无人机目标实时自适应跟踪系统

doi:10.3778/j.issn.1002-8331.2011-0343

摘要/Abstract

摘要： 随着无人机（unmanned aerial vehicle，UAV）在航拍、空中侦察等相关领域被广泛应用，对于无人机的智能化需求逐渐提高。目标跟踪具有信息量大、实时性高等优点，能够为无人机的智能飞行提供大量且实时的外部信息。进行低开销、低功耗的无人机目标跟踪系统的研究，对无人机智能化进程的加速具有深远意义。为更好解决跟踪过程中出现的对背景复杂、光照变化、目标较小、移动速度快等情景的目标跟踪准确度和实时性等问题，提出一种基于FPGA的自适应跟踪算法。将视频RGB数据流进行灰度转换；将模板数据和搜索区域的像素灰度值保存于片内RAM，搜索区域内遍历寻找与模板相似度最高的区域；当背景或光线发生变化，采用更新模板的方式，进一步提高跟踪准确度。仿真结果显示所提跟踪算法具有较好的实时性，跟踪重叠率在95%以上，跟踪速率在50?frame/s以上，有较好的跟踪准确度和实时性。

关键词: 现场可编程门阵列（FPGA）, 目标跟踪, 自适应, 图像储存, 图像处理

Abstract: As unmanned aerial vehicle（UAV） is widely used in aerial photography, aerial reconnaissance and other related fields, the demand for intelligence of UAV gradually increases. Target tracking has the advantages of large amount of information and high real-time performance, which can provide a lot of real-time external information for the intelligent flight of UAV. The research of UAV target tracking system with low cost and power consumption has far-reaching significance for the acceleration of UAV intelligent process. In order to better solve the problems of target tracking accuracy and real-time performance in the process of tracking such situations as complex background, light change, small target and fast moving speed, this paper proposes an adaptive tracking algorithm based on FPGA. Firstly, the video RGB data stream is converted into gray scale. Secondly, the template data and the pixel gray value of the search area are saved in RAM, and the region with the highest similarity to the template is traversed within the search area. Finally, when the background or light changes, the template is updated to further track the target accurately. Simulation results show that the proposed tracking algorithm has good real-time performance, with tracking overlap rate above 95% and tracking rate above 50 frame/s, with good tracking accuracy and real-time performance.

Key words: field programmable gate array（FPGA）, target tracking, self-adaptive, image storage, image processing

严飞, 马可, 刘佳, 刘银萍, 夏金锋. 无人机目标实时自适应跟踪系统[J]. 计算机工程与应用, 2022, 58(10): 178-184.

YAN Fei, MA Ke, LIU Jia, LIU Yinping, XIA Jinfeng. UAV Target Real-Time Adaptive Tracking System[J]. Computer Engineering and Applications, 2022, 58(10): 178-184.

