您的位置：山东大学 -> 科技期刊社 -> 《山东大学学报（工学版）》

山东大学学报 (工学版) ›› 2020, Vol. 50 ›› Issue (3): 51-57.doi: 10.6040/j.issn.1672-3961.0.2019.414

• 机器学习与数据挖掘 • 上一篇    下一篇

联合检测的自适应融合目标跟踪

刘保成(),朴燕*(),宋雪梅   

  1. 长春理工大学电子信息工程学院, 吉林 长春 130012
  • 收稿日期:2019-07-22 出版日期:2020-06-01 发布日期:2020-06-16
  • 通讯作者: 朴燕 E-mail:719741840@qq.com;piaoyan@cust.edu.cn
  • 作者简介:刘保成(1995—)，男，吉林白山人，硕士研究生，主要研究方向为机器学习,计算机视觉. E-mail:719741840@qq.com
  • 基金资助:
    吉林省科技支撑资助项目(20180201091GX);吉林省科技创新中心资助项目(20180623039TC)

Adaptive fusion target tracking based on joint detection

Baocheng LIU(),Yan PIAO*(),Xuemei SONG   

  1. College of Electronic Information Engineering, Changchun University of Science and Technology, Changchun 130012, Jilin, China
  • Received:2019-07-22 Online:2020-06-01 Published:2020-06-16
  • Contact: Yan PIAO E-mail:719741840@qq.com;piaoyan@cust.edu.cn
  • Supported by:
    吉林省科技支撑资助项目(20180201091GX);吉林省科技创新中心资助项目(20180623039TC)

RichHTML

6

PDF (PC)

311

摘要：

由于各种因素的干扰,在现实复杂的情况下目标跟踪过程中可能出现模型漂移和跟踪失败等问题,针对目标跟踪的鲁棒性和准确性提出一种联合检测的自适应融合目标跟踪算法。根据深层和浅层卷积特征具有的不同优点,使它们单独作用于相关滤波器得到其各自的响应分数,通过最小化损失使不同卷积特征的响应分数自适应融合。结合本研究的位置检测方法判断预测位置的有效性和真实性,得到最优的目标跟踪结果。在OTB-2015和VOT-2017两个数据库中进行大量测试,试验结果表明，本研究所提方法与LSART算法相比鲁棒性提高了10%,准确性提高了3.9%,并且对目标遮挡和尺度变化具有出色的性能表现。

关键词: 机器视觉, 目标跟踪, 自适应融合, 卷积特征, 相关滤波

Abstract:

Due to the interference of various factors in the complex situation of reality, the trackers had some problems such as model drift and tracking failure. An adaptive fusion target tracking based on joint detection algorithm was proposed to improve the robustness and accuracy of the tracker. The deep and shallow convolutional features acted on the correlation filters separately to obtain response scores according to their respective advantages, and adaptively fused the response scores of different convolutional features by minimizing the loss. Then it combined with the location detection method to judge the validity and authenticity of the predicted location, so as to get the optimal target tracking results. A large number of tests were done in two open databases: OTB-2015 and VOT-2017. The experimental results showed that the proposed method was 10% more robust and 3.9% more accurate than the LSART algorithm. It also had excellent performance for occlusion and scale variation.

Key words: machine vision, target tracking, adaptive fusion, convolutional feature, correlation filtering

中图分类号: 

  • TP391.41

图1

基于相关滤波的目标跟踪原理框图"

图2

本研究方法的整体框图"

图3

5个视频序列的跟踪结果"

表1

"

方法 精确率/% 成功率/%
Ours 92.4 71.0
ECO 91.0 70.0
C-COT 90.9 69.0
MDNet 89.9 68.5
TCNN 88.4 66.1
DeepSRDCF 85.1 64.3
STRCF 83.5 65.1
BACF 81.3 62.2
SRDCF 78.9 60.5
SiameseFC 77.3 58.2

表2

本研究方法与VOT-2017跟踪器的比较"

方法 平均重叠期望 准确性 鲁棒性
Ours 0.341 0.512 0.196
LSART 0.323 0.493 0.218
CFWCR 0.303 0.484 0.267
CFCF 0.286 0.509 0.281
ECO 0.280 0.483 0.276
Gnet 0.274 0.502 0.276
MCCT 0.270 0.525 0.323
C-COT 0.267 0.494 0.318
CSRDCF 0.256 0.491 0.356
SiamDCF 0.249 0.500 0.473
MCPF 0.248 0.510 0.427
UPDT 0.378 0.536 0.184
1 葛宝义, 左宪章, 胡永江, 等. 基于双步相关滤波的目标跟踪算法[J]. 红外与激光工程, 2018, 47 (12): 388- 397.
GE Baoyi , ZUO Xianzhang , HU Yongjiang , et al. Object tracking algorithm based on two-step correlation filter[J]. Infrared and Laser Engineering, 2018, 47 (12): 388- 397.
2 BHAT G, JOHNANDER J, DANELLJAN M, et al. Unveiling the power of deep tracking[C]//Proceeding of the European Conference on Computer Vision. Munich, Germany: Springer, 2018.
3 BOLME D S, BEVERIDGE J R, DRAPER B A, et al. Visual object tracking using adaptive correlation filters[C]//Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Francisco, USA: IEEE, 2010.
4 HENRIQUES J F, CASEIRO R, MARTINS P, et al. Exploiting the circulant structure of tracking-by-detection with kernels[C]//European Conference on Computer Vision. Berlin, Germany: Springer, 2012.
5 DANELLJAN M, KHAN F S, FELSBERG M, et al. Adaptive color attributes for real-time visual tracking[C]//IEEE Conference on Computer Vision and Pattern Recognition. Columbus, USA: IEEE, 2014.
6 HENRIQUES J F , CASERO R , MARTINS P , et al. High-speed tracking with kernelized correlation filters[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2015, 37 (3): 583- 596.
doi: 10.1109/TPAMI.2014.2345390
7 DANELLJAN M, HAGER G, KHAN F S, et al. Learning spatially regularized correlation filters for visual tracking[C]//IEEE International Conference on Computer Vision. Santiago, Chile: IEEE, 2015.
8 DUANMU F , MA Z , WNAG Y . Fast mode and partition decision using machine learning for intra-frame coding in HEVC screen content coding extension[J]. IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 2016, 6 (4): 517- 531.
doi: 10.1109/JETCAS.2016.2597698
9 NAM H, HAN B. Learning multi-domain convolutional neural networks for visual tracking[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. LAS Vegas, USA: IEEE, 2016.
10 NAM H, BAEK M, HAN B. Modeling and propagating cnns in a tree structure for visual tracking[J/OL]. Computer Science. arXiv: 1608.07242v1.[2019-09-28]. https://arxiv.org/abs/1608.07242.
11 DANELLJAN M, HAGER G, KHAN F S, et al. Convolutional features for correlation filter based visual tracking[C]//Proceedings of the IEEE International Conference on Computer Vision Workshops. Santiago, Chile: IEEE, 2015.
12 DANELLJAN M, ROBINSON A, KHAN F S, et al. Beyond correlation filters: learning continuous convolution operators for visual tracking[C]//European Conference on Computer Vision. Amsterdam, the Netherlands: Springer, 2016.
13 DANELLJAN M, BHAT G, KHAN F S, et al. ECO: efficient convolution operators for tracking[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu Hawaii, USA: IEEE, 2017.
14 HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]// Proceeding of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, USA: IEEE, 2016.
