首页 > 论文 > 光学学报 > 38卷 > 10期(pp:1015002--1)

稳健的双模型自适应切换实时跟踪算法

Robust Real-Time Visual Tracking via Dual Model Adaptive Switching

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

为提升卷积特征目标跟踪算法的实时性和稳健性,利用不同卷积层特征对不同目标表征能力不同的特性,提出双模型自适应切换的实时跟踪方法。该方法对选取的两个卷积层特征使用目标区域和跟踪搜索区域卷积特征的能量均值比来评估卷积特征,选择能量均值比大于给定阈值的卷积通道特征来训练两个相关滤波分类器,然后利用目标相关滤波响应图的峰旁比自适应切换两个相关滤波分类器来预测目标位置,最后采用稀疏模型更新策略来更新分类器。在标准数据集上进行算法测试,实验结果表明,本文算法平均距离精度为89.3%,接近连续卷积跟踪算法,平均跟踪速度为25.8 frams/s,是连续卷积跟踪算法的25倍,整体性能优于实验中的对比跟踪算法。

Abstract

In order to improve the real-time and robust performances of the convolutional features for visual tracking, a real-time tracking method of dual model adaptive switching is proposed based on the analysis of different convolution layer features for different object representation capabilities. This method utilizes the feature energy ratio of the object region and searches region to evaluate the features selected from two convolutional layers. The convolution channel whose energy ratio value is greater than the given threshold is selected to train two correlated filter classifiers. Consequently, the object position is predicted by switching correlation filter classifiers using the peak-to-sidelobe ratio of response map adaptively. Finally, the sparse model update strategy is applied to update the classifiers. The proposed algorithm is tested on the standard dataset. The experimental results show that the average distance accuracy of proposed algorithm is 89.3%, which is close to continuous convolution object tracking, and the average tracking speed is 25.8 frame/s, which is 25 times faster than the continuous convolution object tracking algorithm. The overall performance of the proposed algorithm outperforms other tracking methods contrasted in the experiment.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.4

DOI:10.3788/aos201838.1015002

所属栏目:机器视觉

基金项目:国家重点研发计划(2017YFC0821102)

收稿日期:2018-04-12

修改稿日期:2018-05-09

网络出版日期:2018-05-25

作者单位    点击查看

熊昌镇:城市道路交通智能控制技术北京市重点实验室, 北京 100144
车满强:城市道路交通智能控制技术北京市重点实验室, 北京 100144
王润玲:北方工业大学理学院, 北京 100144
卢颜:城市道路交通智能控制技术北京市重点实验室, 北京 100144

联系人作者:熊昌镇(xczkiong@163.com)

【1】Bolme D S, Beveridge J R, Draper B A, et al. Visual object tracking using adaptive correlation filters[C]∥ 2010 IEEE Conference on Computer Vision and Pattern Recognition, 2010: 2544-2550.

【2】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, 2012: 702-715.

【3】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.

【4】Danelljan M, Hager G, Shahbaz Khan F, et al. Learning spatially regularized correlation filters for visual tracking[C]∥Proceedings of the IEEE International Conference on Computer Vision, 2015: 4310-4318.

【5】Danelljan M, Shahbaz Khan F, Felsberg M, et al. Adaptive color attributes for real-time visual tracking[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014: 1090-1097.

【6】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, 2016: 472-488.

【7】Danelljan M, Bhat G, Khan F S, et al. ECO: efficient convolution operators for tracking[C]∥IEEE Conference on Computer Vision and Pattern Recognition, 2017: 6931-6939.

【8】Xiong C, Zhao L, Guo F. Kernelized correlation filters tracking based on adaptive feature fusion[J]. Journal of Computer-Aided Design & Computer Graphics, 2017, 29(6): 1068-1074.
熊昌镇, 赵璐璐, 郭芬红. 自适应特征融合的核相关滤波跟踪算法[J]. 计算机辅助设计与图形学学报, 2017, 29(6): 1068-1074.

【9】Bertinetto L, Valmadre J, Golodetz S, et al. Staple: complementary learners for real-time tracking[C]∥ Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 1401-1409.

【10】Ma C, Huang J B, Yang X, et al. Hierarchical convolutional features for visual tracking[C]∥ Proceedings of the IEEE International Conference on Computer Vision, 2015: 3074-3082.

