[1]吴慧君,李梅云,杨文元.目标跟踪的尺度参数优化研究[J].南京师范大学学报(自然科学版),2019,42(04):69-76.[doi:10.3969/j.issn.1001-4616.2019.04.010]
　Wu Huijun,Li Meiyun,Yang Wenyuan.Research of Scaling Parameter Optimization for Target Tracking[J].Journal of Nanjing Normal University(Natural Science Edition),2019,42(04):69-76.[doi:10.3969/j.issn.1001-4616.2019.04.010]
点击复制

目标跟踪的尺度参数优化研究()
分享到：

《南京师范大学学报》（自然科学版）[ISSN:1001-4616/CN:32-1239/N]

卷:
第42卷
期数:
2019年04期
页码:
69-76
栏目:
·数学与计算机科学·
出版日期:
2019-12-30

文章信息/Info

Title:
Research of Scaling Parameter Optimization for Target Tracking
文章编号:
1001-4616(2019)04-0069-08
作者:
吴慧君1; 李梅云1; 杨文元2
(1.漳州职业技术学院信息工程学院,福建 漳州 363000)(2.闽南师范大学福建省粒计算及其应用重点实验室,福建 漳州 363000)
Author(s):
Wu Huijun1; Li Meiyun1; Yang Wenyuan2
(1.School of Information Engineering,Zhangzhou Institute of Technology,Zhangzhou 363000,China)(2.Fujian Key Laboratory of Granular Computing and Application,Minnan Normal University,Zhangzhou 363000,China)
关键词:
计算机视觉; 目标跟踪; 相关滤波; 尺度估计; 参数优化
Keywords:
computer vision; target tracking; correlation filtering; scale estimation; parameter optimization
分类号:
TP391.4
DOI:
10.3969/j.issn.1001-4616.2019.04.010
文献标志码:
A
摘要:
鲁棒的尺度判别一直是视频目标跟踪领域中一个富有挑战性的问题.现有的算法在处理复杂图像序列的尺度变化问题时,跟踪速度和精度方面都还有待提升.本文构建两个相关滤波器,加入尺度变换,对目标跟踪的尺度参数进行优化,以提升跟踪速度和精度.首先,构建一维和二维相关滤波器,其中二维位置滤波器实现目标的跟踪以确定目标的位置,一维尺度滤波器对尺度变换进行初步计算得到目标的尺度.然后,组合一维和二维相关滤波器形成三维滤波器,实现最终的目标定位; 最后,分析尺度因子参数的取值对跟踪中的速度、中心位置偏移、位置精度和重叠精度的影
Abstract:
Robust scale estimation has been a challenging problem in target tracking. In handling complex scale variation of the image sequence,existing algorithms have yet to be promoted in tracking speed and tracking precision. We build two related filters and introduce the scale transformation,and optimize the scale parameters of the target tracking,which can enhance the tracking speed and precision. First,this paper constructs a 1-dimensional correlation filter and a 2-dimensional correlation filter,and the 2-dimensional filter realizes the target tracking,determines the location of the object. The evaluation of scale transformation is realized by 1-dimensional filter. Then,the two filters are combined into a 3-dimensional filter to complete the detailed dimension space target positioning. Finally,we analyze the effect of scale factor on the tracking speed,centre location error,distance precision and overlap precision to obtain the optimized value. Experiments are performed on the data set OTB-2015,and the optimized value of target tracking scale parameters are acquired.

参考文献/References:

