Improved TLD algorithm based on artificial fish-swarm particle filter

Zhi-feng ZHOU; Ting TU; Li-duan WANG; Ming-hui WU

doi:10.37188/YJYXS20203509.0965

您当前的位置：

首页 >

文章列表页 >

Improved TLD algorithm based on artificial fish-swarm particle filter

Image Processing | 更新时间：2020-09-08

- Improved TLD algorithm based on artificial fish-swarm particle filter
- Chinese Journal of Liquid Crystals and Displays Vol. 35, Issue 9, Pages: 965-971(2020)
- 作者机构：
  
  1.上海工程技术大学机械与汽车工程学院, 上海 201620
  2.上海司南卫星导航技术股份有限公司, 上海 201801
- 作者简介：
- 基金信息：
  
  Research Fund of Science and Technology Commission of Shanghai Municipality(17511106700)
- DOI：10.37188/YJYXS20203509.0965
  CLC： P391.4
- Received：28 April 2020，
  
  Revised：11 May 2020，
  
  Accepted：11 May 2020，
  
  Published：05 September 2020
- 稿件说明：
移动端阅览
Zhi-feng ZHOU, Ting TU, Li-duan WANG, et al. Improved TLD algorithm based on artificial fish-swarm particle filter[J]. Chinese journal of liquid crystals and displays, 2020, 35(9): 965-971.
DOI：

Zhi-feng ZHOU, Ting TU, Li-duan WANG, et al. Improved TLD algorithm based on artificial fish-swarm particle filter[J]. Chinese journal of liquid crystals and displays, 2020, 35(9): 965-971. DOI： 10.37188/YJYXS20203509.0965.

摘要

在面对光照变化、部分遮挡、背景杂乱和平面内外旋转等跟踪难点时，跟踪学习检测算法(Tracking-Learning-Detection，TLD)容易产生漂移导致跟踪失败，其跟踪性能还有待提高。在传统TLD算法的基础上，提出一种基于人工鱼群粒子滤波的TLD改进算法。首先使用人工鱼群粒子滤波跟踪器代替金字塔光流跟踪器，将颜色直方图特征和方向梯度直方图特征进行融合，建立目标表观模型，引入图像金字塔多尺度思想进行尺度匹配，提高目标跟踪的稳健性。然后通过粒子滤波过程预测目标区域，将TLD算法检测模块的全局扫描改进为局部扫描，剔除大量非目标区域，提高检测模块的检测效率。实验结果表明：基于人工鱼群粒子滤波的TLD改进算法具有良好的跟踪性能，与传统TLD算法相比，其平均成功率和精准度分别提高了19.04%和28.00%，平均跟踪速度可达33.87 FPS，提高了38.78%。

Abstract

Faced with tracking difficulties such as illumination variation

occlusion

background clutters

in-plane and out-of-plane rotation

the Tracking-Learning-Detection (TLD) algorithm is prone to drift and cause tracking failures

and its tracking performance needs to be improved. Based on the traditional TLD algorithm

an improved TLD algorithm based on artificial fish swarm particle filtering is proposed. Firstly

the artificial fish swarm particle filter tracker is used to replace the optical flow tracker. The color histogram feature and histogram of oriented gradient feature are fused to establish the target appearance model. The image pyramid multi-scale idea is introduced for scale matching to improve the robustness of target tracking. Then

the target area is predicted through the particle filtering process. The global scanning of TLD algorithm detection module is improved to be the local scanning. A large number of non-target areas are eliminated

and the detection efficiency is improved. The experimental results show that the improved TLD algorithm based on artificial fish swarm particle filtering has good tracking performance. Compared with the traditional TLD algorithm

its average success rate and precision have improved by 19.04% and 28.00%

and the average tracking speed can reach 33.87 FPS

which has improved by 38.78%.

关键词

Keywords

references

尹宏鹏 , 陈波 , 柴毅 , 等 . 基于视觉的目标检测与跟踪综述 . 自动化学报 , 2016 . 42 ( 10 ): 1466 - 1489 . http://www.cqvip.com/main/zcps.aspx?c=1&id=670334085 http://www.cqvip.com/main/zcps.aspx?c=1&id=670334085 .

H P YIN , B CHEN , Y CHAI , 等 . Vision-based object detection and tracking:a review . Acta Automatica Sinica , 2016 . 42 ( 10 ): 1466 - 1489 . http://www.cqvip.com/main/zcps.aspx?c=1&id=670334085 http://www.cqvip.com/main/zcps.aspx?c=1&id=670334085 .

高文 , 朱明 , 贺柏根 , 等 . 目标跟踪技术综述 . 中国光学 , 2014 . 7 ( 3 ): 365 - 375 . http://www.cqvip.com/QK/60129A/201403/49849350.html http://www.cqvip.com/QK/60129A/201403/49849350.html .

W GAO , M ZHU , B G HE , 等 . Overview of target tracking technology . Chinese Optics , 2014 . 7 ( 3 ): 365 - 375 . http://www.cqvip.com/QK/60129A/201403/49849350.html http://www.cqvip.com/QK/60129A/201403/49849350.html .

