一种基于SiamRPN的无人机目标跟踪及控制算法

doi:10.16182/j.issn1004731x.joss.22-0142

系统仿真学报 ›› 2023, Vol. 35 ›› Issue (6): 1372-1380.doi: 10.16182/j.issn1004731x.joss.22-0142

一种基于SiamRPN的无人机目标跟踪及控制算法

焦嵩鸣(), 丁辉(), 钟宇飞, 姚鑫, 郑家豪

华北电力大学自动化系，河北保定 071003

收稿日期:2022-02-28 修回日期:2022-04-11 出版日期:2023-06-29 发布日期:2023-06-20
通讯作者: 丁辉 E-mail:jiaosongming@ncepu.edu.cn;1413427850@qq.com
作者简介:焦嵩鸣(1972-)，男，副教授，博士，研究方向为机器人智能感知及电力机器人自主巡检。E-mail：jiaosongming@ncepu.edu.cn

A UAV Target Tracking and Control Algorithm Based on SiamRPN

Songming Jiao(), Hui Ding(), Yufei Zhong, Xin Yao, Jiahao Zheng

Department of Automation, North China Electric Power University, Baoding 071003, China

Received:2022-02-28 Revised:2022-04-11 Online:2023-06-29 Published:2023-06-20
Contact: Hui Ding E-mail:jiaosongming@ncepu.edu.cn;1413427850@qq.com

摘要/Abstract

摘要：

针对旋翼无人机自主跟踪陆地移动目标的需求，构建了一种能够适应尺度变化、遮挡、姿态变化等干扰环境下的无人机自主稳定跟踪与控制系统。通过基于深度学习的孪生网络提取目标在机载摄像头的成像位置，获取目标的相对位姿；设计图像处理算法对跟踪框内的图标进行处理，得到无人机相对于跟踪目标的偏航角，引入卡尔曼滤波对上述位姿信息进行处理，实现与移动目标轨迹几乎重合的跟踪控制。该算法基于Gazebo仿真平台实现，能够在干扰因素条件下对移动目标进行长时稳定的跟踪。

关键词: 孪生网络, 卡尔曼滤波, 目标跟踪, 轨迹跟踪, 图像处理

Abstract:

Aiming at the requirement of autonomously tracking land moving targets of rotary-wing UAVs, an autonomous and stable UAV tracking and control system that can adapt to the common interference environments such as scale changes, occlusions, and attitude changes is constructed. The system extracts the imaging position of the target in airborne camera through the twin network based on deep learning, and obtains the relative pose of the target. The image processing algorithm is designed to process the icons in the tracking frame, and the yaw angle of UAV relative to the tracking target is obtained, Kalman filter is introduced to process the above pose information, and finally the tracking control nearly coinciding with the trajectory of the moving target is realized. The algorithm is based on Gazebo simulation platform and can track the moving target stably for a long time under interference condition.

Key words: siamese network, Kalman filtering, target tracking, trajectory tracking, image processing

中图分类号:

V279

焦嵩鸣, 丁辉, 钟宇飞, 姚鑫, 郑家豪. 一种基于SiamRPN的无人机目标跟踪及控制算法[J]. 系统仿真学报, 2023, 35(6): 1372-1380.

Songming Jiao, Hui Ding, Yufei Zhong, Xin Yao, Jiahao Zheng. A UAV Target Tracking and Control Algorithm Based on SiamRPN[J]. Journal of System Simulation, 2023, 35(6): 1372-1380.

