第4期 戴煜彤，等：相关滤波的运动目标抗遮挡再跟踪技术 ·639· 4结束语 The Netherlands:Springer,2016:472-488. [8]DANELLJAN M,BHAT G,SHAHBAZ KHAN F,et al. 本文针对ECO HC算法容易被遮挡以及遮挡 ECO:efficient convolution operators for tracking[Cl//Pro- 后模型污染等情况干扰而导致算法效果不佳的问 ceedings of 2017 IEEE Conference on Computer Vision 题，提出了一种融合ULBP特征的目标重定位机 and Pattern Recognition.Honolulu,HI,USA:IEEE,2017: 制相关滤波算法，有效地解决了由于遮挡因素带 6638-6646. 来的模型漂移问题，提高了算法跟踪的精度。在 [9]LI Bo.YAN Junjie,WU Wei,et al.High performance 视频序列集上的结果显示，本文算法在覆盖率、 visual tracking with Siamese region proposal 跟踪成功率、中心误差等评价指标下较其他算法 network[C]//Proceedings of 2018 IEEE/CVF Computer 性能较好，具有较强的鲁棒性。本文算法在面对 Vision and Pattern Recognition.Salt Lake City,UT,USA: 目标发生快速移动时表现效果较差，因此对目标 EEE,2018:6638-6646. 行动轨迹的预测仍需进一步的改进与研究。 [10]LI Bo,WU Wei,WANG Qiang,et al.SiamRPN++:evol- ution of Siamese visual tracking with very deep 参考文献： networks[C]//Proceedings of 2019 Computer Vision and Pattern Recognition(CVPR).Long Beach,CA,USA: [1]吴小俊，徐天阳，须文波.基于相关滤波的视频目标跟踪 IEEE,2019. 算法综述).指挥信息系统与技术，2017,8(3)：1-5. [11]FAN Heng,LIN Liting,YANG Fan,et al.LaSOT:a high- WU Xiaojun,XU Tianyang,XU Wenbo.Review of target quality benchmark for large-scale single object tracking algorithms in video based on correlation filter[J]. tracking[C]//Proceedings of 2019 IEEE/CVF Computer Command information system and technology,2017,8(3): Vision and Pattern Recognition(CVPR).Long Beach, 1-5 CA,USA:IEEE,2019. [2]张微，康宝生.相关滤波目标跟踪进展综述仞中国图象 [12]HENRIQUES J F,CASEIRO R,MARTINS P,et al.Ex- 图形学报，2017,22(8)：1017-1033 ploiting the Circulant structure of tracking by detection ZHANG Wei,KANG Baosheng.Recent advances in cor- with kernels[C]//Proceedings of the 12th European Con- relation filter-based object tracking:a review[J].Journal of ference on Computer Vision.Florence,Italy:Springer, image and graphics,2017,22(8):1017-1033. 2012:702-715. [3]BOLME D S,BEVERIDGE J R,DRAPER B A,et al. [13]COMANICIU D,MEER P.Mean shift:a robust ap- Visual object tracking using adaptive correlation proach toward feature space analysis[J].IEEE transac- filters[C]//Proceedings of 2010 IEEE Computer Society tions on pattern analysis and machine intelligence,2002. Conference on Computer Vision and Pattern Recognition. 24(5):603-619 San Francisco,CA,USA:IEEE,2010:2544-2550. [14]MEI Xue,LING Haibin.Robust visual tracking and [4]HENRIQUES J F,CASEIRO R,MARTINS P,et al.High- vehicle classification via sparse representation[J].IEEE speed tracking with kernelized correlation filters[J].IEEE transactions on pattern analysis and machine intelligence. transactions on pattern analysis and machine intelligence, 2011,33(11):2259-2272. 2015,37(3):583-596. [15]GRABNER H.GRABNER M.BISCHOF M.Real-time [5]DANELLJAN M.HAGER G.KHAN F S.et al.Accurate tracking via on-line boosting[C]//Proceedings of 2006 scale estimation for robust visual tracking[Cl/British Ma- British Machine Vision Conference.Edinburgh,UK:BM- chine Vision Conference.Nottingham,UK:BMVA Press, VC,2006:47-56 2014. [16]DANELLJAN M,SHAHBAZ KHAN F,FELSBERG M. [6]DANELLJAN M,HAGER G,SHAHBAZ KHAN F,et al. et al.Adaptive color attributes for real-time visual track- Learning spatially regularized correlation filters for visual ing[C]//Proceedings of 2014 IEEE Conference on Com- tracking[Cl//Proceedings of 2015 IEEE International Con- puter Vision and Pattern Recognition.Columbus,OH, ference on Computer Vision.Santiago,Chile:IEEE,2015: USA:IEEE,2014:1090-1097 4310-4318 [17]BERTINETTO L.VALMADRE J.GOLODETZ S,et al. [7]DANELLJAN M,ROBINSON A,KHAN F S,et al.Bey- Staple:complementary learners for real-time ond correlation filters:learning continuous convolution op- tracking[C]//Proceedings of 2016 IEEE Conference on erators for visual tracking[C]//Proceedings of the 14th Computer Vision and Pattern Recognition.Las Vegas, European Conference on Computer Vision.Amsterdam, NV,USA:IEEE.2016:1401-1409.4 结束语 本文针对 ECO_HC 算法容易被遮挡以及遮挡 后模型污染等情况干扰而导致算法效果不佳的问 题，提出了一种融合 ULBP 特征的目标重定位机 制相关滤波算法，有效地解决了由于遮挡因素带 来的模型漂移问题，提高了算法跟踪的精度。