参考文献

[1] 单明媚，王华通，郑浩岚，等.视频运动目标跟踪算法研究综述[J].物联网技术，2019，9（7）：76-78.
SHAN M M，WANG H T，ZHENG H L，et al.Research overview of video motion target tracking algorithm[J].Internet of Things Technology，2019，9（7）：76-78.
[2] ZHU D L，ZHAO B B，WANG S Y.Mobile target indoor tracking based on multi-direction weight position Kalman filter[J].Computer Networks，2018（4）：115-127.
[3] DU D，QI H，WEN L，et al.Geometric hypergraph learning for visual tracking[J].IEEE Transactions on Cybernetics，2017，47（12）：4182-4195.
[4] ZHANG S P，ZHOU H Y，YAO H X.Adaptive NormalHedge for robust visual tracking[J].Signal Processing，2015，110：132-142.
[5] 翟敬梅，刘坤.特征点辅助的时空上下文目标跟踪与定位[J].仪器仪表学报，2017，38（11）：2839-2848.
ZHAI J M，LIU K.Spatio-temporal context target tracking and location aided by feature points[J].Chinese Journal of Scientific Instrument，2017，38（11）：2839-2848.
[6] FUKUNAGA K，HOSTETLER L.The estimation of the gradient of a density function，with applications in pattern recognition[J].IEEE Transactions on Information Theory，1975，21（1）：32-40.
[7] 董蓉，李勃，陈启美.基于SIFT特征的目标多自由度Mean-Shift跟踪算法[J].控制与决策，2012，27（3）：399-402.
DONG R，LI B，CHEN Q M.Multi-degree-of-freedom Mean-Shift tracking algorithm based on SIFT feature[J].Control and Decision，2012，27（3）：399-402.
[8] WANG J，WANG Y H.Multi-period visual tracking via online DeepBoost learning[J].Neurocomputing，2016，200：55-69.
[9] CHEN J，LI J H，YANG S H，et al.Weighted optimization-based distributed Kalman filter for nonlinear target tracking in collaborative sensor networks[J].IEEE Transactions on Cybernetics，2017，47（11）：3892-3905.
[10] ZHANG H B，LIU J J，PANG A C.A Bayesian network model for data losses and faults in medical body sensor networks[J].Computer Networks，2018，143：166-175.
[11] OZATAY E，OZGUNER U，FILEV D，et al.Bayesian traffic light parameter tracking based on semi-hidden Markov models[J].IEEE Transactions on Intelligent Transportation Systems，2016，17（11）：2998-3008.
[12] JIANG L，SINGH S，YILDIRIM S.Bayesian tracking and parameter learning for non-linear multiple target tracking models[J].IEEE Transactions on Signal Processing，2015，63（21）：5733-5745.
[13] LI J，ZHI J M，HU W，et al.Research on the improvement of vision target tracking algorithm for Internet of things technology and simple extended application in pellet ore phase[J].Future Generation Computer Systems，2020，110：233-242.
[14] SOMAYYEH S M，NEDA F.A hybrid algorithm based on particle filter and genetic algorithm for target tracking[J].Expert Systems with Applications，2020，147：113188.
[15] 董蓉，李勃，陈启美.基于局部不变特征点数据集的目标跟踪算法[J].仪器仪表学报，2012，33（9）：2053-2060.
DONG R，LI B，CHEN Q M.Object tracking algorithm based on dataset of local invariant feature points[J].Chinese Journal of Scientific Instrument，2012，33（9）：2053-2060.
[16] 吕清松，许宜申.基于FPGA的目标识别与跟踪系统设计[J].现代电子技术，2018，41（18）：12-16.
LV Q S，XU Y S.Design of target recognition and tracking system based on FPGA[J].Modern Electronics Technique，2016，41（18）：12-16.
[17] 夏浩伟.基于FPGA复杂背景下机动目标识别的技术研究[D].长春：长春理工大学，2018.
XIA H W.Research on maneuvering target recognition based on FPGA complex background[D].Changchun：Changchun University of Science and Technology，2018.
[18] HENRIQUES J F，CASEIRO R，MARTINS P，et al.High-speed tracking with kernelized correlation filters[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2015，37（3）：583-96.
[19] 李艳荻，徐熙平，陈江，等.动态特征块匹配的背景更新在运动检测的应用[J].仪器仪表学报，2017，38（2）：445-453.
LI Y D，XU X P，CHEN J，et al.Background updating based on dynamic feature block matching for the motion detection[J].Chinese Journal of Scientific Instrument，2017，38（2）：445-453.
[20] 伍济钢，王刚，蒋勉，等.光流点匹配跟踪的薄壁件振动模态测试方法[J].电子测量与仪器学报，2017，31（6）：850-858.
WU J G，WANG G，JIANG M，et al.Vibration modal measurement method for thin-walled parts using optical flow point matching and tracking[J].Journal of Electronic Measurement and Instrumentation，2017，31（6）：850-858.
[21] 唐瑞，侯宏录，侯盼晴.高速视频的运动目标匹配识别算法[J].国外电子测量技术，2018，37（11）：52-57.
TANG R，HOU H L，HOU P Q.Moving target matching recognition algorithm for high speed video[J].Foreign Electronic Measurement Technology，2016，37（11）：52-57.