薛陈 , 朱明 , 刘春香 . 遮挡情况下目标跟踪算法综述 . 中国光学 , 2009 . 2 ( 5 ): 388 - 394 . http://www.cnki.com.cn/Article/CJFDTotal-ZGGA200905003.htm http://www.cnki.com.cn/Article/CJFDTotal-ZGGA200905003.htm .

C XUE , M ZHU , C X LIU . Review of tracking algorithms under occlusions . Chinese Optics , 2009 . 2 ( 5 ): 388 - 394 . http://www.cnki.com.cn/Article/CJFDTotal-ZGGA200905003.htm http://www.cnki.com.cn/Article/CJFDTotal-ZGGA200905003.htm .

唐聪 , 凌永顺 , 杨华 , 等 . 基于深度学习的红外与可见光决策级融合跟踪 . 激光与光电子学进展 , 2019 . 56 ( 7 ): 071502 http://www.cnki.com.cn/Article/CJFDTotal-JGDJ201907023.htm http://www.cnki.com.cn/Article/CJFDTotal-JGDJ201907023.htm .

C TANG , Y S LING , H YANG , 等 . Decision-level fusion tracking for infrared and visible spectra based on deep learning . Laser & Optoelectronics Progress , 2019 . 56 ( 7 ): 071502 http://www.cnki.com.cn/Article/CJFDTotal-JGDJ201907023.htm http://www.cnki.com.cn/Article/CJFDTotal-JGDJ201907023.htm .

Z KALAL , K MIKOLAJCZYK , J MATAS . Tracking-learning-detection . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2012 . 34 ( 7 ): 1409 - 1422 . DOI: 10.1109/TPAMI.2011.239 http://doi.org/10.1109/TPAMI.2011.239 .

吴荻 , 战凯 , 肖小凤 . 基于改进光流法和纹理权重的视觉里程计 . 计算机工程与设计 , 2019 . 40 ( 1 ): 230 - 235 . http://www.cnki.com.cn/Article/CJFDTotal-SJSJ201901037.htm http://www.cnki.com.cn/Article/CJFDTotal-SJSJ201901037.htm .

D WU , K ZHAN , X F XIAO . Visual odometry based on modified optical flow and texture weights . Computer Engineering and Design , 2019 . 40 ( 1 ): 230 - 235 . http://www.cnki.com.cn/Article/CJFDTotal-SJSJ201901037.htm http://www.cnki.com.cn/Article/CJFDTotal-SJSJ201901037.htm .

SUN C J, ZHU S H, LIU J W. Fusing Kalman filter with TLD algorithm for target tracking[C]// Proceedings of 2015 34 th Chinese Control Conference . Hangzhou: IEEE, 2015: 3736-3741.

曲海成 , 单晓晨 , 孟煜 , 等 . 检测区域动态调整的TLD目标跟踪算法 . 计算机应用 , 2015 . 35 ( 10 ): 2985 - 2989 . http://www.cnki.com.cn/Article/CJFDTotal-JSJY201510056.htm http://www.cnki.com.cn/Article/CJFDTotal-JSJY201510056.htm .

H C QU , X C SHAN , Y MENG , 等 . Improved TLD target tracking algorithm based on automatic adjustment of surveyed areas . Journal of Computer Applications , 2015 . 35 ( 10 ): 2985 - 2989 . http://www.cnki.com.cn/Article/CJFDTotal-JSJY201510056.htm http://www.cnki.com.cn/Article/CJFDTotal-JSJY201510056.htm .

周鑫 , 钱秋朦 , 叶永强 , 等 . 改进后的TLD视频目标跟踪方法 . 中国图象图形学报 , 2013 . 18 ( 9 ): 1115 - 1123 . http://d.wanfangdata.com.cn/Periodical/zgtxtxxb-a201309008 http://d.wanfangdata.com.cn/Periodical/zgtxtxxb-a201309008 .

X ZHOU , Q M QIAN , Y Q YE , 等 . Improved TLD visual target tracking algorithm . Journal of Image and Graphics , 2013 . 18 ( 9 ): 1115 - 1123 . http://d.wanfangdata.com.cn/Periodical/zgtxtxxb-a201309008 http://d.wanfangdata.com.cn/Periodical/zgtxtxxb-a201309008 .

秦飞 , 汪荣贵 , 梁启香 , 等 . 基于关键特征点的改进TLD目标跟踪算法研究 . 计算机工程与应用 , 2016 . 52 ( 4 ): 181 - 187 . http://www.cqvip.com/QK/91690X/201604/667953780.html http://www.cqvip.com/QK/91690X/201604/667953780.html .

F QIN , R G WANG , Q X LIANG , 等 . Improved TLD target tracking algorithm based on key feature points . Computer Engineering and Applications , 2016 . 52 ( 4 ): 181 - 187 . http://www.cqvip.com/QK/91690X/201604/667953780.html http://www.cqvip.com/QK/91690X/201604/667953780.html .

