基于相似背景与HSV空间颜色直方图的目标跟踪
|
摘要
针对相关滤波器的存在边界效应问题,提出了一种基于相似背景与HSV空间颜色直方图的目标跟踪算法。通过最佳伙伴相似原理(Best-Buddies Similarity),在真实背景中选取与目标相似度较高的相似背景作为负样本训练相关滤波器,降低边界效应。并将HSV空间颜色直方图与贝叶斯分类器结合对目标进行颜色跟踪,利用颜色直方图信息提高复杂背景下目标跟踪的成功率。在OTB-50和OTB-100中挑选16个视频进行实验,与当前主流的6种跟踪算法对比,本文算法的成功率得分0.593,准确率得分0.467,优于6种主流的目标跟踪算法,能够有效提高目标跟踪的成功率和准确率,并且具有较好的实时性。
In order to solve the problem of boundary effects of the correlation filter, an object tracking algorithm is proposed based on similar background and color histogram in HSV color space. By using the Best-Buddies Similarity principle, similar backgrounds with higher similarity to the target are selected in the real background as the negative sample to train the correlation filter, so as to reduce the boundary effect. In order to improve the success rate of object tracking in complicated environment, the color histogram in HSV color space is combined with Bayes classifier for color tracking. Experiments are carried out on 16 videos selected from OTB-50 and OTB-100, and the results are compared with that of the current six tracking algorithms. The success rate and accuracy of the proposed algorithm are 0. 593 and 0. 467 respectively,which is superior to that of the other six algorithms. The proposed algorithm can effectively improve the success rate and accuracy of object tracking and has good real-time performance.
In order to solve the problem of boundary effects of the correlation filter, an object tracking algorithm is proposed based on similar background and color histogram in HSV color space. By using the Best-Buddies Similarity principle, similar backgrounds with higher similarity to the target are selected in the real background as the negative sample to train the correlation filter, so as to reduce the boundary effect. In order to improve the success rate of object tracking in complicated environment, the color histogram in HSV color space is combined with Bayes classifier for color tracking. Experiments are carried out on 16 videos selected from OTB-50 and OTB-100, and the results are compared with that of the current six tracking algorithms. The success rate and accuracy of the proposed algorithm are 0. 593 and 0. 467 respectively,which is superior to that of the other six algorithms. The proposed algorithm can effectively improve the success rate and accuracy of object tracking and has good real-time performance.
引文
[1]吕铁军,蒋宏,梁国威,等.基于多模型的联合目标跟踪与分类算法[J].电光与控制,2013,20(8):18-23,28.
[2]许婉君,侯志强,余旺盛,等.一种改进的多特征融合目标跟踪算法[J].电光与控制,2015,22(12):34-39.
[3]忽晓伟,陈娟.融合颜色特征的核相关滤波器目标跟踪[J].电光与控制,2017,24(6):43-46.
[4]王智军,王建华.多特征融合的图像目标跟踪方法[J].电光与控制,2017,24(11):49-52,57.
[5]BOLME D S,BEVERIDGE J R,DRAPER B A,et al.Visual object tracking using adaptive correlation filters[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2010:2544-2550.
[6]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.
[7]HENRIQUES J F,CASEIRO R,MARTINS P,et al.Highspeed tracking with kernelized correlation filters[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2015,37(3):583-596.
[8]DANELLJAN M,HAGER G,KHAN F S.Accurate scale estimation for robust visual tracking[C]//Proceedings of British Machine Vision Conference,2014:1-11.
[9]DANELLJAN M,HAGER G,KHAN F S,et al.Learning spatially regularized correlation filters for visual tracking[C]//IEEE International Conference on Computer Vision,IEEE Computer Society,2015:4310-4318.
[10]BERTINETTO L,VALMADRE J,GOLODETZ S,et al.Staple:complementary learners for real-time tracking[C]//CVPR,2016:1-9.
[11]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.
[12]KUMAR B V K V,MAHALANOBIS A,JUDAY R D.Correlation pattern recognition[M].New York:Cambridge University Press,2010.
[13]GALOOGAHI H K,SIM T,LUCEY S.Correlation filters with limited boundaries[C]//IEEE Conference on Computer Vision and Pattern Recognition,2015:4630-4638.
