一种基于Multi-Egocentric视频运动轨迹重建的多目标跟踪算法
|
摘要
Egocentric视频具有目标运动剧烈、遮挡频繁、目标尺度差异明显及视角时变性强的特点,给目标跟踪任务造成了极大的困难。本文从重建不同视角Egocentric视频中各目标的运动轨迹出发,提出一种基于Multi-Egocentric视频运动轨迹重建的多目标跟踪算法,该方法基于多视角同步帧之间的单应性约束解决目标遮挡和丢失问题,然后根据多视角目标空间位置约束关系通过轨迹重建进一步优化目标定位,并采用卡尔曼滤波构建目标运动模型优化目标运动轨迹,在BJMOT、EPLF-campus4数据集上的对比实验验证了本文算法在解决Multi-Egocentric视频多目标跟踪轨迹不连续问题的有效性。
In egocentric video, objects have the characteristics of violent motion, frequent occlusion, so it brings much trouble to carrying out the tracking task. In this paper, we propose a multi-object tracking algorithm based on the motion trajectory reconstruction of multi-egocentric video from different visual angles egocentric videos. First, this method is based on the homographic constraint of multi-view synch frames to fix position of occluded and missing object.Second, using the relative position constraint relation of multi-angle target, the trajectory is reconstructed to locate the target position. Meanwhile, the trajectory of the object is optimized by constructing the motion model of object. Then the continuous trajectory of the object is obtained and the problem of the discontinuity trajectory in multi-object tracking is resolved. In the end, the performance of proposed method has been verified by using the multi-view video dataset which is created by us.
In egocentric video, objects have the characteristics of violent motion, frequent occlusion, so it brings much trouble to carrying out the tracking task. In this paper, we propose a multi-object tracking algorithm based on the motion trajectory reconstruction of multi-egocentric video from different visual angles egocentric videos. First, this method is based on the homographic constraint of multi-view synch frames to fix position of occluded and missing object.Second, using the relative position constraint relation of multi-angle target, the trajectory is reconstructed to locate the target position. Meanwhile, the trajectory of the object is optimized by constructing the motion model of object. Then the continuous trajectory of the object is obtained and the problem of the discontinuity trajectory in multi-object tracking is resolved. In the end, the performance of proposed method has been verified by using the multi-view video dataset which is created by us.
引文
[1]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.
[2]ZHANG Lei, LI Yuan, NEVATIA R. Global data association for multi-object tracking using network flows[C]//Proceedings of 2008 IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, AK, USA, 2008:1–8.
[3]AVIDAN S. Ensemble tracking[J]. IEEE transactions on pattern analysis and machine intelligence, 2007, 29(2):261–271.
[4]XU Yuanlu, LIU Xiaobai, LIU Yang, et al. Multi-view people tracking via hierarchical trajectory composition[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA, 2016:4256–4265.
[5]HE Shengfeng, YANG Qingxiong, LAU R W H, et al.Visual tracking via locality sensitive histograms[C]//Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition. Portland, USA, 2013:2427–2434.
[6]FLEURET F, BERCLAZ J, LENGAGNE R, et al. Multicamera people tracking with a probabilistic occupancy map[J]. IEEE transactions on pattern analysis and machine intelligence, 2008, 30(2):267–282.
[7]MEI Xue, LING Haibo. Robust visual tracking using?1minimization[C]//Proceedings of the 12th IEEE International Conference on Computer Vision. Kyoto, Japan,2009:1436–1443.
[8]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.
[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[J].计算机学报, 2016, 39(7):1294–1306.WANG Yuxia, ZHAO Qingjie, CAI Yiming, et al. Tracking by auto-reconstructing particle filter trackers[J].Chinese journal of computers, 2016, 39(7):1294–1306.
[10]BAE S H, YOON K J. Robust online multi-object tracking based on tracklet confidence and online discriminative appearance learning[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition.Columbus, OH, USA, 2014:1218–1225.
[11]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.
[12]XIANG Yu, ALAHI A, SAVARESE S. Learning to track:online multi-object tracking by decision making[C]//Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago, Chile, 2015:4705–4713.
