浏览全部资源
扫码关注微信
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.中国科学院大学,北京 100049
[ "朱均安(1992-),男,湖北黄冈人,博士研究生,2015年于东北大学获得学士学位,主要从事目标检测、识别与跟踪方面的研究。E-mail:zhujunan15@mails.ucas.edu.cn" ]
[ "陈 涛(1965-),男,内蒙古赤峰人,博士,研究员,博士生导师,2007年于中科院长春光学精密机械与物理研究所获得博士学位,主要从事光电精密跟踪测量技术的研究。E-mail:chent@ciomp.ac.cn" ]
收稿日期:2020-07-13,
修回日期:2020-09-08,
纸质出版日期:2021-02-15
移动端阅览
朱均安,陈涛,曹景太.基于显著性区域加权的相关滤波目标跟踪[J].光学精密工程,2021,29(02):363-373.
ZHU Jun-an,CHEN Tao,CAO Jing-tai.Salient region weighted correlation filter for object tracking[J].Optics and Precision Engineering,2021,29(02):363-373.
朱均安,陈涛,曹景太.基于显著性区域加权的相关滤波目标跟踪[J].光学精密工程,2021,29(02):363-373. DOI: 10.37188/OPE.20212902.0363.
ZHU Jun-an,CHEN Tao,CAO Jing-tai.Salient region weighted correlation filter for object tracking[J].Optics and Precision Engineering,2021,29(02):363-373. DOI: 10.37188/OPE.20212902.0363.
为了提高跟踪过程中目标位置的定位精度,提出了基于显著性区域加权的相关滤波目标跟踪算法。本文在高效卷积算子跟踪算法(Efficient Convolution Operators for Tracking,ECO)的跟踪框架基础上,首先采用预训练的改进残差网络SE-ResNet来提取不同层的多分辨率特征,充分利用浅层和深层特征的不同特性来增强特征表达,通过因式分解的卷积求出相关滤波的响应图;然后采用背景对像模型来获取目标的显著性图,并使用显著性图来对相关滤波的响应图进行加权,提高定位精度;最后,在视觉目标跟踪(Visual Object Tracking,VOT)竞赛上与8种流行的跟踪算法进行对比,在VOT2016和VOT2017竞赛上的平均重叠期望(Expected Average Overlap,EAO)得分分别达到了0.415 7和0.341 2,均优于其他算法。实验表明本算法可以有效提升目标跟踪中的定位精度,改善跟踪性能。
To improve the positioning accuracy of target positions in object tracking, an object tracking algorithm based on a salient region weighted correlation filter is proposed in this study. Using the tracking framework of efficient convolution operators (ECO) for tracking, we first apply SE-ResNet, which is a pre-trained improved residual network, to extract the multi-resolution features of different layers and fully utilize the different characteristics of the shallow and deep features to enhance feature expression. Next, a background object model is used to obtain a saliency map of the target. The saliency map is then applied to weight the response map of the correlation filter to improve positioning accuracy. Finally, compared with eight popular tracking algorithms employed at the Visual Object Tracking (VOT) challenge, the expected average overlap scores of VOT2016 and VOT2017 are determined to be 0.415 7 and 0.341 2, respectively, which are better than those of the other algorithms. Experimental results show that the proposed algorithm can effectively improve positioning accuracy and tracking performance.
KRISTAN M , LEONARDIS A , MATAS J , et al .. The visual object tracking VOT2016 challenge results [C]. Europeon Conference on Computer Vision , 2016 : 777 - 823 .
KRISTAN M , LEONARDIS A , MATAS J , et al . . The visual object tracking VOT2017 challenge results [J]. IEEE International Conference on Computer Vision , 2017 : 1949 - 1972 .
COLLINS R T . Mean-shift blob tracking through scale space [C]. Internaltional Conference on Computer Vision and Pattern Recogintion , 2003 : 234 - 240 .
董超 , 郑兵 , 李彬 , 等 . 改进核相关滤波器的海上船只目标跟踪 [J]. 光学 精密工程 , 2019 , 27 ( 4 ): 911 - 921 .
DONG CH , ZHENG B , LI B , et al . . Ship target tracking with improved kernelized correlation filters [J]. Opt. precision Eng. , 2019 , 27 ( 4 ): 911 - 921 . (in Chinese)
刘教民 , 郭剑威 , 师硕 . 自适应模板更新和目标重定位的相关滤波器跟踪 [J]. 光学 精密工程 , 2018 , 26 ( 8 ): 270 - 281 .
LIU J M , GUO J W , SHI SH . Correlation filter tracking based on adaptive learning rate and location refiner [J]. Opt. precision Eng. , 2018 , 26 ( 8 ): 2100 - 2111 . (in Chinese)
张博 , 江沸菠 , 刘刚 . 利用视觉显著性和扰动模型的上下文感知跟踪 [J]. 光学 精密工程 , 2018 , 26 ( 8 ): 282 - 291 .
