基于视频的装甲车和飞机检测跟踪及轨迹预测算法

doi:10.3969/j.issn.1000-1093.2021.03.010

兵工学报 ›› 2021, Vol. 42 ›› Issue (3): 545-554.doi: 10.3969/j.issn.1000-1093.2021.03.010

基于视频的装甲车和飞机检测跟踪及轨迹预测算法

张永梅¹，赖裕平¹，马健喆²，冯超¹，束颉¹

（1.北方工业大学信息学院，北京 100144； 2.香港理工大学电子与信息工程系，香港 00852）

上线日期:2021-04-26
通讯作者: 赖裕平(1983—)，男，副教授，硕士生导师，博士 E-mail:laiyp@ncut.edu.cn
作者简介:张永梅(1967—)，女，教授，博士生导师。E-mail: zhangym@ncut.edu.cn；
马健喆(1995—)，男，硕士研究生。E-mail: 774381239@qq.com；
冯超(1993—)，男，硕士研究生。E-mail: 2647364229@qq.com；
束颉(1983—)，男，讲师，博士。E-mail: shujie@ncut.edu.cn
基金资助:
国家自然科学基金项目（61371143）；国家重点研发计划项目（2020YFC0811004）；北京市教育委员会基本科研业务费项目（110052971921/002）；教育部科技发展中心“天诚汇智”创新促教基金项目（2018A03029）；教育部高等教育司产学合作协同育人项目（201902083001）；北京市教育委员会科技项目（KM202110009002）

A Video-based Prediction Algorithm for Armored Vehicle and Aircraft Detection/tracking and Trajectory

ZHANG Yongmei¹， LAI Yuping¹， MA Jianzhe²， FENG Chao¹， SHU Jie¹

(1.School of Information Science and Technology， North China University of Technology， Beijing 100144， China;2.Department of Electronic & Information Engineering， The Hong Kong Polytechnic University， Hong Kong 00852， China)

Online:2021-04-26

摘要/Abstract

摘要： 针对当前视频目标跟踪算法跟踪多目标容易跟丢的问题，以视频中的装甲车、飞机为研究对象，研究一种改进跟踪学习检测（TLD）的视频多目标检测跟踪算法。对于跟丢的目标，利用Kalman滤波算法的预测功能跟踪视频中典型目标的轨迹，并采用Kalman滤波算法跟踪的轨迹来弥补TLD算法丢失的部分，从而获得视频中典型目标的完整轨迹，以提高视频多目标跟踪的准确率。由于现有轨迹预测算法存在准确性较差的局限性，提出一种基于社交长短时记忆（Social-LSTM）网络的视频典型目标轨迹预测算法，将上下文环境信息和多个目标轨迹之间的相互影响关系融入Social-LSTM网络，预测待检测典型目标的轨迹序列。仿真实验结果表明，所提轨迹预测算法优于传统的LSTM算法、隐马尔可夫模型算法以及混合高斯模型算法，有利于提高视频典型目标轨迹预测的准确率。

关键词: 装甲车, 飞机, 目标跟踪, 多目标检测, 社交长短时记忆网络, 轨迹预测

Abstract: To solve the problem of easily losing the targets when tracking multiple targets by the current video target tracking algorithms，an improved tracking-learning-detection (TLD) algorithm is presented for multi-target detection and tracking by taking armored vehicles and aircrafts in videos as the research objects.For the lost targets，the trajectories of typical targets in video are tracked by using the prediction function of Kalman filtering algorithm，and the tracked trajectories are used to compensate for the lost parts of TLD algorithm so as to obtain the complete trajectories of typical targets in videos，which is beneficial to improve the accuracy of video multi-target tracking.For the poorer accuracy of the existing trajectory prediction methods，a video target trajectory prediction algorithm based on social long short term memory (Social-LSTM) network is proposed. The algorithm integrates the contextual environment information and the interaction relationship among multiple target trajectories into Social-LSTM network and predicts the trajectories of the typical targets to be detected. Simulation experimental results show the trajectory prediction algorithm is superior to the traditional LSTM algorithm，hidden Markov model (HMM) algorithm，and Gaussian mixture model (GMM) algorithm，which is helpful to improve the accuracy of trajectory prediction for typical video targets.

