固定翼无人机数据的训练达到对真实固定翼无人机数据的检测。在此基础上又提出一个两阶段学习策略，利用多尺度特征融合进一步降低无人机的漏检率。仿真实验结果表明，利用仿真数据检测真实固定翼无人机在未来目标检测研究中有潜在应用前景。

关键词: 视觉检测, 固定翼无人机, 权重迁移, 多尺度特征

Abstract:

Data play an important role in visual inspection tasks, but it is difficult to obtain a sufficient amount of real fixed-wing UAV data. Therefore, a data set containing a large number of simulated fixed-wing UAV data and a small number of real fixed-wing UAV data is constructed, and the real fixed-wing UAV data are detected by training simulated fixed-wing UAV data based on the idea of weight transfer. On this basis, a two-stage learning strategy is proposed to further reduce the missed detection rate of UAVs by using multi-scale feature fusion.The simulation results show that simulated data can be used to detect real fixed-wing UAVs, which has potential application prospects in future target detection research.

Key words: visual inspection, fixed-wing UAV, weight transfer, multi-scale feature

中图分类号:

TP391.9

付玉,张垚,赵萌等 . 基于仿真数据迁移学习的固定翼无人机检测[J]. 系统仿真学报, 2023, 35(5): 998-1007.

Yu Fu,Yao Zhang,Meng Zhao,et al . Fixed-Wing UAV Detection Based on Simulated Data Transfer Learning[J]. Journal of System Simulation, 2023, 35(5): 998-1007.

