[1]董春燕,刘 怀,梁秦嘉,等.自适应特征融合的核相关滤波目标跟踪算法研究[J].南京师范大学学报(工程技术版),2020,20(03):050-56.[doi:10.3969/j.issn.1672-1292.2020.03.009]
　Dong Chunyan,Liu Huai,Liang Qinjia,et al.Kernelized Correlation Filter Tracking AlgorithmBased on Adaptive Feature Fusion[J].Journal of Nanjing Normal University(Engineering and Technology),2020,20(03):050-56.[doi:10.3969/j.issn.1672-1292.2020.03.009]
点击复制

自适应特征融合的核相关滤波目标跟踪算法研究
分享到：

南京师范大学学报（工程技术版）[ISSN:1006-6977/CN:61-1281/TN]

卷:
20卷
期数:
2020年03期
页码:
050-56
栏目:
计算机科学与技术
出版日期:
2020-09-15

文章信息/Info

Title:
Kernelized Correlation Filter Tracking AlgorithmBased on Adaptive Feature Fusion
文章编号:
1672-1292(2020)03-0050-07
作者:
董春燕; 刘 怀; 梁秦嘉; 梁 磊
南京师范大学电气与自动化工程学院,江苏 南京 210023
Author(s):
Dong Chunyan; Liu Huai; Liang Qinjia; Liang Lei
School of Electrical and Automation Engineering,Nanjing Normal University,Nanjing 210023,China
关键词:
目标跟踪; 核相关滤波; 特征融合; 模型更新
Keywords:
object tracking; kernelized correlation filter; feature fusion; model update
分类号:
TP391
DOI:
10.3969/j.issn.1672-1292.2020.03.009
文献标志码:
A
摘要:
在核相关滤波目标跟踪算法中,为了克服采用单一特征导致的特征表达不足,以及采用线性插值模型更新策略造成模型漂移的问题,提出了一种自适应特征融合和模型更新的核相关滤波目标跟踪算法. 首先使用主成分分析法对方向梯度直方图特征和颜色名特征进行降维,以提高算法的运行速度; 其次计算两种特征的响应图,用所得响应图的峰值与平均峰值相关能量值的乘积来计算响应图权重,实现响应图的加权融合,从而获得目标位置; 最后根据两帧间颜色名特征的相似度调整模型更新速率. 在OTB-50数据集上的实验结果分析表明,该算法跟踪性能优于其他算法,能够提高处理速度.
Abstract:
In the kernelized correlation filter object tracking algorithm,the use of mere histograms of oriented gradients(HOG)feature can easily cause insufficient feature expression. In addition,the linear interpolation model updating strategy used in this algorithm can easily cause model drift. To solve these problems,an improved kernelized correlation filter tracking algorithm based on adaptive feature fusion and model updating is proposed in this paper. Firstly,PCA is applied to reduce the dimension of HOG feature and color name(CN)feature to improve the speed of the algorithm. Secondly,the response maps of the two dimensionality reduction features are calculated independently. After that,the product of the peak value and the average peak-to-correlation energy(APCE)of two response maps are used to obtain their weights so that we can use weights to obtain the fused response map. Finally,the model updating rate is determined according to the similarity of CN feature between the two frames. Qualitative and quantitative analysis of experimental results on the OTB-50 dataset show that the tracking performance of the proposed algorithm is superior to that of other tracking algorithms and it can ensure the real-time performance.

参考文献/References:

[1] 卢湖川,李佩霞,王栋. 目标跟踪算法综述[J]. 模式识别与人工智能,2018,31(1):61-76.
[2]VOJIR T,NOSKOVA J,MATAS J. Robust scale-adaptive mean-shift for tracking[J]. Pattern Recognition Letters,2014,49:250-258.
[3]ZHANG T Z,XU C S,YANG M H. Learning multi-task correlation particle filters for visual tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2019,41(2):365-378.
[4]KALAL Z,MIKOLAJCZYK K,MATAS J. Tracking-learning-detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(7):1409-1422.
[5]HARE S,GOLODETZ S,SAFFARI A,et al. Struck:structured output tracking with kernels[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(10):2096-2109.
[6]张惊雷,时鹏,温显斌. 基于尺度自适应均值偏移优化的TLD跟踪算法[J]. 控制与决策,2019,34(1):144-150.
[7]CHI Z,LI H,LU H,et al. Dual deep network for visual tracking[J]. IEEE Transactions on Image Processing,2017,26(4):2005-2015.
[8]GORDON D,FARHADI A,FOX D. Re3:real-time recurrent regression networks for visual tracking of generic objects[J]. IEEE Robotics and Automation Letters,2018,3(2):788-795.
[9]WANG Q,ZHANG L,BERTINETTO L,et al. Fast online object tracking and segmentation:a unifying approach[C]//IEEE Conference on Computer Vision and Pattern Recognition. Los Angeles:IEEE,2019:1328-1338.
[10]BOLME D S,BEVERIDGE J R,DRAPER B A,et al. Visual object tracking using adaptive correlation filters[C]//IEEE Conference on Computer Vision and Pattern Recognition. San Francisco:IEEE,2010:2544-2550.
[11]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. Singapore:IEEE,2012:702-715.
[12]HENRIQUES J F,CASEIRO R,MARTINS P,et al. High-speed tracking with kernelized correlation filters[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(3):583-596.
[13]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:IEEE,2014:1090-1097.
[14]BERTINETTO L,VALMADRE J,GOLODETZ S,et al. Staple:complementary learners for real-time tracking[C]//IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas:IEEE,2016:1401-1409.
[15]茅正冲,陈海东. 基于核相关滤波的长期目标跟踪算法[J]. 激光与光电子学进展,2019,56(1):94-101.
[16]ASHA C S,NARASIMHADHAN A V. Adaptive learning rate for visual tracking using correlation filters[J]. Procedia Computer Science,2016,89:614-622.
[17]陈智,柳培忠,骆炎民,等. 自适应特征融合的多尺度相关滤波目标跟踪算法[J]. 计算机辅助设计与图形学学报,2018,30(11):2063-2073.
[18]WANG M,LIU Y,HUANG Z. Large margin object tracking with circulant feature maps[C]//IEEE Conference on Computer Vision and Pattern Recognition. Honolulu:IEEE,2017:4800-4808.
[19]SINGH G,CHHABRA I. Effective and fast face recognition system using complementary OC-LBP and HOG feature descriptors with SVM classifier[J]. Journal of Information Technology Research,2018,11(1):91-110.
[20]DANELLJAN M,H?GER G,KHAN F S,et al. Discriminative scale space tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(8):1561-1575.
[21]WU Y,LIM J,YANG M H. Object tracking benchmark[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1834-1848.

相似文献/References:

[1]沈世斌,谢 非,牛友臣,等.基于混合高斯模型优化的运动人体跟踪方法[J].南京师范大学学报(工程技术版),2019,19(01):051.[doi:10.3969/j.issn.1672-1292.2019.01.007]
　Shen Shibin,Xie Fei,Niu Youchen,et al.A Moving Human Body Tracking Method Based onOptimized Gaussian Mixture Model[J].Journal of Nanjing Normal University(Engineering and Technology),2019,19(03):051.[doi:10.3969/j.issn.1672-1292.2019.01.007]
[2]黄戌霞,林淑彬.迁移学习融合双HOG特征的目标跟踪[J].南京师范大学学报(工程技术版),2022,22(04):029.[doi:10.3969/j.issn.1672-1292.2022.04.004]
　Huang Xuxia,Lin Shubin.Object Tracking Based on Transfer Learning Fusion of Dual HOG Feature[J].Journal of Nanjing Normal University(Engineering and Technology),2022,22(03):029.[doi:10.3969/j.issn.1672-1292.2022.04.004]
[3]董春燕,刘 怀,梁秦嘉.基于核相关滤波的TLD跟踪算法的研究[J].南京师范大学学报(工程技术版),2020,20(04):037.[doi:10.3969/j.issn.1672-1292.2020.04.006]
　Dong Chunyan,Liu Huai,Liang Qinjia.TLD Object Tracking Algorithm Based on Kernelized Correlation Filter[J].Journal of Nanjing Normal University(Engineering and Technology),2020,20(03):037.[doi:10.3969/j.issn.1672-1292.2020.04.006]

备注/Memo

备注/Memo:
收稿日期:2019-05-21.
基金项目:国家自然科学基金项目(61603194).
通讯作者:刘怀,博士,副教授,研究方向:数字图像处理、实时控制系统. E-mail:liuhuai@njnu.edu.cn
更新日期/Last Update: 2020-09-15