在 视频序列集上的结果显示，本文算法在覆盖率、 跟踪成功率、中心误差等评价指标下较其他算法 性能较好，具有较强的鲁棒性。本文算法在面对 目标发生快速移动时表现效果较差，因此对目标 行动轨迹的预测仍需进一步的改进与研究。 参考文献： 吴小俊, 徐天阳, 须文波. 基于相关滤波的视频目标跟踪 算法综述 [J]. 指挥信息系统与技术, 2017, 8(3): 1–5. WU Xiaojun, XU Tianyang, XU Wenbo. Review of target tracking algorithms in video based on correlation filter[J]. Command information system and technology, 2017, 8(3): 1–5. [1] 张微, 康宝生. 相关滤波目标跟踪进展综述 [J]. 中国图象 图形学报, 2017, 22(8): 1017–1033. ZHANG Wei, KANG Baosheng. Recent advances in cor￾relation filter-based object tracking: a review[J]. Journal of image and graphics, 2017, 22(8): 1017–1033. [2] 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 Conference on Computer Vision and Pattern Recognition. San Francisco, CA, USA: IEEE, 2010: 2544−2550. [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, HÄGER G, KHAN F S, et al. Accurate scale estimation for robust visual tracking[C]//British Ma￾chine Vision Conference. Nottingham, UK: BMVA Press, 2014. [5] DANELLJAN M, HÄGER G, SHAHBAZ KHAN F, et al. Learning spatially regularized correlation filters for visual tracking[C]//Proceedings of 2015 IEEE International Con￾ference on Computer Vision. Santiago, Chile: IEEE, 2015: 4310−4318. [6] DANELLJAN M, ROBINSON A, KHAN F S, et al. Bey￾ond correlation filters: learning continuous convolution op￾erators for visual tracking[C]//Proceedings of the 14th European Conference on Computer Vision. Amsterdam, [7] The Netherlands: Springer, 2016: 472−488. DANELLJAN M, BHAT G, SHAHBAZ KHAN F, et al. ECO: efficient convolution operators for tracking[C]//Pro￾ceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE, 2017: 6638−6646. [8] LI Bo, YAN Junjie, WU Wei, et al. High performance visual tracking with Siamese region proposal network[C]//Proceedings of 2018 IEEE/CVF Computer Vision and Pattern Recognition. Salt Lake City, UT, USA: IEEE, 2018: 6638−6646. [9] LI Bo, WU Wei, WANG Qiang, et al. SiamRPN++: evol￾ution of Siamese visual tracking with very deep networks[C]//Proceedings of 2019 Computer Vision and Pattern Recognition (CVPR). Long Beach, CA, USA: IEEE, 2019. [10] FAN Heng, LIN Liting, YANG Fan, et al. LaSOT: a high￾quality benchmark for large-scale single object tracking[C]//Proceedings of 2019 IEEE/CVF Computer Vision and Pattern Recognition (CVPR). Long Beach, CA, USA: IEEE, 2019. [11] HENRIQUES J F, CASEIRO R, MARTINS P, et al. Ex￾ploiting the Circulant structure of tracking by detection with kernels[C]//Proceedings of the 12th European Con￾ference on Computer Vision. Florence, Italy: Springer, 2012: 702−715. [12] COMANICIU D, MEER P. Mean shift: a robust ap￾proach toward feature space analysis[J]. IEEE transac￾tions on pattern analysis and machine intelligence, 2002, 24(5): 603–619. [13] MEI Xue, LING Haibin. Robust visual tracking and vehicle classification via sparse representation[J]. IEEE transactions on pattern analysis and machine intelligence, 2011, 33(11): 2259–2272. [14] GRABNER H, GRABNER M. BISCHOF M. Real-time tracking via on-line boosting[C]//Proceedings of 2006 British Machine Vision Conference. Edinburgh, UK: BM￾VC, 2006: 47−56. [15] DANELLJAN M, SHAHBAZ KHAN F, FELSBERG M, et al. Adaptive color attributes for real-time visual track￾ing[C]//Proceedings of 2014 IEEE Conference on Com￾puter Vision and Pattern Recognition. Columbus, OH, USA: IEEE, 2014: 1090−1097. [16] 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: 1401−1409. [17] 第 4 期 戴煜彤，等：相关滤波的运动目标抗遮挡再跟踪技术 ·639·