图/表 9

图1

图2

图3

图4

表1

表2

图5

图6

图7

参考文献 39

1	刘丹, 王运宏. 限制型自适应SUSAN边缘检测算法[J]. 计算机辅助设计与图形学学报, 2020, 32(6): 971-978.
	Liu Dan, Wang Yunhong. Constraint Self-Adaptive SUSAN Algorithm for Edge Detection[J]. Journal of Computer-Aided Design and Computer Graphics, 2020, 32(6): 971-978.
2	何炜婷, 曾碧, 陈文轩. 基于轻量级人体姿态估计和图卷积的摔倒实时检测方法[J]. 计算机科学与应用, 2021, 11(4): 783-794.
	He Weiting, Zeng Bi, Chen Wenxuan. Real-Time Fall Detection Based on Light-Weight Human Pose Estimation and Graph Convolution Network[J]. Computer Science and Applications, 2021, 11(4): 783-794.
3	陈淼妙, 续晋华. 基于高分辨率卷积神经网络的场景文本检测模型[J]. 计算机应用与软件, 2020, 37(10): 138-144.
	Chen Miaomiao, Xu Jinhua. Scene Text Detection Model Based on High Resolution Convolutional Neural Networks[J]. Computer Applications and Software, 2020, 37(10): 138-144.
4	邓珍荣, 白善今, 马富欣, 等. 改进YOLO的密集小尺度人脸检测方法[J]. 计算机工程与设计, 2020, 41(3): 874-879.
	Deng Zhenrong, Bai Shanjin, Ma Fuxin, et al. Improved YOLO Dense Small-Scale Face Detection Method [J]. Computer Engineering and Design, 2020, 41(3): 874-879.
5	陈勇, 谢文阳, 刘焕淋, 等. 结合头部和整体信息的多特征融合行人检测[J]. 电子与信息学报, 2022, 44(4): 1453-1460.
	Chen Yong, Xie Wenyang, Liu Huanlin, et al. Multi-feature Fusion Pedestrian Detection Combining Head and Overall Information[J]. Journal of Electronics and Information Technology, 2021, 44(4): 1453-1460.
6	骆子铭, 许书彬, 王杰勋. 一种基于机器学习的TLS恶意流量检测方案[J]. 网络空间安全, 2019, 10(7): 89-94.
	Luo Ziming, Xu Shubin, Wang Jiexun. A Scheme for Identifying Malware Traffic with TLS Data Based on Machine Learning[J]. Cyberspace Security, 2019, 10(7): 89-94.
7	宋羿铭, 解文彬, 周未. 基于机器学习的军事目标检测系统开发研究[J]. 现代计算机, 2020(22): 54-58.
	Song Yiming, Xie Wenbin, Zhou Wei. Development and Research of Military Target Detection System Based on Machine Learning[J]. Modern Computer, 2020(22): 54-58.
8	张富凯, 杨峰, 李策. 基于改进YOLOv3的快速车辆检测方法[J]. 计算机工程与应用, 2019, 55(2): 12-20.
	Zhang Fukai, Yang Feng, Li Ce. Fast Vehicle Detection Method Based on Improved YOLOv3[J]. Computer Engineering and Applications, 2019, 55(2): 12-20.
9	席孝倩, 刘威. 基于目标检测算法的肺结节辅助诊断系统[J]. 计算机与现代化, 2020(11): 1-7.
	Xi Xiaoqian, Liu Wei. Pulmonary Nodule Aided Diagnosis System Based on Target Detection Algorithm[J].Computer and Modernization, 2020(11): 1-7.
10	Cheng X, Shi F, Liu X, et al. A Novel Deep Class-Imbalanced Semisupervised Model for Wind Turbine Blade Icing Detection[J]. IEEE Transactions on Neural Networks and Learning Systems (S2162-237X), 2022, 33(6): 2258-2570.
11	Ahuja S, Panigrahi B K, Dey N, et al. Deep Transfer Learning-Based Automated Detection of COVID-19 from Lung CT Scan Slices[J]. Applied Intelligence (S0924-669X), 2021, 51(1): 571-585.
12	Cheng X, Li G, Han P, et al. Data-Driven Modeling for Transferable Sea State Estimation Between Marine Systems[J]. IEEE Transactions on Intelligent Transportation Systems (S1524-9050), 2022, 23(3):2561-2571.
13	Behera S K, Rath A K, Sethy P K. Maturity Status Classification of Papaya Fruits Based on Machine Learning and Transfer Learning Approach[J]. Information Processing in Agriculture (S2214-3173), 2021, 8(2): 244-250.
14	Felzenszwalb P F, Girshick R B, McAllester D, et al. Object Detection with Discriminatively Trained Part-Based Models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (S0162-8828), 2009, 32(9): 1627-1645.
15	He K, Zhang X, Ren S, et al. Deep Residual Learning for Image Recognition[C]// IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA: IEEE, 2016: 770-778.
16	Szegedy C, Liu W, Jia Y, et al. Going Deeper with Convolutions[C]// IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA, USA: IEEE, 2015: 1-9.
17	Krizhevsky A, Sutskever I, Hinton G E. Imagenet Classification with Deep Convolutional Neural Networks[J]. Advances in Neural Information Processing Systems (S1049-5258), 2012, 25: 1097-1105.
18	Ren S, He K, Girshick R, et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks[J]. Advances in Neural Information Processing Systems (S1049-5258), 2015, 28: 91-99.
19	Girshick R. Fast R-CNN[C]// IEEE International Conference on Computer Vision. Santiago, Chile: IEEE, 2015: 1440-1448.
20	Bochkovskiy A, Wang C Y, Liao H Y M. YOLOv4: Optimal Speed and Accuracy of Object Detection[J]. arXiv preprint, arXiv: , 2020.
21	Wang C Y, Liao H Y M, Wu Y H, et al. CSPNet: A New Backbone that can Enhance Learning Capability of CNN[C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Seattle, WA, USA: IEEE, 2020: 390-391.
22	Lin T Y, Dollár P, Girshick R, et al. Feature Pyramid Networks for Object Detection[C]// IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE, 2017: 2117-2125.
23	Liu S, Qi L, Qin H, et al. Path Aggregation Network for Instance Segmentation[C]// IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, Utah, USA: IEEE, 2018: 8759-8768.
24	Rezatofighi H, Tsoi N, Gwak J Y, et al. Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression[C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition. Savarese, Silvio. Long Beach, CA, USA: IEEE, 2019: 658-666.
25	宋闯, 赵佳佳, 王康, 等. 面向智能感知的小样本学习研究综述[J]. 航空学报, 2020, 41(增1): 15-28.
	Song Chuang, Zhao Jiajia, Wang Kang, et al. A Survey of Few Shot Learning Based on Intelligent Perception[J]. Acta Aeronautica et Astronautica Sinica, 2020, 41(S1): 15-28.
26	Dai J, Qi H, Xiong Y, et al. Deformable Convolutional Networks[C]// IEEE International Conference on Computer Vision. Washington, USA: IEEE, 2017: 764-773.
27	Zhang P, Zhong Y, Li X. SlimYOLOv3: Narrower, Faster and Better for Real-Time UAV Applications[C]// IEEE/CVF International Conference on Computer Vision Workshops. Seoul, Korea: IEEE, 2019: 37-45.
28	Redmon J, Farhadi A. YOLOv3: An Incremental Improvement[J]. arXiv preprint, arXiv: , 2018.
29	饶威. 基于深度学习的无人机地面小目标算法研究[D]. 沈阳: 沈阳理工大学, 2020.
	Rao Wei. Research on UAV Ground Small Target Algorithm Based on Deep Learning[D]. Shenyang: Shenyang Ligong University, 2020.
30	Zhao Q, Sheng T, Wang Y, et al. M2Det: A Single-Shot Object Detector Based on Multi-Level Feature Pyramid Network[J]. Proceedings of the AAAI Conference on Artificial Intelligence (S2159-5399), 2019, 33: 9259-9266.
31	He K, Zhang X, Ren S, et al. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (S0162-8828), 2015, 37(9): 1904-1916.
32	Simonyan K, Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition[J]. arXiv preprint, arXiv: , 2014.
33	He K, Zhang X, Ren S, et al. Deep Residual Learning for Image Recognition[C]// IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA: IEEE, 2016: 770-778.
34	Bodla N, Singh B, Chellappa R, et al. Soft-NMS--Improving Object Detection with One Line of Code[C]// IEEE International Conference on Computer Vision. Venice, Italy: IEEE, 2017: 5561-5569.
35	Chen Q, Wang Y, Yang T, et al. You Only Look One-level Feature[C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville, USA: IEEE, 2021: 13039-13048.
36	Wong A, Famuori M, Shafiee M J, et al. YOLO Nano: A Highly Compact You Only Look Once Convolutional Neural Network for Object Detection[J]. arXiv preprint, arXiv: , 2019.
37	Long X, Deng K, Wang G, et al. PP-YOLO: An Effective and Efficient Implementation of Object Detector[J]. arXiv preprint, arXiv: , 2020.
38	Carion N, Massa F, Synnaeve G, et al. End-to-End Object Detection with Transformers[C]// 16th European Conference on Computer Vision. Glasgow, UK: Springer, Cham, 2020: 213-229.
39	Ge Z, Liu S, Wang F, et al. YOLOX: Exceeding YOLO Series in 2021[J]. arXiv preprint, arXiv:, 2021.

