融合上下文和重定位的加权相关滤波跟踪算法
|
摘要
为提升融合梯度直方图特征和颜色属性特征的有效卷积操作跟踪算法(ECO-HC)的跟踪精度和速度,提出一种融合上下文和重定位的加权相关滤波跟踪方法。根据梯度直方图和颜色属性的不同特性加权融合相关滤波响应值,采用自适应迭代方法预测目标位置;融合多尺度搜索区域,目标上下文特征和目标预测失败时重定位方法进一步提高跟踪精度。在标准数据集OTB-100上进行算法评估,实验结果表明,所提算法的平均距离精度为89.2%,平均重叠率精度为80.6%,比ECO-HC算法分别高3.6%和2.1%。中央处理器的跟踪速度达65.2 frame/s,优于实验中对比的其他跟踪算法。所提算法有效地提高了跟踪精度,在严重遮挡、光照变化等干扰下,仍能较好地跟踪目标。
In order to improve both the tracking accuracy and speed of the efficient convolution operators based tracking algorithm fusing the histogram of oriented gradient and color names features(ECO-HC), a weighted correlation filtering algorithm based on context and relocation is proposed. Considering the differences between the histogram of oriented gradient and color names features, the responses of two features are fused in different weights. The adaptive iterative method is used to predict the position of a target, which combines with the multi-scale search area, the contextual features and the relocation method when the target prediction is failure to further improve the tracking accuracy. The algorithm is evaluated on the OTB-100 dataset. The experimental results show that the average distance accuracy of the proposed algorithm is 89.2% and the average overlap rate is 80.6%, 3.6% and 2.1% higher than those of the ECO-HC method, respectively. In addition, the tracking speed on the central processing unit is 65.2 frame/s, superior to that of the other tracking algorithms compared in the experiments. The proposed algorithm effectively improves the tracking accuracy and can track the objects well under the condition of severe occlusion, illumination variation and other interferences.
In order to improve both the tracking accuracy and speed of the efficient convolution operators based tracking algorithm fusing the histogram of oriented gradient and color names features(ECO-HC), a weighted correlation filtering algorithm based on context and relocation is proposed. Considering the differences between the histogram of oriented gradient and color names features, the responses of two features are fused in different weights. The adaptive iterative method is used to predict the position of a target, which combines with the multi-scale search area, the contextual features and the relocation method when the target prediction is failure to further improve the tracking accuracy. The algorithm is evaluated on the OTB-100 dataset. The experimental results show that the average distance accuracy of the proposed algorithm is 89.2% and the average overlap rate is 80.6%, 3.6% and 2.1% higher than those of the ECO-HC method, respectively. In addition, the tracking speed on the central processing unit is 65.2 frame/s, superior to that of the other tracking algorithms compared in the experiments. The proposed algorithm effectively improves the tracking accuracy and can track the objects well under the condition of severe occlusion, illumination variation and other interferences.
引文
[1] Bolme D S,Beveridge J R,Draper B A,et al.Visual object tracking using adaptive correlation filters[C].IEEE Computer Society 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,Khan F S,Felsberg M,et al.Adaptive color attributes for real-time visual tracking[C].IEEE Conference on Computer Vision and Pattern Recognition,2014:1090-1097.
[5] Bertinetto L,Valmadre J,Golodetz S,et al.Staple:complementary learners for real-time tracking[C].IEEE Conference on Computer Vision and Pattern Recognition,2016:1401-1409.
[6] Ma C,Huang J B,Yang X K,et al.Hierarchical convolutional features for visual tracking[C].IEEE International Conference on Computer Vision,2015:3074-3082.
[7] Ma C,Huang J B,Yang X K,et al.Robust visual tracking via hierarchical convolutional features[EB/OL].(2018-08-11)[2018-10-25].https:∥arxiv.org/abs/1707.03816.
[8] Li S S,Zhao G P,Wang J N.Distractor-aware object tracking based on multi-feature fusion and scale-adaption[J].Acta Optica Sinica,2017,37(5):0515005.李双双,赵高鹏,王建宇.基于特征融合和尺度自适应的干扰感知目标跟踪[J].光学学报,2017,37(5):0515005.