图/表 9

图1

图2

图3

图4

图5

图6

图7

图8

图9

参考文献 19

1	邢金昊. 基于无人机平台的地面目标追踪算法研究[D]. 济南: 山东大学, 2021.
	Xing Jinhao. Research on Ground Target Tracking Algorithm Based on UAV Platform[D]. Jiʹnan: Shandong University, 2021.
2	李靖, 马晓东, 陈怀民, 等. 无人机视觉导航着陆地标实时检测跟踪方法[J]. 西北工业大学学报, 2018, 36(2): 294-301.
	Li Jing, Ma Xiaodong, Chen Huaimin, et al. Real Time Detection and Tracking Method of UAV Visual Navigation Landmark[J] Journal of Northwest University of technology, 2018, 36(2): 294-301.
3	叱干鹏飞, 宁纪锋, 石武祯. 基于全局搜索的实时分布场目标跟踪方法[J]. 计算机应用研究, 2014, 31(10): 3169-3172, 3176.
	Pengfei Chigan, Ning Jifeng, Shi Wuzhen. Real Time Distributed Field Target Tracking Method Based on Global Search[J] Computer Application Research, 2014, 31(10): 3169-3172, 3176.
4	Zhao Zhiqiang, Feng Ping, Guo Jingjuan, et al. A Hybrid Tracking Framework Based on Kernel Correlation Filtering and Particle Filtering[J]. Neurocomputing, 2018, 297: 40-49.
5	Wang Xin, Hou Zhiqiang, Yu Wangsheng, et al. Robust Occlusion-aware Part-based Visual Tracking with Object Scale Adaptation[J]. Pattern Recognition, 2018, 81: 456-470.
6	Milan A, Rezatofighi S H, Dick A, et al. Online Multi-target Tracking Using Recurrent Neural Networks[C]//Thirty-first AAAI Conference on Artificial Intelligence. San Francisco California, USA: AAAI, 2017: 4225-4232.
7	Sadeghian A, Alahi A, Savarese S. Tracking the Untrackable: Learning to Track Multiple Cues with Long-term Dependencies[C]//2017 IEEE International Conference on Computer Vision(ICCV). Venice, Italy: IEEE, 2017: 300-311.
8	Valmadre J, Bertinetto L, Henriques J F, et al. End-to-end Representation Learning for Correlation Filter Based Tracking[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Honolulu, HI, USA: IEEE, 2017: 2805-2813.
9	Wang Qiang, Gao Jin, Xing Junliang, et al. Discriminant Correlation Filters Network for Visual Tracking[J/OL]. [2022-01-23]. .
10	Bertinetto L, Valmadre J, Henriques J F, et al. Fully-convolutional Siamese Networks for Object Tracking[C]//European conference on computer vision. Cham, Switzerland: Springer, 2016: 850-865.
11	程相博,李建胜,胡鹏, 等. 改进的GOTUＲN算法[J]. 测绘科学技术学报, 2018, 35(6): 605-608, 615.
	Cheng Xiangbo, Li Jiansheng, Hu Peng, et al. An Improved Algorithm of the Generic Object Tracking Using Regression Networks[J]. Journal of Geomatics Science and Technology, 2018, 35(6): 605-615.
12	Li Bo, Yan Junjie, Wu Wei, et al. High Performance Visual Tracking with Siamese Region Proposal Network[C]//IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA: IEEE, 2018: 8971-8980.
13	Li Bo, Wu Wei, Wang Qiang, et al. Siamrpn++: Evolution of Siamese Visual Tracking with very Deep Networks[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA, USA: IEEE, 2019: 4282-4291.
14	Danelljan M, Bhat G, Khan F S, et al. Atom: Accurate Tracking by Overlap Maximization[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA, USA: IEEE, 2019: 4660-4669.
15	Bhat G, Danelljan M, Gool L V, et al. Learning Discriminative Model Prediction for Tracking[C]//IEEE/CVF International Conference on Computer Vision. Seoul, Korea(South): IEEE, 2019: 6182-6191.
16	陈琳, 刘允刚. 面向无人机的视觉目标跟踪算法: 综述与展望[J]. 信息与控制, 2022, 51(1): 23-40.
	Chen Lin, Liu Yungang. Visual Target Tracking Algorithm for UAV: Overview and Prospect[J]. Information and Control, 2022, 51(1): 23-40.
17	张宏伟, 李晓霞, 朱斌, 等. 基于孪生神经网络的两阶段目标跟踪方法[J]. 红外与激光工程, 2021, 50(9): 341-352.
	Zhang Hongwei, Li Xiaoxia, Zhu Bin, et al. Stage Target Tracking Method Based on Twin Neural Network[J]. Infrared and Laser Engineering, 2021, 50(9): 341-352.
18	夏候凯顺, 陈善星, 邬依林. 基于双目云台相机的目标跟踪系统建模与仿真[J]. 系统仿真学报, 2015, 27(2): 362-368.
	Xiahou Kaishun, Chen Shanxing, Wu Yilin. Modeling and Simulation of Target Tracking System Based on Binocular Gimbal Camera[J]. Journal of System Simulation, 2015, 27(2): 362-368.
19	卢燕梅, 宗群, 张秀云, 等. 集群无人机队形重构及虚拟仿真验证[J]. 航空学报, 2020, 41(4): 248-259.
	Lu Yanmei, Zong Qun, Zhang Xiuyun, et al. Formation Reconstruction and Virtual Simulation Verification of Cluster UAV[J]. Journal of Aeronautics and Astronautics, 2020, 41(4): 248-259.