T H WU , P WANG , S N YIN , 等 . A new human eye tracking algorithm of optimized TLD based on improved mean-shift . International Journal of Pattern Recognition and Artificial Intelligence , 2017 . 31 ( 3 ): 1755007 DOI: 10.1142/S0218001417550072 http://doi.org/10.1142/S0218001417550072 .

康海林 , 赵婷 , 周骅 , 等 . 结合BRISK与区域预估的改进长时跟踪算法 . 激光与光电子学进展 , 2018 . 55 ( 6 ): 061503 http://kns.cnki.net/KCMS/detail/detail.aspx?dbcode=CJFD&filename=JGDJ201806042 http://kns.cnki.net/KCMS/detail/detail.aspx?dbcode=CJFD&filename=JGDJ201806042 .

H L KANG , T ZHAO , H ZHOU , 等 . Improved long time tracking algorithm by combining BRISK and region estimation . Laser & Optoelectronics Progress , 2018 . 55 ( 6 ): 061503 http://kns.cnki.net/KCMS/detail/detail.aspx?dbcode=CJFD&filename=JGDJ201806042 http://kns.cnki.net/KCMS/detail/detail.aspx?dbcode=CJFD&filename=JGDJ201806042 .

王姣尧 , 侯志强 , 余旺盛 , 等 . 采用核相关滤波的快速TLD视觉目标跟踪 . 中国图象图形学报 , 2018 . 23 ( 11 ): 1686 - 1696 . http://www.cnki.com.cn/Article/CJFDTotal-ZGTB201811006.htm http://www.cnki.com.cn/Article/CJFDTotal-ZGTB201811006.htm .

J Y WANG , Z Q HOU , W S YU , 等 . Fast TLD visual tracking algorithm with kernel correlation filter . Journal of Image and Graphics , 2018 . 23 ( 11 ): 1686 - 1696 . http://www.cnki.com.cn/Article/CJFDTotal-ZGTB201811006.htm http://www.cnki.com.cn/Article/CJFDTotal-ZGTB201811006.htm .

张晶 , 王旭 , 范洪博 . 时空上下文相似性的TLD目标跟踪算法 . 计算机科学与探索 , 2018 . 12 ( 7 ): 1169 - 1181 . http://www.cqvip.com/QK/93336B/201807/675880708.html http://www.cqvip.com/QK/93336B/201807/675880708.html .

J ZHANG , X WANG , H B FAN . TLD object tracking algorithm based on Spatio-temporal context similarity . Journal of Frontiers of Computer Science and Technology , 2018 . 12 ( 7 ): 1169 - 1181 . http://www.cqvip.com/QK/93336B/201807/675880708.html http://www.cqvip.com/QK/93336B/201807/675880708.html .

王法胜 , 鲁明羽 , 赵清杰 , 等 . 粒子滤波算法 . 计算机学报 , 2014 . 37 ( 8 ): 1679 - 1694 .

F S WANG , M Y LU , Q J ZHAO , 等 . Particle filtering algorithm . Chinese Journal of Computers , 2014 . 37 ( 8 ): 1679 - 1694 .

李志 , 谢强 . 一种基于改进粒子滤波的运动目标跟踪 . 计算机科学 , 2014 . 41 ( 2 ): 232 - 235, 252 . http://qikan.cqvip.com/Qikan/Article/Detail?id=48439241 http://qikan.cqvip.com/Qikan/Article/Detail?id=48439241 .

Z LI , Q XIE . Moving target tracking based on improved particle filter . Computer Science , 2014 . 41 ( 2 ): 232 - 235, 252 . http://qikan.cqvip.com/Qikan/Article/Detail?id=48439241 http://qikan.cqvip.com/Qikan/Article/Detail?id=48439241 .

郭巳秋 , 张涛 , 苗锡奎 . 引入样本删除机制的TLD粒子群目标跟踪 . 光学精密工程 , 2019 . 27 ( 5 ): 1206 - 1217 . http://www.cnki.com.cn/Article/CJFDTotal-GXJM201905024.htm http://www.cnki.com.cn/Article/CJFDTotal-GXJM201905024.htm .

S Q GUO , T ZHANG , X K MIAO . TLD particle swarm optimization target tracking using a sample deletion mechanism . Optics and Precision Engineering , 2019 . 27 ( 5 ): 1206 - 1217 . http://www.cnki.com.cn/Article/CJFDTotal-GXJM201905024.htm http://www.cnki.com.cn/Article/CJFDTotal-GXJM201905024.htm .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Advances in twin network research in visual tracking technology

Single-objective tracking algorithm based on Siamese networks

Design of salience target detection method for RGB depth images

Related Author

HE Zemin

ZENG Juntao

YUAN Baoxi

LIANG Dejian

MIAO Zongcheng

MIAO Zong-cheng

GAO Shi-yan

HE Ze-min

Related Institution

Technological Institute of Materials & Energy Science， Xijing University

Beijing Xinghang Electromechanical Equipment Co. Ltd.

School of Artificial Intelligence， Optics and Electronics， Northwestern Polytechnical University

Xi'an Key Laboratory of Advanced Photo-electronics Materials and Energy Conversion Device， Xijing University

Institute of System Engineering， Academy of Military Sciences

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