[9] He Z Q,Fan Y R,Zhuang J F,et al.Correlation filters with weighted convolution responses[C].IEEE International Conference on Computer Vision Workshops,2017:1992-2000.
[10] Xiong C Z,Zhao L L,Guo F H.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.
[11] Danelljan M,H?ger G,Khan F S,et al.Learning spatially regularized correlation filters for visual tracking[C].IEEE International Conference on Computer Vision,2015:4310-4318.
[12] 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.
[13] Wang M M,Liu Y,Huang Z Y.Large margin object tracking with circulant feature maps[C].IEEE Conference on Computer Vision and Pattern Recognition,2017:4800-4808.
[14] Danelljan M,H?ger G,Khan F S,et al.Discriminative scale space tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(8):1561-1575.
[15] Li Y,Zhu J K.A scale adaptive kernel correlation filter tracker with feature integration[C].European Conference on Computer Vision,2014:254-265.
[16] 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.
[17] Xiong C Z,Che M Q,Wang R L,et al.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,等.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.
[18] Wu Y,Lim J,Yang M H.Object tracking benchmark[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1834-1848.
[19] 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.
[20] Luke?ic A,Vojír T,Zajc L C,et al.Discriminative correlation filter with channel and spatial reliability[C].IEEE Conference on Computer Vision and Pattern Recognition,2017:4847-4856.
[21] Danelljan M,H?ger G,Khan F S,et al.Convolutional features for correlation filter based visual tracking[C].IEEE International Conference on Computer Vision Workshop,2015:621-629.
[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,Khan F S,Felsberg M,et al.Adaptive color attributes for real-time visual tracking[C].IEEE Conference on Computer Vision and Pattern Recognition,2014:1090-1097.
[5] Bertinetto L,Valmadre J,Golodetz S,et al.Staple:complementary learners for real-time tracking[C].IEEE Conference on Computer Vision and Pattern Recognition,2016:1401-1409.
[6] Ma C,Huang J B,Yang X K,et al.Hierarchical convolutional features for visual tracking[C].IEEE International Conference on Computer Vision,2015:3074-3082.
[7] Ma C,Huang J B,Yang X K,et al.Robust visual tracking via hierarchical convolutional features[EB/OL].(2018-08-11)[2018-10-25].https:∥arxiv.org/abs/1707.03816.
[8] Li S S,Zhao G P,Wang J N.Distractor-aware object tracking based on multi-feature fusion and scale-adaption[J].Acta Optica Sinica,2017,37(5):0515005.李双双,赵高鹏,王建宇.基于特征融合和尺度自适应的干扰感知目标跟踪[J].光学学报,2017,37(5):0515005.
[9] He Z Q,Fan Y R,Zhuang J F,et al.Correlation filters with weighted convolution responses[C].IEEE International Conference on Computer Vision Workshops,2017:1992-2000.
[10] Xiong C Z,Zhao L L,Guo F H.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.
[11] Danelljan M,H?ger G,Khan F S,et al.Learning spatially regularized correlation filters for visual tracking[C].IEEE International Conference on Computer Vision,2015:4310-4318.
[12] 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.
[13] Wang M M,Liu Y,Huang Z Y.Large margin object tracking with circulant feature maps[C].IEEE Conference on Computer Vision and Pattern Recognition,2017:4800-4808.
[14] Danelljan M,H?ger G,Khan F S,et al.Discriminative scale space tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(8):1561-1575.
[15] Li Y,Zhu J K.A scale adaptive kernel correlation filter tracker with feature integration[C].European Conference on Computer Vision,2014:254-265.
[16] 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.
[17] Xiong C Z,Che M Q,Wang R L,et al.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,等.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.
[18] Wu Y,Lim J,Yang M H.Object tracking benchmark[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1834-1848.
[19] 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.
[20] Luke?ic A,Vojír T,Zajc L C,et al.Discriminative correlation filter with channel and spatial reliability[C].IEEE Conference on Computer Vision and Pattern Recognition,2017:4847-4856.
[21] Danelljan M,H?ger G,Khan F S,et al.Convolutional features for correlation filter based visual tracking[C].IEEE International Conference on Computer Vision Workshop,2015:621-629.