[1]	刘兴华, 董思文, 田佳强. 基于卡尔曼滤波分解的配电网安全状态估计[J]. 系统仿真学报, 2023, 35(6): 1191-1202.
[2]	刘东阳, 查文文, 陶亮, 朱诚, 辜丽川, 焦俊. 基于LSTM和SMC的农用履带机器人轨迹跟踪控制[J]. 系统仿真学报, 2023, 35(4): 747-759.
[3]	张思贤, 杨艺, 张猛, 米鹏博. 高效的多特征自适应相关滤波跟踪器[J]. 系统仿真学报, 2022, 34(8): 1864-1873.
[4]	杜宝林, 朱大昌, 盘意华. 机械臂模糊超螺旋二阶滑模轨迹跟踪控制[J]. 系统仿真学报, 2022, 34(6): 1343-1352.
[5]	王志伟, 胡继宗, 王风杰, 黄杰. 基于非线性观测器的导航过程仿真研究[J]. 系统仿真学报, 2022, 34(5): 1127-1139.
[6]	袁彬淦, 钟铭恩, 倪晶鑫. 线束端子压接后外观缺陷的视觉检测算法研究[J]. 系统仿真学报, 2022, 34(5): 1152-1159.
[7]	吴定会, 张桐瑞, 张秀丽. 扰动累积下基于数字孪生的车间重调度[J]. 系统仿真学报, 2022, 34(3): 573-583.
[8]	江达, 蔡志勤, 刘忠振, 彭海军, 吴志刚. 基于强化学习的连续型机械臂自适应跟踪控制[J]. 系统仿真学报, 2022, 34(10): 2264-2271.
[9]	路宏广, 赵树恩. 基于鲁棒模型预测的智能汽车轨迹跟踪控制研究[J]. 系统仿真学报, 2022, 34(1): 153-162.
[10]	周维, 刘宇翔, 廖广平, 马鑫. 结合交并比损失的孪生网络目标跟踪算法研究[J]. 系统仿真学报, 2022, 34(09): 1956-1967.
[11]	王启明, 蒋江月, 吕志超, 张汉祖. 基于改进MPC的协同自适应巡航控制策略研究[J]. 系统仿真学报, 2022, 34(09): 2087-2097.
[12]	张瑞民, 陈巧玉. 基于光滑二阶滑模的机械臂轨迹跟踪控制[J]. 系统仿真学报, 2021, 33(6): 1315-1322.
[13]	李琪, 墨瀚林, 王向东, 李华. 短道速滑场景下的多目标跟踪与运动仿真[J]. 系统仿真学报, 2021, 33(5): 1039-1050.
[14]	冷姚, 赵树恩. 智能车辆横向轨迹跟踪的显式模型预测控制方法[J]. 系统仿真学报, 2021, 33(5): 1177-1187.
[15]	马立新, 朱勇杰, 季乐延. 神经网络优化的无感永磁同步电机控制系统[J]. 系统仿真学报, 2021, 33(3): 622-630.

一种基于SiamRPN的无人机目标跟踪及控制算法

A UAV Target Tracking and Control Algorithm Based on SiamRPN

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 19

相关文章 15

编辑推荐

Metrics

本文评价