实时高置信度更新补充学习跟踪
|
摘要
为解决补充学习跟踪算法(Staple)在目标被部分遮挡时存在的跟踪失败问题,文中提出了一种简单而有效的高置信度补充学习跟踪算法(High-confidence updata Complementary Learner Tracker,HCLT)。首先,输入当前帧,得到标准相关滤波分类器的检测响应值;然后,计算相关滤波响应的置信度,若计算结果大于阈值则当前帧更新滤波器,否则停止更新;接着,计算出持续不更新的帧数,如果有连续10帧不更新,则强制更新;最后,通过融合颜色补充学习器的响应,得到总的响应结果,其中,响应中最大值的位置即为跟踪结果。将所提算法与补充学习跟踪(Correlation Filter Net tracker,Staple)、端到端表示跟踪(CFNet)、注意力相关滤波网络跟踪(Attentional Correlation Filter Network tracker,ACFN)和对冲深度跟踪(Hedged Deep Tracking,HDT)等先进算法进行实验对比。在OTB100和VOT2016数据集上的结果表明,所提算法在成功率和预期覆盖率方面分别超过基准补充学习跟踪算法(Staple)1.0个百分点和0.4个百分点。另外,在严重遮挡和剧烈光照变化的视频集上的良好表现也充分说明了所提算法在处理表观剧烈变化的情况时很有效。
To address the issue that the complementary learner tracking algorithm(Staple) cannot perform well when the target suffers from severe occlusions,a high-confidence update complementary learner tracker(HCLT) was proposed.Firstly,at the input frame,a standard correlation filter is employed to calculate the correlation filter(CF) response.Secondly,the confidence value based on the CF response is calculated and the update of the correlation filter is stopped when the current confidence value exceeds the mean confidence value.Then,if the number of the continuous no-updated frames comes up to ten,the tracker will be forced to update the filter.Finally,the final response is obtained by combining the CF response with the color response,and the location of maximum response is the tracking result.Expe-riment results show that compared with several state-of-the-art trackers including complementary learner(Staple),end-to-end representation correlation filter net tracker(CFNet),attentional correlation filter network tracker(ACFN) and hedged deep tracking(HDT),the proposed algorithm is the best in terms of success rate,outperforming the baseline tracker Staple by 1.0 percentage points and 0.4 percentage points interms of success rate and expected average overlap(EAO)on OTB100 dataset and VOT2016 dataset,respectively.Besides,the performance on heavy occlusion and severe illumination variation sequences demonstrates the effectiveness of proposed tracker when handling drastic appearance variations.
To address the issue that the complementary learner tracking algorithm(Staple) cannot perform well when the target suffers from severe occlusions,a high-confidence update complementary learner tracker(HCLT) was proposed.Firstly,at the input frame,a standard correlation filter is employed to calculate the correlation filter(CF) response.Secondly,the confidence value based on the CF response is calculated and the update of the correlation filter is stopped when the current confidence value exceeds the mean confidence value.Then,if the number of the continuous no-updated frames comes up to ten,the tracker will be forced to update the filter.Finally,the final response is obtained by combining the CF response with the color response,and the location of maximum response is the tracking result.Expe-riment results show that compared with several state-of-the-art trackers including complementary learner(Staple),end-to-end representation correlation filter net tracker(CFNet),attentional correlation filter network tracker(ACFN) and hedged deep tracking(HDT),the proposed algorithm is the best in terms of success rate,outperforming the baseline tracker Staple by 1.0 percentage points and 0.4 percentage points interms of success rate and expected average overlap(EAO)on OTB100 dataset and VOT2016 dataset,respectively.Besides,the performance on heavy occlusion and severe illumination variation sequences demonstrates the effectiveness of proposed tracker when handling drastic appearance variations.
引文
[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 (CVPR).IEEE,2010:2544-2550.
[2] 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.
[3] LIU S,ZHANG T,CAO X,et al.Structural correlation filter for robust visual tracking[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2016:4312-4320.
[4] 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.IEEE,2016:1401-1409.
[5] MUELLER M,SMITH N,GHANEM B.Context-aware correlation filter tracking[C]//Proc.IEEE Conf.Comput.Vis.Pattern Recognit.(CVPR).IEEE,2017:1396-1404.
[6] GALOOGAHI H K,FAGG A,LUCEY S.Learning back- ground-aware correlation filters for visual tracking[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Honolulu,HI,USA,2017:21-26.
[7] ZHANG T,XU C,YANG M H.Multi-task correlation particle filter for robust object tracking[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2017.
[8] ZHANG T,LIU S,XU C,et al.Correlation particle filter for visual tracking[J].IEEE Transactions on Image Processing,2018,27(6):2676-2687.