Key words: armoredvehicle, aircraft, objecttracking, multi-targetdetection, social-longshorttermmemorynetwork, trajectoryprediction

中图分类号:

TP391.413

张永梅，赖裕平，马健喆，冯超，束颉. 基于视频的装甲车和飞机检测跟踪及轨迹预测算法[J]. 兵工学报, 2021, 42(3): 545-554.

ZHANG Yongmei， LAI Yuping， MA Jianzhe， FENG Chao， SHU Jie. A Video-based Prediction Algorithm for Armored Vehicle and Aircraft Detection/tracking and Trajectory[J]. Acta Armamentarii, 2021, 42(3): 545-554.

参考文献

［1］孙红，陈锁.一种聚类隐马尔可夫模型的时空轨迹预侧算法[J].小型微型计算机系统，2019，40(3):472-476.
SUN H，CHEN S.Spatio-temporal trajectory prediction algorithm based on clustering based hidden markov model[J].Journal of Chinese Computer Systems，2019，40(3):472-476.(in Chinese)
[2］张净，孙志挥，杨明，等.基于网格和密度的海量数据增量式离群点挖掘算法[J].计算机研究与发展，2011，48(5):823-830.
ZHANG J，SUN Z H，YANG M，et al.Fast incremental outlier mining algorithm based on grid and capacity[J].Journal of Computer Research and Development，2011，48(5):823-830.(in Chinese)
[3］ LASSOUED Y，MONTEIL J，GU Y Q，et al.A hidden Markov model for route and destination prediction[C]∥Proceedings of the 20th International Conference on Intelligent Transportation Systems. Piscataway，NJ，US:IEEE，2017:1-6.
[4］林毅，张建伟，武喜萍，等.基于GMM的航班轨迹预侧算法研究[J].工程科学与技术，2018，50(4):104-109.
LIN Y，ZHANG J W，WU X P，et al.Study on algorithm for flight trajectory prediction based on GMM[J]. Advanced Engineering Sciences，2018，50(4):104-109. (in Chinese)
[5］乔少杰,金琨，韩楠，等.一种基于高斯混合模型的轨迹预测算法[J].软件学报，2015，26(5): 1048-1063.
QIAO S J，JIN K，HAN N，et al.Trajectory prediction algorithm based on Gaussian mixture mode[J].Journal of Software，2015，26(5): 1048-1063.(in Chinese)
[6］ HOCHREITER S，SCHMIDHUBER J.Long short-term memory[J]. Neural Computation，1997，9(8):1735-1780.
[7］崔粟晋，王雪. 基于长短时记忆太阳能无线传感节点能量预测[J].仪器仪表学报，2018，39(11):147-154.
CUI S J，WANG X.Solar wireless sensor node energy prediction based on long-short term memory[J].Chinese Journal of Scientific Instrument，2018，39(11):147-154.(in Chinese)
[8］魏昱洲，许西宁.基于LSTM长短期记忆网络的超短期风速预测[J].电子测量与仪器学报，2019，33(2):64-71.
WEI Y Z，XU X N.Ultra-short-term wind speed prediction model using LSTM networks[J].Journal of Electronic Measurement and Instrument，2019，33(2):64-71.(in Chinese)
[9］ XUE H，HUYNH D Q，REYNOLDS M，et al.SS-LSTM:a hierarchical LSTM model forpedestrian trajectory prediction[C]∥Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision.Lake Tahoe，NV，US:IEEE，2018:1186-1194.
[10］ ALAHI A，GOEL K，RAMANATHAN V，et al. Social LSTM:human trajectory prediction in crowded spaces[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas，NV，US:IEEE，2016:961-971.
[11］黄健斌，张盼盼，皇甫学军，等.融合语义特征的移动对象轨迹预测方法[J].计算机研究与发展，2014，51(1):76-87.
HUANG J B，ZHANG P P，HUANGFU X J，et al.A trajectory prediction approach for mobile objects by combining semantic features[J].Journal of Computer Research and Development，2014，51(1):76-87.(in Chinese)
[12］刘彩虹，张磊，黄华.交通路口监控视频跨视域多目标跟踪的可视化[J].计算机学报，2018，41(1):221-235.
LIU C H，ZHANG L，HUANG H.Visualization of cross-view multi-object tracking for surveillance videos in crossroad[J].Chinese Journal of Computers，2018，41(1):221-235. (in Chinese)
[13］ DANELLJAN M，BHAT G，SHAHBAZ KHAN F，et al. ECO:Efficient convolution operators for tracking[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Honolulu，HI，US:IEEE，2017:6638-6646.
[14］ BIBI A，MUELLER M，GHANEM B.Target response adaptation for correlation filter tracking[C]∥Proceedings of the 2016 IEEE European Conference on Computer Vision Workshop.Amsterdam，the Nethland:IEEE，2016:419-433.
[15］梁杰，李磊，任君，等.基于深度学习的红外图像遮挡干扰检测方法[J].兵工学报，2019，40(7):1401-1410.
LIANG J，LI L，REN J，et al.Infrared image occlusion interference detection method based on deep learning[J]. Acta Armamentarii，2019，40(7):1401-1410. (in Chinese)
[16］ GRAVES A，MOHAMED A R，HINTON G.Speech recognition with deep recurrent neural networks[C]∥Proceedings of 2013 IEEE International Conference on Acoustics，Speech and Signal Processing.Vancouver，Canada:IEEE，2013:2348-2356.

[1]	杜志岐，唐镜. 基于系统工程的装甲车辆总体设计[J]. 兵工学报, 2022, 43(S1): 1-10.
[2]	李景奎，林文杰，江秀红，卢雨泽. 基于GO-Markov的飞机燃油闭环控制系统可靠性分析[J]. 兵工学报, 2022, 43(6): 1447-1455.
[3]	张昀普，单甘霖. 道路约束下多传感器协同地面目标跟踪的管理方法[J]. 兵工学报, 2022, 43(3): 542-555.
[4]	骆亮，裴扬，侯鹏，张梦涛，李明锁. 飞机燃油箱油气空间引燃概率函数预测模型[J]. 兵工学报, 2022, 43(2): 383-390.
[5]	江秀红，李佳欣，刘彦娟，王玉颖. 含反馈环的电动飞机驱动系统可靠性分析方法[J]. 兵工学报, 2022, 43(2): 451-457.
[6]	李纪三，侯娇，刘溶，任渊. 基于贝叶斯滤波算法的警戒相控阵雷达目标跟踪时间资源优化分配算法[J]. 兵工学报, 2021, 42(9): 1902-1910.
[7]	姜珊，底晓强，韩成. 融合时空特性的孪生网络视觉跟踪[J]. 兵工学报, 2021, 42(9): 1940-1950.
[8]	丁海婷，周琳，刁伟峰. 基于背包问题的多相控阵雷达多目标跟踪时间资源管理算法[J]. 兵工学报, 2021, 42(5): 997-1003.
[9]	郭司南，完颜笑如，刘双，梁超然，陈浩. 智能化设计与信息加工通道复杂度对装甲车乘员脑力负荷的影响[J]. 兵工学报, 2021, 42(2): 234-241.
[10]	张君彪，熊家军，兰旭辉，李凡，陈新，席秋实. 基于自适应多通道交互式多模型的高超声速滑翔飞行器跟踪方法[J]. 兵工学报, 2021, 42(12): 2626-2636.
[11]	林锋，姚婉，秦国华，叶海潮，陶江. 飞机整体结构件加工变形的初始残余应力-初始几何误差耦合影响与控制[J]. 兵工学报, 2021, 42(12): 2731-2742.
[12]	廖自力，疏歆，高强，李嘉麒. 电传动装甲车辆母线电压双通道补偿控制[J]. 兵工学报, 2021, 42(10): 2082-2091.
[13]	刘春光，陈路明，张运银，张征，徐浩轩. 基于改进灰色马尔可夫链的电传动装甲车辆负载需求功率预测[J]. 兵工学报, 2021, 42(10): 2130-2144.
[14]	蔡立春，廖自力，李嘉麒，张运银，王科淯. 8×8分布式电驱动装甲车辆稳定性直接横摆力矩与转矩矢量控制[J]. 兵工学报, 2021, 42(10): 2196-2205.
[15]	刘越，席军强，田真，张欣. 轮式装甲车辆电驱动轮机电耦合动力学建模与振动特性[J]. 兵工学报, 2021, 42(10): 2260-2267.

基于视频的装甲车和飞机检测跟踪及轨迹预测算法

A Video-based Prediction Algorithm for Armored Vehicle and Aircraft Detection/tracking and Trajectory

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价