方法	Precision/%	Recall/%	mAP/%	MR/%	FPS
YOLOF^[35]	100	53.75	77.50	46.25	20.30
YOLO Nano^[36]	40.18	56.25	9.12	43.75	30.08
PP-YOLO^[37]	95.77	85.00	78.20	15.00	72.90
DETR^[38]	98.41	77.5	45.60	22.50	0.52
YOLOX^[39]	92.31	90.00	85.90	10.00	22.98
本文方法	94.05	98.75	91.67	1.25	25.72

方法	Precision/%	Recall/%	mAP/%	MR/%	FPS
YOLOv5	90.67	85.00	72.30	15.00	80.65
M2Det^[30]	74.47	87.50	70.20	12.50	4.65
本文方法	94.05	98.75	91.67	1.25	25.72

[1]	李明煜, 林家泉. 基于YOLOv8-DF的轻量化驾驶员面部目标检测算法[J]. 系统仿真学报, 2025, 37(8): 2103-2114.
[2]	杨路, 裴俊莹. 融合多尺度特征的航拍目标检测算法[J]. 系统仿真学报, 2025, 37(6): 1486-1498.
[3]	周华平, 吴涛, 孙克雷. 面向遮挡行人检测的自适应多尺度特征金字塔网络[J]. 系统仿真学报, 2025, 37(5): 1222-1233.
[4]	张稀柳, 张晓玲, 何敏军. 基于改进YOLOX-s的车辆检测方法研究[J]. 系统仿真学报, 2024, 36(2): 487-496.
[5]	伍云鹏, 付应雄, 沈丽君, 崔峰. 基于YOLOX-Tiny的长尾分布交通标志识别模型[J]. 系统仿真学报, 2024, 36(11): 2503-2516.
[6]	于豪, 蒋锦霞, 赖晓翰, 梅峰, 王庆. 基于自适应感受野的电力设备表面缺陷检测方法[J]. 系统仿真学报, 2023, 35(7): 1572-1580.
[7]	许仁杰, 张小明, 王晨, 吴鹏. 基于跨模块注意力的3D目标检测方法研究[J]. 系统仿真学报, 2023, 35(12): 2680-2691.

基于仿真数据迁移学习的固定翼无人机检测

Fixed-Wing UAV Detection Based on Simulated Data Transfer Learning

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 39

相关文章 7

编辑推荐

Metrics

本文评价