[9] WU Y,LIM J,YANG M H.Online object tracking:A.benchmark[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2013:2411-2418.
[10] KRISTAN M,PFLUGFELDER R,LEONARDIS A,et al.The visual object tracking vot2013 challenge results[C]//Procee-dings of the IEEE International Conference on Computer Vision Workshops.IEEE,2013:98-111.
[11] LUKEZIC A,VOJIR T,ZAJC L C,et al.Discriminative Correlation Filter with Channel and Spatial Reliability[C]//IEEE Conference on Computer Vision and Pattern Recognition.IEEE Computer Society,2017:4847-4856.
[12] QI Y,ZHANG S,QIN L,et al.Hedged deep tracking[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE〈2016:4303-4311.
[13] BERTINETTO L,VALMADRE J,HENRIQUES J F,et al. Fully-Convolutional Siamese Networks for Object Tracking[C]//European Conference on Computer Vision.Cham:Springer,2016:850-865.
[14] VALMADRE J,BERTINETTO L,HENRIQUES J,et al.End-to-End Representation Learning for Correlation Filter Based Tracking[C]//Proceedings of the IEEE Conference on ComputerVision and Pattern Recognition.IEEE Computer Society,2017:5000-5008.
[15] CHOI J,CHANG H J,YUN S,et al.Attentional Correlation Filter Network for Adaptive Visual Tracking[C]//IEEE Conference on Computer Vision and Pattern Recognition.IEEE Computer Society,2017:4828-4837.
[16] LI Y,ZHU J,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.IEEE,2015:353-361.
[17] NING J,YANG J,JIANG S,et al.Object tracking via dual linear structured SVM and explicit feature map[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2016:4266-4274.
[18] ZHANG J,MA S,SCLAROFF S.MEEM:robust tracking via multiple experts using entropy minimization[C]//European Conference on Computer Vision.Cham:Springer,2014:188-203.
[2] 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.
[3] LIU S,ZHANG T,CAO X,et al.Structural correlation filter for robust visual tracking[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2016:4312-4320.
[4] 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.IEEE,2016:1401-1409.
[5] MUELLER M,SMITH N,GHANEM B.Context-aware correlation filter tracking[C]//Proc.IEEE Conf.Comput.Vis.Pattern Recognit.(CVPR).IEEE,2017:1396-1404.
[6] GALOOGAHI H K,FAGG A,LUCEY S.Learning back- ground-aware correlation filters for visual tracking[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Honolulu,HI,USA,2017:21-26.
[7] ZHANG T,XU C,YANG M H.Multi-task correlation particle filter for robust object tracking[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2017.
[8] ZHANG T,LIU S,XU C,et al.Correlation particle filter for visual tracking[J].IEEE Transactions on Image Processing,2018,27(6):2676-2687.
[9] WU Y,LIM J,YANG M H.Online object tracking:A.benchmark[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2013:2411-2418.
[10] KRISTAN M,PFLUGFELDER R,LEONARDIS A,et al.The visual object tracking vot2013 challenge results[C]//Procee-dings of the IEEE International Conference on Computer Vision Workshops.IEEE,2013:98-111.
[11] LUKEZIC A,VOJIR T,ZAJC L C,et al.Discriminative Correlation Filter with Channel and Spatial Reliability[C]//IEEE Conference on Computer Vision and Pattern Recognition.IEEE Computer Society,2017:4847-4856.
[12] QI Y,ZHANG S,QIN L,et al.Hedged deep tracking[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE〈2016:4303-4311.
[13] BERTINETTO L,VALMADRE J,HENRIQUES J F,et al. Fully-Convolutional Siamese Networks for Object Tracking[C]//European Conference on Computer Vision.Cham:Springer,2016:850-865.
[14] VALMADRE J,BERTINETTO L,HENRIQUES J,et al.End-to-End Representation Learning for Correlation Filter Based Tracking[C]//Proceedings of the IEEE Conference on ComputerVision and Pattern Recognition.IEEE Computer Society,2017:5000-5008.
[15] CHOI J,CHANG H J,YUN S,et al.Attentional Correlation Filter Network for Adaptive Visual Tracking[C]//IEEE Conference on Computer Vision and Pattern Recognition.IEEE Computer Society,2017:4828-4837.
[16] LI Y,ZHU J,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.IEEE,2015:353-361.
[17] NING J,YANG J,JIANG S,et al.Object tracking via dual linear structured SVM and explicit feature map[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2016:4266-4274.
[18] ZHANG J,MA S,SCLAROFF S.MEEM:robust tracking via multiple experts using entropy minimization[C]//European Conference on Computer Vision.Cham:Springer,2014:188-203.