[14]GALOOGAHI H K,FAGG A,LUCEY S.Learning background-aware correlation filters for visual tracking[C]//IEEE International Conference on Computer Vision,2017:1144-1152.
[15]NAM H,HAN B.Learning multi-domain convolutional neural networks for visual tracking[C]//IEEE Conference on Computer Vision and Pattern Recognition,2016:4293-4302.
[16]NAM H,BAEK M,HAN B.Modeling and propagating CNNs in a tree structure for visual tracking[C]//IEEE Conference on Computer Vision and Pattern Recognition,2016:1-10.
[17]DEKEL T,ORON S,RUBINSTEIN M,et al.Best-buddies similarity for robust template matching[C]//IEEE Conference on Computer Vision and Pattern Recognition,2015:2021-2029.
[18]POSSEGGER H,MAUTHNER T,BISCHOF H.In defense of color-based model-free tracking[C]//IEEE Conference on Computer Vision and Pattern Recognition,2015:2113-2120.
[19]徐福来,王鸿鹏,张普,等.基于贝叶斯模型与最佳伙伴相似度量的目标跟踪[J].计算机应用研究,2018(8):2498-2502,2526.
[20]WU Y,LIM J,YANG M H.Online object tracking:a benchmark[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2013:2411-2418.
[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.
[2]许婉君,侯志强,余旺盛,等.一种改进的多特征融合目标跟踪算法[J].电光与控制,2015,22(12):34-39.
[3]忽晓伟,陈娟.融合颜色特征的核相关滤波器目标跟踪[J].电光与控制,2017,24(6):43-46.
[4]王智军,王建华.多特征融合的图像目标跟踪方法[J].电光与控制,2017,24(11):49-52,57.
[5]BOLME D S,BEVERIDGE J R,DRAPER B A,et al.Visual object tracking using adaptive correlation filters[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2010:2544-2550.
[6]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.
[7]HENRIQUES J F,CASEIRO R,MARTINS P,et al.Highspeed tracking with kernelized correlation filters[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2015,37(3):583-596.
[8]DANELLJAN M,HAGER G,KHAN F S.Accurate scale estimation for robust visual tracking[C]//Proceedings of British Machine Vision Conference,2014:1-11.
[9]DANELLJAN M,HAGER G,KHAN F S,et al.Learning spatially regularized correlation filters for visual tracking[C]//IEEE International Conference on Computer Vision,IEEE Computer Society,2015:4310-4318.
[10]BERTINETTO L,VALMADRE J,GOLODETZ S,et al.Staple:complementary learners for real-time tracking[C]//CVPR,2016:1-9.
[11]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.
[12]KUMAR B V K V,MAHALANOBIS A,JUDAY R D.Correlation pattern recognition[M].New York:Cambridge University Press,2010.
[13]GALOOGAHI H K,SIM T,LUCEY S.Correlation filters with limited boundaries[C]//IEEE Conference on Computer Vision and Pattern Recognition,2015:4630-4638.
[14]GALOOGAHI H K,FAGG A,LUCEY S.Learning background-aware correlation filters for visual tracking[C]//IEEE International Conference on Computer Vision,2017:1144-1152.
[15]NAM H,HAN B.Learning multi-domain convolutional neural networks for visual tracking[C]//IEEE Conference on Computer Vision and Pattern Recognition,2016:4293-4302.
[16]NAM H,BAEK M,HAN B.Modeling and propagating CNNs in a tree structure for visual tracking[C]//IEEE Conference on Computer Vision and Pattern Recognition,2016:1-10.
[17]DEKEL T,ORON S,RUBINSTEIN M,et al.Best-buddies similarity for robust template matching[C]//IEEE Conference on Computer Vision and Pattern Recognition,2015:2021-2029.
[18]POSSEGGER H,MAUTHNER T,BISCHOF H.In defense of color-based model-free tracking[C]//IEEE Conference on Computer Vision and Pattern Recognition,2015:2113-2120.
[19]徐福来,王鸿鹏,张普,等.基于贝叶斯模型与最佳伙伴相似度量的目标跟踪[J].计算机应用研究,2018(8):2498-2502,2526.
[20]WU Y,LIM J,YANG M H.Online object tracking:a benchmark[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2013:2411-2418.
[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.