第2期 欧伟奇，等：一种基于Multi-Egocentric视频运动轨迹重建的多目标跟踪算法 ·253· 参考文献： neural networks for visual tracking[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern [1]SHAN Caifeng,WEI Yucheng,TAN Tieniu,et al.Real Recognition.Las Vegas.NV.USA.2016:4293-4302. time hand tracking by combining particle filtering and [14]KHAN S M,YAN Pingkun,SHAH M.A homographic mean shift[C]//Proceedings of the 6th IEEE International framework for the fusion of multi-view silhouettes[C]// Conference on Automatic Face and Gesture Recognition. Proceedings of the 11th International Conference on Seoul,South Korea,2004:669-674. Computer Vision.Rio de Janeiro,Brazil,2007:1-8. [2]ZHANG Lei,LI Yuan,NEVATIA R.Global data associ- [15]FISCHLER M A.BOLLES R C.Random sample con- ation for multi-object tracking using network flows[C1// sensus:a paradigm for model fitting with applications to Proceedings of 2008 IEEE Conference on Computer Vis- image analysis and automated cartography[J.Communic- ion and Pattern Recognition.Anchorage,AK.USA.2008:1-8. ations of the ACM,1981,24(6):381-395. [3]AVIDAN S.Ensemble tracking[J].IEEE transactions on [16]ZHANG Z.A flexible new technique for camera calibra- pattern analysis and machine intelligence,2007,29(2): tion[J].IEEE transactions on pattern analysis and ma- 261-271 chine intelligence,2000,22(11):1330-1334. [4]XU Yuanlu,LIU Xiaobai,LIU Yang,et al.Multi-view [17]SCHWEIGHOFER G,PINZ A.Robust pose estimation people tracking via hierarchical trajectory composition[Cl// from a planar target[J].IEEE transactions on pattern ana- Proceedings of 2016 IEEE Conference on Computer Vis- ion and Pattern Recognition.Las Vegas,NV,USA,2016: lysis and machine intelligence,2006,28(12):2024-2030. 4256-4265. [18]BEKIR E.Adaptive Kalman filter for tracking maneuver [5]HE Shengfeng,YANG Qingxiong,LAU R W H,et al. ing targets[J].Journal of guidance,control,and dynamics. Visual tracking via locality sensitive histograms[C]//Pro- 2015,6(5):414-416. ceedings of 2013 IEEE Conference on Computer Vision [19]DOLLAR P.APPEL R.BELONGIE S,et al.Fast feature and Pattern Recognition.Portland,USA,2013:2427-2434. pyramids for object detection[J].IEEE transactions on [6]FLEURET F,BERCLAZ J,LENGAGNE R,et al.Mul- pattern analysis and machine intelligence,2014,36(8): ticamera people tracking with a probabilistic occupancy 1532-1545 map[J].IEEE transactions on pattern analysis and machine [20]BERNARDI K,STIEFELHAGEN R.Evaluating mul- intelligence,2008.30(2):267-282. tiple object tracking performance:the CLEAR MOT met- [7]MEI Xue,LING Haibo.Robust visual tracking using (1 rics[J].EURASIP Journal on image and video processing. minimization[C]//Proceedings of the 12th IEEE Interna- 2008.2008(1):246309 tional Conference on Computer Vision.Kyoto,Japan, 作者简介： 2009:1436-1443 [8]BABENKO B,YANG M H.BELONGIE S.Robust object 欧伟奇，男，1992出生，硕士研究 生，主要研究方向为图像处理、机器 tracking with online multiple instance learning[J].IEEE 学习。 transactions on pattern analysis and machine intelligence. 2011.33(8):1619-1632. [9]王宇霞，赵清杰，蔡艺明，等.基于自重构粒子滤波算法 的目标跟踪).计算机学报，2016,39(7)：1294-1306. WANG Yuxia,ZHAO Qingjie,CAI Yiming,et al.Track- ing by auto-reconstructing particle filter trackers[J]. 尹辉.女，1972出生，教授，博士， Chinese journal of computers,2016,39(7):1294-1306. 主要研究方向为机器视觉、模式识别 [10]BAE S H,YOON K J.Robust online multi-object track- 和神经计算。主持和参加国家和省部 ing based on tracklet confidence and online discriminat- 级科研项目60余项，发表学术论文 ive appearance learning[C]//Proceedings of 2014 IEEE 20余篇，知识产权18项，获国家科学 Conference on Computer Vision and Pattern Recognition. 技术进步奖一等奖1项，教育部科技 Columbus.OH.USA.2014:1218-1225 进步一等奖1项，中国专利优秀奖 [11]DICLE C,CAMPS O I,SZNAIER M.The way they 1项，中国铁道学会科学技术奖特等奖、二等奖各1项，北京 move:tracking multiple targets with similar appearance[Cl/ 市高等教育教学成果奖二等奖1项。 Proceedings of 2013 IEEE International Conference on Computer Vision.Sydney,NSW,Australia,2013: 许宏丽，女，1963出生.教授，博 2304-2311. 士，主要研究方向为图像处理、机器学 [12]XIANG Yu.ALAHI A,SAVARESE S.Learning to track: 习和认知计算。主持铁道部项目 online multi-object tracking by decision making[C]//Pro- 2项国重项目1项，参与多项国家和省 ceedings of 2015 IEEE International Conference on Com- 部级科研项目，发表学术论文20余 puter Vision.Santiago,Chile,2015:4705-4713. 篇。主持国家精品课程《多媒体技术 [13]NAM H.HAN B.Learning multi-domain convolutional 应用》，获国家教学进步二等奖。