[13]NAM H, HAN B. Learning multi-domain convolutional neural networks for visual tracking[C]//Proceedings of2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA, 2016:4293–4302.
[14]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.
[15]FISCHLER M A, BOLLES R C. Random sample consensus:a paradigm for model fitting with applications to image analysis and automated cartography[J]. Communications of the ACM, 1981, 24(6):381–395.
[16]ZHANG Z. A flexible new technique for camera calibration[J]. IEEE transactions on pattern analysis and machine intelligence, 2000, 22(11):1330–1334.
[17]SCHWEIGHOFER G, PINZ A. Robust pose estimation from a planar target[J]. IEEE transactions on pattern analysis and machine intelligence, 2006, 28(12):2024–2030.
[18]BEKIR E. Adaptive Kalman filter for tracking maneuvering targets[J]. Journal of guidance, control, and dynamics,2015, 6(5):414–416.
[19]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.
[20]BERNARDI K, STIEFELHAGEN R. Evaluating multiple object tracking performance:the CLEAR MOT metrics[J]. EURASIP Journal on image and video processing,2008, 2008(1):246309.
[2]ZHANG Lei, LI Yuan, NEVATIA R. Global data association for multi-object tracking using network flows[C]//Proceedings of 2008 IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, AK, USA, 2008:1–8.
[3]AVIDAN S. Ensemble tracking[J]. IEEE transactions on pattern analysis and machine intelligence, 2007, 29(2):261–271.
[4]XU Yuanlu, LIU Xiaobai, LIU Yang, et al. Multi-view people tracking via hierarchical trajectory composition[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA, 2016:4256–4265.
[5]HE Shengfeng, YANG Qingxiong, LAU R W H, et al.Visual tracking via locality sensitive histograms[C]//Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition. Portland, USA, 2013:2427–2434.
[6]FLEURET F, BERCLAZ J, LENGAGNE R, et al. Multicamera people tracking with a probabilistic occupancy map[J]. IEEE transactions on pattern analysis and machine intelligence, 2008, 30(2):267–282.
[7]MEI Xue, LING Haibo. Robust visual tracking using?1minimization[C]//Proceedings of the 12th IEEE International Conference on Computer Vision. Kyoto, Japan,2009:1436–1443.
[8]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.
[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[J].计算机学报, 2016, 39(7):1294–1306.WANG Yuxia, ZHAO Qingjie, CAI Yiming, et al. Tracking by auto-reconstructing particle filter trackers[J].Chinese journal of computers, 2016, 39(7):1294–1306.
[10]BAE S H, YOON K J. Robust online multi-object tracking based on tracklet confidence and online discriminative appearance learning[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition.Columbus, OH, USA, 2014:1218–1225.
[11]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.
[12]XIANG Yu, ALAHI A, SAVARESE S. Learning to track:online multi-object tracking by decision making[C]//Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago, Chile, 2015:4705–4713.
[13]NAM H, HAN B. Learning multi-domain convolutional neural networks for visual tracking[C]//Proceedings of2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA, 2016:4293–4302.
[14]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.
[15]FISCHLER M A, BOLLES R C. Random sample consensus:a paradigm for model fitting with applications to image analysis and automated cartography[J]. Communications of the ACM, 1981, 24(6):381–395.
[16]ZHANG Z. A flexible new technique for camera calibration[J]. IEEE transactions on pattern analysis and machine intelligence, 2000, 22(11):1330–1334.
[17]SCHWEIGHOFER G, PINZ A. Robust pose estimation from a planar target[J]. IEEE transactions on pattern analysis and machine intelligence, 2006, 28(12):2024–2030.
[18]BEKIR E. Adaptive Kalman filter for tracking maneuvering targets[J]. Journal of guidance, control, and dynamics,2015, 6(5):414–416.
[19]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.
[20]BERNARDI K, STIEFELHAGEN R. Evaluating multiple object tracking performance:the CLEAR MOT metrics[J]. EURASIP Journal on image and video processing,2008, 2008(1):246309.