连续域卷积操作跟踪算法的改善

王鑫; 李玉芳; 宋策; 韩松伟

doi:10.3788/YJYXS20193411.1115

您当前的位置：

首页 >

文章列表页 >

连续域卷积操作跟踪算法的改善

图像处理 | 更新时间：2020-07-05

- 连续域卷积操作跟踪算法的改善
- Algorithm improvement strategy about continuous convolution operators for visual tracking
- 液晶与显示 2019年34卷第11期页码：1115-1123
- 作者机构：
  
  1.中国科学院长春光学精密机械与物理研究所, 吉林长春 130033
  2.中国第一汽车集团有限公司研发总院, 吉林长春 130013
- 作者简介：
  
  [ "王鑫(1993-), 男, 黑龙江绥化人, 硕士, 2016年于哈尔滨工业大学获得硕士学位, 主要从事图像跟踪方面的研究。E-mail:14S104020@hit.edu.cn" ]
- 基金信息：
- DOI：10.3788/YJYXS20193411.1115
  中图分类号： TP391.4
- 收稿日期：2019-04-09，
  
  录用日期：2019-9-11，
  
  纸质出版日期：2019-11-05
- 稿件说明：
移动端阅览
王鑫, 李玉芳, 宋策, 等. 连续域卷积操作跟踪算法的改善[J]. 液晶与显示, 2019,34(11):1115-1123.

Xin WANG, Yu-fang LI, Ce SONG, et al. Algorithm improvement strategy about continuous convolution operators for visual tracking[J]. Chinese journal of liquid crystals and displays, 2019, 34(11): 1115-1123.
王鑫, 李玉芳, 宋策, 等. 连续域卷积操作跟踪算法的改善[J]. 液晶与显示, 2019,34(11):1115-1123. DOI： 10.3788/YJYXS20193411.1115.

Xin WANG, Yu-fang LI, Ce SONG, et al. Algorithm improvement strategy about continuous convolution operators for visual tracking[J]. Chinese journal of liquid crystals and displays, 2019, 34(11): 1115-1123. DOI： 10.3788/YJYXS20193411.1115.

摘要

针对连续域卷积操作跟踪算法中存在的计算复杂问题和过拟合问题，提出一种降维卷积因式分解方法和一个紧凑衍生模型。本文选取连续域卷积操作跟踪算法中的部分特征通道、因式分解卷积算子，并结合高斯-牛顿法和共轭梯度迭代求取降维矩阵和分类器，以达到降低系统的计算复杂程度的目的。选取服从高斯分布的若干样本，结合联和概率密度函数及混合高斯分布模型，构建一个更具代表性的紧凑衍生模型，既能降低过拟合出现的风险又能保证样本的多样性。通过降低模型更新频率，减少计算复杂度，同时降低模型漂移发生的概率。经实验验证，本文基于四类标准数据集获得的跟踪性能曲线积分比连续域卷积操作跟踪算法最少高出0.8%，最多高出13%。结果表明，降维卷积因式分解法和紧凑衍生模型可以有效地提升系统跟踪性能。

Abstract

The reduced dimensional factorized convolution method and the compact generative model (RFCG) are proposed in order to solve the computational complexity and over-fitting problems in the continuous convolution operators for visual tracking(C-COT). Some feature channels in the C-COT are selected in advance

then the convolution operator is factorized

and the reduced dimension matrix and filter are obtained by combining Gauss-Newton method and conjugate gradient iteration (CG)

so as to reduce the computational complexity of the system in this paper. A number of samples subject to the Gaussian distribution are selected and combined with the joint probability density function and the mixed Gaussian distribution model to build a compact generative model with stronger representativeness. The risk of the over-fitting problems can be reduced and the diversity of samples can be guaranteed in this way. Finally

the model updating frequency is reduced to save the calculation time and avoid the drift of the model. Experimental results show that the area under the tracking performance curve (AUC) score of the improved algorithm based on four benchmarks achieves at least 0.8% higher than C-COT

and 13% higher at most. This shows that the RFCG can effectively improve the tracking performance of the system.

关键词

Keywords

references

DANELLJAN M, KHAN F S, FELSBERG M, et al . Adaptive color attributes for real-time visual tracking[C]// Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition . Columbus, OH, USA: IEEE, 2014. https://www.researchgate.net/publication/286593879_Adaptive_Color_Attributes_for_Real-Time_Visual_Tracking

GALOOGAHI H K, SIM T, LUCEY S. Multi-channel correlation filters[C]// Proceedings of 2013 IEEE International Conference on Computer Vision . Sydney, NSW, Australia: IEEE, 2014. https://ieeexplore.ieee.org/document/6751493

WANG R L, ZOU J C, CHE M Q, et al . Robust and real-time visual tracking based on single-layer convolutional features and accurate scale estimation[C]// Proceedings of the 13th Conference on Image and Graphics Technologies and Applications . Beijing, China: Springer, 2018: 471-482.

DANELLJAN M, HÄGER G, KHAN F S, et al . Discriminative scale space tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2017, 39(8):1561-1575.

BIBI A, MUELLER M, GHANEM B. Target Response Adaptation for Correlation Filter Tracking[M].LEIBE B, MATAS J, SEBE N, et al . Computer Vision-ECCV 2016 . Cham: Springer, 2016.

DANELLJAN M, HÄGER G, KHAN F S, et al . Adaptive decontamination of the training set: a unified formulation for discriminative visual tracking[C]// Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition . Las Vegas, NV, USA: IEEE, 2016. https://www.researchgate.net/publication/308361660_Adaptive_Decontamination_of_the_Training_Set_A_Unified_Formulation_for_Discriminative_Visual_Tracking?ev=prf_high

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.

DANELLJAN M, HÄGER G, KHAN F S, et al . Learning spatially regularized correlation filters for visual tracking[C]// Proceedings of 2015 IEEE International Conference on Computer Vision . Santiago, Chile: IEEE, 2016.

GALOOGAHI H K, SIM T, LUCEY S. Correlation filters with limited boundaries[C]// Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition . Boston, MA, USA: IEEE, 2015. https://ieeexplore.ieee.org/document/7299094

BOLME D S, BEVERIDGE J R, DRAPER B A, et al . Visual object tracking using adaptive correlation filters[C]// Proceedings of 2010 IEEE Computer Society IEEE Conference on Computer Vision and Pattern Recognition . San Francisco, CA, USA: IEEE, 2010. https://ieeexplore.ieee.org/document/5539960

DANELLJAN M, ROBINSON A, KHAN F S, et al . Beyond correlation filters: learning continuous convolution operators for visual tracking[C]// Proceedings of the 14th European Conference on Computer Vision . Amsterdam, The Netherlands: Springer, 2016. https://link.springer.com/chapter/10.1007%2F978-3-319-46454-1_29

KRISTAN M, LEONARDIS A, MATAS J, et al . The Visual Object Tracking VOT2016 Challenge Results[M].HUA G, JÉGOU H. Computer Vision-ECCV 2016 Workshops . Cham: Springer, 2016.

MUELLER M, SMITH N, GHANEM B. A benchmark and simulator for UAV tracking[C]// Proceedings of the 14th European Conference on Computer Vision . Amsterdam, The Netherlands: Springer, 2016: 445-461. https://link.springer.com/chapter/10.1007%2F978-3-319-46448-0_27

WU Y, LIM J, YANG M H. Object tracking benchmark[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2015, 37(9):1834-1848.

LIANG P P, BLASCH E, LING H B. Encoding color information for visual tracking:algorithms and benchmark[J]. IEEE Transactions on Image Processing , 2015, 24(12):5630-5644.

DAM N, NGUYEN V T, DO M N, et al . Realtime Face Verification with Lightweight Convolutional Neural Networks[M].BEBIS G, BOYLE R, PARVIN B, et al . Advances in Visual Computing . Cham: Springer, 2015.

DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]// Proceedings of 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition . San Diego, CA, USA: IEEE, 2005. https://ieeexplore.ieee.org/document/1467360

VAN DE WEIJER J, SCHMID C, VERBEEK J, et al . Learning color names for real-world applications[J]. IEEE Transactions on Image Processing , 2009, 18(7):1512-1523.

FELSBERG M, BERG A, HAGER G, et al . The thermal infrared visual object tracking VOT-TIR2015 challenge results[C]// Proceedings of 2015 IEEE International Conference on Computer Vision Workshop . Santiago, Chile: IEEE, 2015.

KALAL Z, MATAS J, MIKOLAJCZYK K. P-N learning: bootstrapping binary classifiers by structural constraints[C]// Proceedings of 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition . San Francisco, CA, USA: IEEE, 2010. https://www.researchgate.net/publication/224164394_P-N_Learning_Bootstrapping_Binary_Classifiers_by_Structural_Constraints

HARE S, SAFFARI A, TORR P H S. Struck: structured output tracking with kernels[C]// Proceedings of 2011 International Conference on Computer Vision . Barcelona, Spain: IEEE, 2011.

GAO J, LING H B, HU W M, et al . Transfer learning based visual tracking with Gaussian processes regression[C]// Proceedings of the 13th European Conference on Computer Vision . Zurich, Switzerland: Springer, 2014. https://link.springer.com/chapter/10.1007/978-3-319-10578-9_13

LI Y, ZHU J K. A scale adaptive kernel correlation filter tracker with feature integration[C]// Proceedings of the European Conference on Computer Vision . Zurich, Switzerland: Springer, 2014.

ZHANG J M, MA S G, SCLAROFF S. MEEM: robust tracking via multiple experts using entropy minimization[C]// Proceedings of the 13th European Conference on Computer Vision . Zurich, Switzerland: Springer, 2014. https://link.springer.com/chapter/10.1007%2F978-3-319-10599-4_13

POSSEGGER H, MAUTHNER T, BISCHOF H. In defense of color-based model-free tracking[C]// Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition . Boston, MA, USA: IEEE, 2015. https://ieeexplore.ieee.org/document/7298823

MA C, YANG X K, ZHANG C Y, et al . Long-term correlation tracking[C]// Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition . Boston, MA, USA: IEEE, 2015.

MA C, HUANG J B, YANG X K, et al . Hierarchical convolutional features for visual tracking[C]// Proceedings of 2015 IEEE International Conference on Computer Vision . Santiago, Chile: IEEE, 2015. https://ieeexplore.ieee.org/document/7410709?arnumber=7410709

DECLERCQ A, PIATER J H. On-line simultaneous learning and tracking of visual feature graphs[C]// Proceedings of 2007 IEEE Conference on Computer Vision and Pattern Recognition . Minneapolis, MN, USA: IEEE, 2007. https://ieeexplore.ieee.org/document/4270433

HONG J H, FITZGIBBON A. Secrets of matrix factorization: approximations, numerics, manifold optimization and random restarts[C]// Proceedings of 2015 IEEE International Conference on Computer Vision . Santiago, Chile: IEEE, 2015. https://ieeexplore.ieee.org/document/7410827?arnumber=7410827

DANELLJAN M, HÄGER G, KHAN F S, et al . Convolutional features for correlation filter based visual tracking[C]// Proceedings of 2015 IEEE International Conference on Computer Vision Workshop . Santiago, Chile: IEEE, 2015. https://ieeexplore.ieee.org/document/7406433?arnumber=7406433

BERTINETTO L, VALMADRE J, GOLODETZ S, et al . Staple: complementary learners for real-time tracking[C]// Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition . Las Vegas, NV, USA: IEEE, 2016. https://ieeexplore.ieee.org/document/7780525

NAM H, HAN B. Learning multi-domain convolutional neural networks for visual tracking[C]// Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition . Las Vegas, NV, USA: IEEE, 2016. https://ieeexplore.ieee.org/document/7780834

BERTINETTO L, VALMADRE J, HENRIQUES J F, et al . Fully-convolutional Siamese networks for object tracking[C]// Proceedings of the European Conference on Computer Vision . Amsterdam, The Netherlands: Springer, 2016. https://link.springer.com/chapter/10.1007/978-3-319-48881-3_56

NAM H, BAEK M, HAN B. Modeling and propagating CNNs in a tree structure for visual tracking[J]. arXiv preprint arXiv : 1608 . 07242 , 2016. https://www.researchgate.net/publication/306885463_Modeling_and_Propagating_CNNs_in_a_Tree_Structure_for_Visual_Tracking

闫辉, 许廷发, 吴青青, 等.多特征融合匹配的多目标跟踪[J].中国光学, 2013, 6(2):163-170.

YAN H, XU T F, WU Q Q, et al . Multi-object tracking based on multi-feature joint matching[J]. Chinese Optics , 2013, 6(2):163-170. (in Chinese)

王铭明, 陈涛, 王建立, 等. Mean-shift跟踪算法及其在光电跟踪系统中的应用[J].中国光学, 2014, 7(2):332-338.

WANG M M, CHEN T, WANG J L, et al . Mean-shift tracking algorithm and its application in optoelectronic tracking system[J]. Chinese Optics , 2014, 7(2):332-338. (in Chinese)

江山, 张锐, 韩广良, 等.复杂背景灰度图像下的多特征融合运动目标跟踪[J].中国光学, 2016, 9(3):320-328.

JIANG S, ZHANG R, HAN G L, et al . Moving object tracking based on multi-feature fusion in the complex background gray image[J]. Chinese Optics , 2016, 9(3):320-328. (in Chinese)

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据