参考文献： SHAN Caifeng, WEI Yucheng, TAN Tieniu, et al. Real time hand tracking by combining particle filtering and mean shift[C]//Proceedings of the 6th IEEE International Conference on Automatic Face and Gesture Recognition. Seoul, South Korea, 2004: 669–674. [1] ZHANG Lei, LI Yuan, NEVATIA R. Global data associ￾ation for multi-object tracking using network flows[C]// Proceedings of 2008 IEEE Conference on Computer Vis￾ion and Pattern Recognition. Anchorage, AK, USA, 2008: 1–8. [2] AVIDAN S. Ensemble tracking[J]. IEEE transactions on pattern analysis and machine intelligence, 2007, 29(2): 261–271. [3] XU Yuanlu, LIU Xiaobai, LIU Yang, et al. Multi-view people tracking via hierarchical trajectory composition[C]// Proceedings of 2016 IEEE Conference on Computer Vis￾ion and Pattern Recognition. Las Vegas, NV, USA, 2016: 4256–4265. [4] HE Shengfeng, YANG Qingxiong, LAU R W H, et al. Visual tracking via locality sensitive histograms[C]//Pro￾ceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition. Portland, USA, 2013: 2427–2434. [5] FLEURET F, BERCLAZ J, LENGAGNE R, et al. Mul￾ticamera people tracking with a probabilistic occupancy map[J]. IEEE transactions on pattern analysis and machine intelligence, 2008, 30(2): 267–282. [6] MEI Xue, LING Haibo. Robust visual tracking using ℓ1 minimization[C]//Proceedings of the 12th IEEE Interna￾tional Conference on Computer Vision. Kyoto, Japan, 2009: 1436–1443. [7] BABENKO B, YANG M H, BELONGIE S. Robust object tracking with online multiple instance learning[J]. IEEE transactions on pattern analysis and machine intelligence, 2011, 33(8): 1619–1632. [8] 王宇霞, 赵清杰, 蔡艺明, 等. 基于自重构粒子滤波算法 的目标跟踪[J]. 计算机学报, 2016, 39(7): 1294–1306. WANG Yuxia, ZHAO Qingjie, CAI Yiming, et al. Track￾ing by auto-reconstructing particle filter trackers[J]. Chinese journal of computers, 2016, 39(7): 1294–1306. [9] BAE S H, YOON K J. Robust online multi-object track￾ing based on tracklet confidence and online discriminat￾ive appearance learning[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH, USA, 2014: 1218–1225. [10] DICLE C, CAMPS O I, SZNAIER M. The way they move: tracking multiple targets with similar appearance[C]// Proceedings of 2013 IEEE International Conference on Computer Vision. Sydney, NSW, Australia, 2013: 2304–2311. [11] XIANG Yu, ALAHI A, SAVARESE S. Learning to track: online multi-object tracking by decision making[C]//Pro￾ceedings of 2015 IEEE International Conference on Com￾puter Vision. Santiago, Chile, 2015: 4705–4713. [12] [13] NAM H, HAN B. Learning multi-domain convolutional neural networks for visual tracking[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA, 2016: 4293–4302. KHAN S M, YAN Pingkun, SHAH M. A homographic framework for the fusion of multi-view silhouettes[C]// Proceedings of the 11th International Conference on Computer Vision. Rio de Janeiro, Brazil, 2007: 1–8. [14] FISCHLER M A, BOLLES R C. Random sample con￾sensus: a paradigm for model fitting with applications to image analysis and automated cartography[J]. Communic￾ations of the ACM, 1981, 24(6): 381–395. [15] ZHANG Z. A flexible new technique for camera calibra￾tion[J]. IEEE transactions on pattern analysis and ma￾chine intelligence, 2000, 22(11): 1330–1334. [16] SCHWEIGHOFER G, PINZ A. Robust pose estimation from a planar target[J]. IEEE transactions on pattern ana￾lysis and machine intelligence, 2006, 28(12): 2024–2030. [17] BEKIR E. Adaptive Kalman filter for tracking maneuver￾ing targets[J]. Journal of guidance, control, and dynamics, 2015, 6(5): 414–416. [18] DOLLÁR P, APPEL R, BELONGIE S, et al. Fast feature pyramids for object detection[J]. IEEE transactions on pattern analysis and machine intelligence, 2014, 36(8): 1532–1545. [19] BERNARDI K, STIEFELHAGEN R. Evaluating mul￾tiple object tracking performance: the CLEAR MOT met￾rics[J]. EURASIP Journal on image and video processing, 2008, 2008(1): 246309. [20] 作者简介： 欧伟奇，男，1992 出生，硕士研究 生，主要研究方向为图像处理、机器 学习。 尹辉，女，1972 出生，教授，博士， 主要研究方向为机器视觉、模式识别 和神经计算。主持和参加国家和省部 级科研项目 60 余项，发表学术论文 20 余篇，知识产权 18 项，获国家科学 技术进步奖一等奖 1 项，教育部科技 进步一等奖 1 项，中国专利优秀奖 1 项，中国铁道学会科学技术奖特等奖、二等奖各 1 项，北京 市高等教育教学成果奖二等奖 1 项。 许宏丽，女，1963 出生，教授，博 士，主要研究方向为图像处理、机器学 习和认知计算。主持铁道部项目 2 项,国重项目 1 项,参与多项国家和省 部级科研项目,发表学术论文 20 余 篇。主持国家精品课程《多媒体技术 应用》，获国家教学进步二等奖。 第 2 期 欧伟奇，等：一种基于 Multi-Egocentric 视频运动轨迹重建的多目标跟踪算法 ·253·