ZHANG B , JIANG F B , LIU G . Context-aware tracking based on a visual saliency and perturbation model [J]. Opt. precision Eng. , 2018 , 26 ( 8 ): 2112 - 2121 . (in Chinese)
梁慧慧 , 何秋生 , 贾伟振 , 等 . 一种多特征融合的目标跟踪算法 [J]. 液晶与显示 , 2020 , 35 ( 6 ): 583 - 594 .
LIANG H H , HE Q SH , JIA W ZH , et al . . Multi-feature fusion target tracking algorithm [J]. Chinese Journal of Liquid Crystals and Displays , 2020 , 35 ( 6 ): 583 - 594 . (in Chinese)
韩亚君 , 杨德东 , 李勇 , 等 . 基于多特征融合相关滤波的红外目标跟踪 [J]. 液晶与显示 , 2019 , 34 ( 2 ): 177 - 187 .
HAN Y J , YANG D D , LI Y , et al . . Infrared target tracking based on correlation filter with multi-features fusion [J]. Chinese Journal of Liquid Crystals and Displays , 2019 , 34 ( 2 ): 177 - 187 . (in Chinese)
BOLME D , BEVERIDGE J R , DRAPER B A , et al .. Visual object tracking using adaptive correlation filters [C]. Internaltional Conference on Computer Vision and Pattern Recogintion . IEEE , 2010 : 2544 - 2550 .
HENRIQUES J F , CASEIRO R , MARTINS P , et al .. Exploiting the circulant structure of tracking-by-detection with kernels [C]. Europeon Conference on Computer Vision , 2012 : 702 - 715 .
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 : 583 - 596 .
DANELLJAN M , HAGER G , KHAN F S , et al . . Discriminative scale space tracking [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2017 , 39 : 1561 - 1575 .
LI Y , ZHU J . A scale adaptive kernel correlation filter tracker with feature integration [C]. Europeon Conference on Computer Vision , 2014 : 254 - 265 .
DANELLJAN M , HAGER G , KHAN F S , et al . . Learning spatially regularized correlation filters for visual tracking [J]. IEEE International Conference on Computer Vision , 2015 : 4310 - 4318 .
DANELLJAN M , ROBINSON A , KHAN F S , et al .. Beyond correlation filters: Learning continuous convolution operators for visual tracking [C]. Europeon Conference on Computer Vision , 2016 : 472 - 488 .
BERTINETTO L , VALMADRE J , GOLODETZ S , et al . . Staple: Complementary learners for real-time tracking [J]. Internaltional Conference on Computer Vision and Pattern Recogintion , 2016 , ( 12 ): 1401 - 1409 .
DALAL N , TRIGGS B . Histograms of oriented gradients for human detection [C]. Internaltional Conference on Computer Vision and Pattern Recogintion , 2005 : 886 - 893 .
DANELLJAN M , BHAT G , SHAHBAZ KHAN F , et al . . ECO: Efficient convolution operators for tracking [J]. IEEE Conference on Computer Vision and Pattern Recognition , 2017 : 6931 - 6939 .
HU J , SHEN L , SUN G . Squeeze and excitation networks [J]. IEEE Conference on Computer Vision and Pattern Recognition , 2018 : 7132 - 7141 .
POSSEGGER H , MAUTHNER T , BISCHOF H . In defense of color-based model-free tracking [C]. Internaltional Conference on Computer Vision and Pattern Recogintion , 2015 : 2113 - 2120 .
DANELLJAN M , KHAN F S , FELSBERG M , et al . . Adaptive color attributes for real-time visual tracking [J]. Internaltional Conference on Computer Vision and Pattern Recogintion , 2014 : 1090 - 1097 .
YOSINSKI J , CLUNE J , NGUYEN A , et al . . Understanding neural networks through deep visualization [J]. arXiv preprint arXiv: 1506 . 06579 , 2015 .
GAO P , ZHANG Q , WANG F , et al . . Learning reinforced attentional representation for end to end visual tracking [J]. Information Sciences , 2020 , 517 : 52 - 67 .
ITTI L , KOCH C , NIEBUR E . A model of saliency-based visual attention for rapid scene analysis [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 1998 , 20 ( 11 ): 1254 - 1259 .
VEDALDI A , LENC K . MatConvNet: Convolutional neural networks for MATLAB [C]. ACM International Conference on Multimedia , 2015 : 689 - 692 .
DANELLJAN M , HAGER G , KHAN F S , et al .. Convolutional features for correlation filter based visual tracking [C]. IEEE International Conference on Computer Vision , 2015 : 621 - 629 .
BERTINETTO L , VALMADRE J , HENRIQUES J F , et al .. Fully-convolutional siamese networks for object tracking [C]. Europeon Conference on Computer Vision , 2016 : 850 - 865 .
VALMADRE J , BERTINETTO L , HENRIQUES J , et al . . End to end representation learning for correlation filter based tracking [J]. Internaltional Conference on Computer Vision and Pattern Recogintion , 2017 : 5000 - 5008 .
WANG Q , GAO J , XING J , et al . . DCFNet: Discriminant correlation filters network for visual tracking [J]. arXiv preprint arXiv:1704 . 04057 , 2017 .
0
浏览量
334
下载量
1
CSCD
关联资源
相关文章
相关作者
相关机构