基于正交试验的运动目标跟踪算法性能评价

doi:10.19678/j.issn.1000-3428.0054295

计算机工程 ›› 2020, Vol. 46 ›› Issue (3): 254-260,266. doi: 10.19678/j.issn.1000-3428.0054295

基于正交试验的运动目标跟踪算法性能评价

郗润平^1,2,3, 薛少辉^1,2,3

1. 西北工业大学计算机学院, 西安 710129;
2. 空天地海一体化大数据应用技术国家工程实验室, 西安 710129;
3. 陕西省语音与图像信息处理重点实验室, 西安 710129

收稿日期:2019-03-19 修回日期:2019-04-23 发布日期:2019-05-16
作者简介:郗润平(1971-),男,副教授、博士,主研方向为图形图像处理、计算机视觉;薛少辉(通信作者),硕士研究生。
基金资助:
国家自然科学基金"基于生物视觉的无人机群多源图像目标协同检测方法研究"（61572405）；国家高技术研究发展计划"全景互动关键技术与示范系统主题项目"（2015AA016400）。

Performance Evaluation for Moving Target Tracking Algorithm Based on Orthogonal Test

XI Runping^1,2,3, XUE Shaohui^1,2,3

1. School of Computer Science, Northwestern Polytechnical University, Xi'an 710129, China;
2. National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, Xi'an 710129, China;
3. Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, Xi'an 710129, China

Received:2019-03-19 Revised:2019-04-23 Published:2019-05-16

摘要/Abstract

摘要： 针对目前运动目标跟踪算法性能评价中测试数据量大、试验次数多以及未充分考虑多因素组合场景下的算法性能表现等问题，提出一种基于正交试验的运动目标跟踪算法性能评价方法。分析影响算法性能的因素和水平，构建正交试验数据集，通过该数据集测试算法性能并利用极差分析法分析数据结果，以得到各影响因素间的强弱关系以及算法性能表现较好时的因素水平组合方式。分析结果表明，该方法能够全面、有效地评估运动目标跟踪算法的性能，减少测试次数和数据量，并为其他图像处理算法的性能评估提供参考。

关键词: 正交试验, 目标跟踪, 评价指标, 多因素组合, 极差分析法

Abstract: The performance evaluation of existing moving target tracking algorithms has many drawbacks,such as massive amount of data,redundant tests and insufficient consideration on algorithm performance under multifactor situation.Therefore,this paper proposes a performance evaluation method for moving target tracking algorithm based on orthogonal test.After a full analysis on the factors and levels that affect algorithm performance,the dataset of orthogonal test is built and then used for algorithm performance test.The data results are analyzed by the range analysis method,so as to obtain the relationship between the factors that affect the algorithm,as well as the combination of factor levels when the algorithm performance is good.Experimental results show that the proposed method can evaluate the performance of the moving target tracking algorithm in a comprehensive and effective way.Besides,this method can reduce the number of tests and data volume,and provide reference for the performance evaluation of other image processing algorithms.

Key words: orthogonal test, target tracking, evaluation index, multifactor combination, range analysis method

中图分类号:

TP391

郗润平, 薛少辉. 基于正交试验的运动目标跟踪算法性能评价[J]. 计算机工程, 2020, 46(3): 254-260,266.

XI Runping, XUE Shaohui. Performance Evaluation for Moving Target Tracking Algorithm Based on Orthogonal Test[J]. Computer Engineering, 2020, 46(3): 254-260,266.

https://www.ecice06.com/CN/Y2020/V46/I3/254

图/表 18

20200321092054

20200321092107

20200321092115

20200321092118

20200321092122

20200321092125

20200321092129

20200321092132

20200321092135

20200321092138

20200321092141

20200321092145

20200321092149

20200321092152

20200321092156

20200321092200

20200321092203

20200321092206

参考文献

[1] LI Y,ZHU J K,STEVEN C H H,et al.Robust estimation of similarity transformation for visual object tracking[EB/OL].[2019-02-20].https://arxiv.org/pdf/1712.05231.pdf.
[2] LI Bo,WU Wei,WANG Qiang,et al.SiamRPN++:evolution of siamese visual tracking with very deep networks[EB/OL].[2019-02-20].https://deepai.org/publication/siamrpn-evolution-of-siamese-visual-tracking-with-very-deep-networks.
[3] FAN Heng,LING Haibin.Siamese cascaded region proposal networks for real-time visual tracking[EB/OL].[2019-02-20].https://arxiv.org/abs/1812.06148?context=cs.CV.
[4] COLLINS R,ZHOU X,SENG K T.An open source tracking testbed and evaluation Web site[EB/OL].[2019-02-20].http://www.doc88.com/p-3147684661181.html.
[5] FISHER R B.The PETS04 surveillance ground-truth data sets[EB/OL].[2019-02-20].http://homepages.inf.ed.ac.uk/rbf/CAVIAR/PAPERS/pets04.pdf.
[6] FERRYMAN J,SHAHROKNI A.PETS2009:dataset and challenge[C]//Proceedings of the 20th IEEE International Workshop on Performance Evaluation of Tracking and Surveillance.Washington D.C.,USA:IEEE Press,2010:1-6.
[7] WU Y,LIM J,YANG M H.Online object tracking:a benchmark[C]//Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:2411-2418.
[8] WU Y,LIM J,YANG M H.Object tracking benchmark[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1834-1848.
[9] KRISTAN M,PFLUGFELDER R,MATAS J,et al.The visual object tracking VOT2015 challenge results[C]//Proceedings of IEEE International Conference on Computer Vision Workshop.Washington D.C.,USA:IEEE Press,2015:564-586.
[10] KRISTAN M,LEONARDIS A,MATAS J,et al.The visual object tracking VOT2016 challenge results[C]//Proceedings of IEEE International Conference on Computer Vision Workshop.Washington D.C.,USA:IEEE Press,2016:98-111.
[11] KRISTAN M,ELDESOKEY A,XING Y,et al.The visual object tracking VOT2017 challenge results[C]//Proceedings of IEEE International Conference on Computer Vision Workshop.Washington D.C.,USA:IEEE Press,2017:25-36.
[12] CHENG Yongchun,ZHANG Peng,JIAO Yubo,et al.Grey correlation analysis method to analyze the influence factors of attenuated performance of asphalt mixture under water-temperature-radiation cycle action[J].Applied Mechanics and Materials,2013,361/362/363:1857-1860.
[13] HARE S,SAFFARI A,TORR P H S.Struck:structured output tracking with kernels[C]//Proceedings of International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2011:263-270.
[14] DINH T B,VO N,GÉRARD M.Context tracker:exploring supporters and distracters in unconstrained environments[C]//Proceedings of the 24th IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2011:1177-1184.
[15] BROX T,DERICHE R,WEICKERT J.Colour,texture,and motion in level set based segmentation and tracking[J].Image and Vision Computing,2010,28(3):376-390.
[16] KASS M,WITKIN A,TERZOPOULOS D.Snakes:active contour models[J].International Journal of Computer Vision,1988,1(4):321-331.
[17] GUAN Xing.Research on behavior detection and tracking algorithm of moving targets in intelligent monitoring[D].Chongqing:Chongqing University of Posts and Telecommunications,2013.(in Chinese)关兴.智能监控中运动目标的行为探测跟踪算法研究[D].重庆:重庆邮电大学,2013.
[18] LIU Changyun,SHUI Penglang,LI Song.Unscented extended Kalman filter for target tracking[J].Journal of Systems Engineering and Electronics,2011,22(2):188-192.
[19] SHERRAH J,RISTIC B,REDDING N J.Particle filter to track multiple people for visual surveillance[J].IET Computer Vision,2011,5(4):192-200.
[20] ZHENG Geyu.A construction method of orthogonal table L_(p~2)(p~(p-1))[J].Journal of Central China Normal University(Natural Sciences),1982(2):35-49.(in Chinese)郑格于.正交表L_(p~2)(p~(p-1))的一种构造方法[J].华中师范大学学报(自然科学版),1982(2):35-49.
[21] LI Na,WANG Dan.Image synthesis algorithm based on sample cutout and adaptive color[J].Chinese Journal of Liquid Crystals and Displays,2018,33(2):156-164.(in Chinese)李娜,王丹.基于采样抠图和自适应颜色的图像合成算法[J].液晶与显示,2018,33(2):156-164.
[22] LIU Minglei.Analysis of variance in orthogonal experimental design[D].Harbin:Northeast Forestry University,2011.(in Chinese)刘明磊.正交试验设计中的方差分析[D].哈尔滨:东北林业大学,2011.
[23] FAWCETT T.An introduction to ROC analysis[J].Pattern Recognition Letters,2006,27(8):861-874.