【11】Huang C, Lucey S, Ramanan D. Learning policies for adaptive tracking with deep feature cascades[C]∥ IEEE International Conference on Computer Vision, 2017: 105-114.

【12】Wang L, Ouyang W, Wang X, et al. Visual tracking with fully convolutional networks[C]∥Proceedings of the IEEE International Conference on Computer Vision, 2015: 3119-3127.

【13】Ma C, Huang J B, Yang X, et al. Adaptive correlation filters with long-term and short-term memory for object tracking[J]. International Journal of Computer Vision, 2018, 126(8): 771-796.

【14】Wang Y C, Huang H, Li S M, et al. Correlation filter tracking based on online detection and scale-adaption[J]. Acta Optica Sinica, 2018, 38(2): 0215002.
王艳川, 黄海, 李邵梅, 等. 基于在线检测和尺度自适应的相关滤波跟踪[J]. 光学学报, 2018, 38(2): 0215002.

【15】Ma C, Huang J B, Yang X, et al. Robust visual tracking via hierarchical convolutional features[J]. arXiv, 2017: 1707. 03816.

【16】Song Y, Ma C, Gong L, et al. Crest: convolutional residual learning for visual tracking[C]∥IEEE International Conference on Computer Vision, 2017: 2574-2583.

【17】Danelljan M, Hger G, Khan F, et al. Accurate scale estimation for robust visual tracking[C]∥British Machine Vision Conference, 2014: 1-11.

【18】Pan Z F, Zhu Y L. Kernelized correlation filters object tracking method with multi-scale estimation[J]. Laser & Optoelectronics Progress, 2016, 53(10): 101501.
潘振福, 朱永利. 多尺度估计的核相关滤波器目标跟踪方法[J]. 激光与光电子学进展, 2016, 53(10): 101501.

【19】Wang X, Hon Z Q, Yu W S, et al. Target scale adaptive robust tracking based on fusion of multilayer convolutional features[J]. Acta Optica Sinica, 2017, 37(11): 1115005.
王鑫, 侯志强, 余旺盛, 等. 基于多层卷积特征融合的目标尺度自适应稳健跟踪[J]. 光学学报, 2017, 37(11): 1115005.

【20】Galoogahi H K, Fagg A, Lucey S. Learning background-aware correlation filters for visual tracking[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 1135-1143.

【21】Ma C, Yang X, Zhang C, et al. Long-term correlation tracking[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015: 5388-5396.

【22】Zhao G P, Shen Y P, Wang J Y. Adaptive feature fusion object tracking based on circulant structure with kernel[J]. Acta Optica Sinica, 2017, 37(8): 0815001.
赵高鹏, 沈玉鹏, 王建宇. 基于核循环结构的自适应特征融合目标跟踪[J]. 光学学报, 2017, 37(8): 0815001.

【23】Wang X, Li H, Li Y, et al. Robust and real-time deep tracking via multi-scale domain adaptation[J]. arXiv, 2017: 1701.00561.

【24】Cai Y Z, Yang D D, Mao N, et al. Visual tracking based on adaptive convolutional features[J]. Acta Optica Sinica, 2017, 37(3): 0315002.
蔡玉柱, 杨德东, 毛宁, 等. 基于自适应卷积特征的目标跟踪算法[J]. 光学学报, 2017, 37(3): 0315002.

【25】Held D, Thrun S, Savarese S. Learning to track at 100 fps with deep regression networks[C]∥European Conference on Computer Vision, 2016: 749-765.

【26】Li Y, Zhu J K, Hoi S C H. Reliable patch trackers: Robust visual tracking by exploiting reliable patches[C]∥ Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015: 353-361.

【27】Wang M, Liu Y, Huang Z. Large margin object tracking with circulant feature maps[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 4800-4808.

【28】Qi Y K, Zhang S P, Qin L, et al. Hedged deep tracking[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 4303-4311.

引用该论文

Xiong Changzhen,Che Manqiang,Wang Runling,Lu Yan. Robust Real-Time Visual Tracking via Dual Model Adaptive Switching[J]. Acta Optica Sinica, 2018, 38(10): 1015002

熊昌镇,车满强,王润玲,卢颜. 稳健的双模型自适应切换实时跟踪算法[J]. 光学学报, 2018, 38(10): 1015002

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF