Using KCF and Face Recognition for Outdoor Target Tracking UAV

被引:2
|
作者
Chen, Lu [1 ]
Shao, Yanhua [1 ]
Mei, Yanying [1 ]
Chu, Hongyu [1 ]
Chang, Zhiyuan [1 ]
Zhan, Huayi [2 ]
Rao, Yunbo [3 ]
Yang, Gui [4 ]
机构
[1] Southwest Univ Sci & Technol, Sch Informat Engn, Mianyang 621010, Sichuan, Peoples R China
[2] Northwestern Univ, Elect Engn & Comp Sci, Evanston, IL 60208 USA
[3] Univ Elect Sci & Technol China, Sch Informat & Software Engn, Chengdu 610054, Sichuan, Peoples R China
[4] Univ Elect Sci & Technol China, Control Sci & Engn, Chengdu 611731, Sichuan, Peoples R China
来源
TENTH INTERNATIONAL CONFERENCE ON GRAPHICS AND IMAGE PROCESSING (ICGIP 2018) | 2019年 / 11069卷
基金
中国国家自然科学基金;
关键词
UAV; Face recognition; Target tracking; KCF;
D O I
10.1117/12.2524401
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
Outdoor target tracking UAV (Unmanned Aerial Vehicle), which is a research hotspot in the field of computer vision and unmanned aerial system, needs robust target-tracking algorithms with good real-time performance, accurate position estimator of UAV and the corresponding control strategy of the system. In this paper, we designed an outdoor drone tracking system using PCA (Principal Component Analysis) face recognition algorithm and KCF (Kernel Correlation Filter) target tracking algorithm. Firstly, an image acquisition unit is constructed by using an on-board pan-and-tilt camera to capture an outdoor monitored area. Secondly, the PCA algorithm is used for face matching, then the tracking mode is automatically transferred when the expected face target is recognized. Finally, the target tracking is performed by the KCF algorithm. After that, the position error is calculated and sent to the flight control system through the MavLink protocol, thereby performing posture adjustment and completing the tracking and monitoring task. Experimental results show that the performance of outdoor target tracking flight robot is stable and reliable, which meets the requirements of outdoor target tracking and has a good application prospect.
引用
收藏
页数:6
相关论文
empty
未找到相关数据