选择文件类型/文献管理软件名称

选择包含的内容

基于正交试验的运动目标跟踪算法性能评价

Performance Evaluation for Moving Target Tracking Algorithm Based on Orthogonal Test

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 18

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	安玉, 葛海波, 何文昊, 马赛, 程梦洋. 基于补偿注意力机制的Siamese网络跟踪算法[J]. 计算机工程, 2024, 50(4): 187-196.
[2]	王春雷, 张建林, 李美惠, 徐智勇, 魏宇星. 结合卷积Transformer的目标跟踪算法[J]. 计算机工程, 2023, 49(4): 281-288,296.
[3]	周海赟, 项学智, 王馨遥, 任文凯. 多特征融合的端到端链式行人多目标跟踪网络[J]. 计算机工程, 2022, 48(9): 305-313.
[4]	杨帅东, 谌海云, 徐钒诚, 赵书朵, 袁杰敏. 基于孪生区域建议网络的无人机目标跟踪算法[J]. 计算机工程, 2022, 48(1): 288-295,304.
[5]	张海涛, 秦鹏程. 基于GMS与FPME的视频目标跟踪方法[J]. 计算机工程, 2021, 47(7): 226-231.
[6]	任立成, 杨嘉棋, 魏宇星, 张建林. 基于特征融合与双模板嵌套更新的孪生网络跟踪算法[J]. 计算机工程, 2021, 47(7): 239-248.
[7]	苏超群, 朱正为, 郭玉英. 基于高效卷积算子的异常抑制目标跟踪算法[J]. 计算机工程, 2021, 47(7): 266-272,288.
[8]	李志鹏, 张睿. 一种基于对抗学习的实时跟踪模型设计[J]. 计算机工程, 2021, 47(6): 262-270.
[9]	尚桠朝, 孟令军. 基于多特征和尺度估计的KCF_MTSA算法[J]. 计算机工程, 2021, 47(3): 102-108,116.
[10]	罗朔, 侯进, 谭光鸿, 韩雁鹏. 一种低参数的孪生卷积网络实时目标跟踪算法[J]. 计算机工程, 2021, 47(2): 84-89.
[11]	张腾飞, 周书仁, 彭建. 基于双孪生网络的自适应选择跟踪系统[J]. 计算机工程, 2020, 46(6): 103-107.
[12]	沈泽君, 丁飞飞, 杨文元. 多粒度相关滤波视频跟踪方法[J]. 计算机工程, 2020, 46(5): 274-281.
[13]	周双双, 宋慧慧, 张开华, 樊佳庆. 基于增强语义与多注意力机制学习的深度相关跟踪[J]. 计算机工程, 2020, 46(2): 279-285.
[14]	王宇丰, 冯新喜. 基于纯测距的移动传感器网络目标跟踪算法[J]. 计算机工程, 2020, 46(11): 77-83.
[15]	李明杰, 冯有前, 尹忠海, 周诚, 董方昊. 一种用于单目标跟踪的锚框掩码孪生RPN模型[J]. 计算机工程, 2019, 45(9): 216-221.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于正交试验的运动目标跟踪算法性能评价

Performance Evaluation for Moving Target Tracking Algorithm Based on Orthogonal Test

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 18

参考文献

相关文章 15

编辑推荐

Metrics

本文评价