[1] 毕笃彦,库涛,查宇飞,等. 基于颜色属性直方图的尺度目标跟踪算法研究[J]. 电子与信息学报,2016,38(5):1099-1106.
[2]蔡念,周杨,刘根,等. 鲁棒主成分分析的运动目标检测综述[J]. 中国图象图形学报,2018,21(10):1265-1275.
[3]HENRIQUES J F,CASEIRO R,MARTINS P,et al. High-speed tracking with kernelized correlation filters[J]. IEEE transactions on pattern analysis machine intelligence,2015,37(3):583-596.
[4]YUE Z,NARASIMHA L,PRAMOD T,et al. A robust real-time object detection and tracking system.[J]. Proceedings of SPIE—the international society for optical engineering,2008,6971:697108-1-697108-9.
[5]ROYER L,KRUPA A,DARDENNE G,et al. Real-time target tracking of soft tissues in 3D ultrasound images based on robust visual information and mechanical simulation[J]. Medical image analysis,2017,35:582-598.
[6]HENRIQUES J F,RUI C,MARTINS P,et al. Exploiting the circulant structure of tracking-by-detection with kernels[M]. Computer Vision:ECCV 2012. Berlin Heidelberg:Springer,2012.
[7]高文,朱明,贺柏根,等. 目标跟踪技术综述.[J]. 中国光学,2014,7(3):365-375.
[8]WU Y,LIM J,YANG M H. Online object tracking:a benchmark[C]//The IEEE Conference on Computer Vision & Pattern Recognition(CVPR),Portland,2013:.2411-2418.
[9]WU J,LI J,XIAO C,et al. Real-time robust algorithm for circle object detection:[C]//International Conference for Young Computer Scientists(ICYCS). Zhangjiajie,China. 2008:1722-1727.
[10]陈旭,孟朝晖. 基于深度学习的目标视频跟踪算法综述[J]. 计算机系统应用,2019,28(1):1-9.
[11]DANELLJAN M,KHAN F S,FELSBERG M,et al. Adaptive color attributes for real-time visual tracking[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR),Columbus,OH,USA. 2014:1090-1097.
[12]GUAN M,LI Z,HE R,et al. High speed tracking with a fourier domain kernelized correlation filter[J]. arXiv preprint arXiv:03236,2018.
[13]ZHANG K,ZHANG L,LIU Q,et al. Fast visual tracking via dense spatio-temporal context learning[J]. European Conference on Computer Vision(ECCV),Zurich,Switzerland,2014:127-141.
[14]ZHANG K H,ZHANG L,YANG M H. Real-time object tracking via online discriminative feature selection[J]. IEEE transactions on image processing,2013,22(12):4664-4677.
[15]DING Z,LIU Y,LIU J,et al. Adaptive interacting multiple model algorithm based on information-weighted consensus for maneuvering target tracking[J]. Sensors,2018,18(7):2012-2021.
[16]ZHANG T Z,XU C S,YANG M H. Multi-task correlation particle filter for robust object tracking[C]//The IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Honolulu. HI,USA,2017:4335-4343.
[17]瞿中,赵从梅. 一种抗遮挡的自适应尺度目标跟踪算法[J]. 计算机科学,2018,45(4):296-300.
[18]BOLME D S,BEVERIDGE J R,DRAPER B A,et al. Visual object tracking using adaptive correlation filters[C]//2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR),San Francisco,CA,USA,2010:2544-2550.
[19]纪纲,高富东,范加利. 基于改进的MOSSE相关滤波的目标跟踪[J]. 计算机测量与控制,2018,237(6):244-247.
[20]ZHANG D,MAEI H,WANG X,et al. Deep reinforcement learning for visual object tracking in videos[J]. arXiv preprint arXiv:08936,2017.
[21]LI C,LIU X,SU X,et al. Robust kernelized correlation filter with scale adaption for real-time single object tracking[J]. Journal of real-time image processing,2018,15(4):583-596.
[22]CEHOVIN L,LEONARDIS A,KRISTAN M. Visual object tracking performance measures revisited[J]. IEEE transactions on image processing a publication of the IEEE signal processing society,2016,25(3):1261-1272.
[23]张雷,王延杰,孙宏海,等. 采用核相关滤波器的自适应尺度目标跟踪[J]. 光学精密工程,2016,24(2):448-459.
[24]ZHANG X,WANG Z,XIA G,et al. Accurate object tracking by combining correlation filters and keypoints[C]//International Joint Conference on Neural Networks(IJCNN),Vancouver,BC,Canada,2016:2522-2525.
[25]YANG R,WEI Z. Real-time visual tracking through fusion features[J]. Sensors,2016,16(7):949-958.
[26]李远状,韩彦芳,于书盼. 一种核相关滤波器的多尺度目标跟踪方法[J]. 电子科技,2018,31(10):5-9.
[27]陈倩茹,刘日升,樊鑫. 多相关滤波自适应融合的鲁棒目标跟踪.[J]. 中国图象图形学报,2018,23(2):269-276.
[28]ZHANG T,XU C S,YANG M H. Learning multi-task correlation particle filters for visual tracking[J]. IEEE transactions on pattern analysis and machine intelligence,2018,41(99):365-378.

相似文献/References:

[1]李梦静,吉根林.视频行人重识别研究进展[J].南京师范大学学报(自然科学版),2020,43(02):120.[doi:10.3969/j.issn.1001-4616.2020.02.019]
　Li Mengjing,Ji Genlin.Research Progress on Video-based Person Re-Identification[J].Journal of Nanjing Normal University(Natural Science Edition),2020,43(04):120.[doi:10.3969/j.issn.1001-4616.2020.02.019]

备注/Memo

备注/Memo:
收稿日期:2019-06-25.
基金项目:国家自然科学青年基金项目(61703196)、福建省自然科学基金项目(2018J01549).
通讯联系人:杨文元,博士,副教授,研究生导师,研究方向:计算机视觉与模式识别. E-mail:yangwycn@163.com
更新日期/Last Update: 2019-12-31