15 WU Y , LIM J , YANG M H . Object tracking benchmark[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2015, 37 (9): 1834- 1848.
doi: 10.1109/TPAMI.2014.2388226
16 KRISTAN M, LEONARDIS A, MATAS J, et al. The visual object tracking vot2017 challenge results[C]//Proceedings of the IEEE International Conference on Computer Vision. Venice, Italy: IEEE, 2017.
17 LI F, TIAN C, ZUO W, et al. Learning spatial-temporal regularized correlation filters for visual tracking[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE, 2018.
18 GALOOGAHI H K, FAGG A, LUCEY S. Learning background-aware correlation filters for visual tracking[C]//Proceedings of the IEEE International Conference on Computer Vision. Venice, Italy: IEEE, 2017.
19 BERTINETTO L, VALMADRE J, HENRIQUES J F, et al. Fully-convolutional siamese networks for object tracking[C]//European Conference on Computer Vision. Amsterdam, the Netherlands: Springer, 2016.
20 刘万军, 孙虎, 姜文涛. 自适应特征选择的相关滤波跟踪算法[J]. 光学学报, 2019, 39 (6): 242- 255.
LIU Wanjun , SUN Hu , JIANG Wentao . Correlation filter tracking algorithm for adaptive feature selection[J]. Acta Optica Sinica, 2019, 39 (6): 242- 255.
[1] 黄劲潮. 深度残差特征与熵能量优化运动目标跟踪算法[J]. 山东大学学报 (工学版), 2019, 49(4): 14-23.
[2] 侯秋林,孙杰,皇攀凌,孙超,牟文平. 基于机器视觉刀具几何参数检测算法与误差分析[J]. 山东大学学报(工学版), 2017, 47(4): 77-82.
[3] 马帅依凡,赵子健. 基于人工标记的手术导航仪[J]. 山东大学学报(工学版), 2017, 47(3): 63-68.
[4] 王海军,葛红娟,张圣燕. 基于L1范数和最小软阈值均方的目标跟踪算法[J]. 山东大学学报(工学版), 2016, 46(3): 14-22.
[5] 郭志波, 董健, 庞成. 多技术融合的Mean-Shift目标跟踪算法[J]. 山东大学学报(工学版), 2015, 45(2): 10-16.
[6] 葛凯蓉, 常发亮, 董文会. 基于局部敏感直方图的稀疏表达跟踪算法[J]. 山东大学学报(工学版), 2014, 44(5): 14-19.
[7] 李武,侯志强*,魏国剑,余旺盛. 跟踪框自适应的尺度变化目标跟踪算法[J]. 山东大学学报(工学版), 2014, 44(2): 28-34.
[8] 邱晓欣1,2,张文强1,2*,秦晋贤1,2,杜正阳1,2,张德峰1,2. 恶劣环境下多目标实时跟踪算法研究[J]. 山东大学学报(工学版), 2014, 44(2): 21-27.
[9] 方 挺,杨 忠,沈春林 . 无人机编队视频序列中的多目标精确跟踪[J]. 山东大学学报(工学版), 2008, 38(4): 22-26 .
[10] 毕侠飞,孙同景,杨福刚,张巍 . 非接触式并行连铸方坯在线定尺切割系统研究[J]. 山东大学学报(工学版), 2008, 38(1): 52-55 .
[11] 冯显英,任长志,黄燕云 . 基于机器视觉的异性纤维检测系统[J]. 山东大学学报(工学版), 2006, 36(4): 5-08 .
[12] 马丽,常发亮,乔谊正 . 基于遗传算法和粒子滤波器的非刚性目标跟踪[J]. 山东大学学报(工学版), 2006, 36(3): 26-29 .
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
[1] 张永花,王安玲,刘福平 . 低频非均匀电磁波在导电界面的反射相角[J]. 山东大学学报(工学版), 2006, 36(2): 22 -25 .
[2] 韩雪. 平庄西露天煤矿滑坡灾害远程监测实例分析[J]. 山东大学学报(工学版), 2009, 39(4): 116 -120 .
[3] 孔祥臻,刘延俊,王勇,赵秀华 . 气动比例阀的死区补偿与仿真[J]. 山东大学学报(工学版), 2006, 36(1): 99 -102 .
[4] 陈瑞,李红伟,田靖. 磁极数对径向磁轴承承载力的影响[J]. 山东大学学报(工学版), 2018, 48(2): 81 -85 .
[5] 王波,王宁生 . 机电装配体拆卸序列的自动生成及组合优化[J]. 山东大学学报(工学版), 2006, 36(2): 52 -57 .
[6] 李可,刘常春,李同磊 . 一种改进的最大互信息医学图像配准算法[J]. 山东大学学报(工学版), 2006, 36(2): 107 -110 .
[7] 季涛,高旭,孙同景,薛永端,徐丙垠 . 铁路10 kV自闭/贯通线路故障行波特征分析[J]. 山东大学学报(工学版), 2006, 36(2): 111 -116 .
[8] 刘文亮,朱维红,陈涤,张泓泉. 基于雷达图像的运动目标形态检测及跟踪技术[J]. 山东大学学报(工学版), 2010, 40(3): 31 -36 .
[9] 张英,郎咏梅,赵玉晓,张鉴达,乔鹏,李善评 . 由EGSB厌氧颗粒污泥培养好氧颗粒污泥的工艺探讨[J]. 山东大学学报(工学版), 2006, 36(4): 56 -59 .
[10] 李芳佳, 高尚策, 唐政, 石井雅博, 山下和也. 基于元胞自动化模型的三维雪花晶体近似模式的产生（英文）[J]. 山东大学学报(工学版), 2009, 39(1): 102 -105 .
版权所有 © 2018 《山东大学学报(工学版)》编辑部　
地址: 济南市山大南路27号（250100）　 电话: 0531-88366735　 E-mail: xbgxb@sdu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发