[1]欧伟奇,尹辉,许宏丽,等.一种基于Multi-Egocentric视频运动轨迹重建的多目标跟踪算法[J].智能系统学报,2019,14(02):246-253.[doi:10.11992/tis.201709003]
 OU Weiqi,YIN Hui,XU Hongli,et al.A multi-object tracking algorithm based on trajectory reconstruction on multi-egocentric video[J].CAAI Transactions on Intelligent Systems,2019,14(02):246-253.[doi:10.11992/tis.201709003]
点击复制

一种基于Multi-Egocentric视频运动轨迹重建的多目标跟踪算法(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第14卷
期数:
2019年02期
页码:
246-253
栏目:
出版日期:
2019-03-05

文章信息/Info

Title:
A multi-object tracking algorithm based on trajectory reconstruction on multi-egocentric video
作者:
欧伟奇12 尹辉12 许宏丽12 刘志浩12
1. 北京交通大学 计算机与信息技术学院, 北京 100044;
2. 北京交通大学 交通数据分析与挖掘北京市重点实验室, 北京 100044
Author(s):
OU Weiqi12 YIN Hui12 XU Hongli12 LIU Zhihao12
1. Department of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China;
2. Beijing Key Lab of Transportation Data Analysis and Mining, Beijing Jiaotong University, Beijing 100044, China
关键词:
Multi-egocentric视频轨迹重建多目标跟踪单应性约束对极几何约束空间重构卡尔曼滤波运动模型
Keywords:
Multi-Egocentric videotrajectory reconstructionmulti-object trackinghomographic constraintepipolar geometry constraintspatial reconstructionKalman filtermotion model
分类号:
TP391.4
DOI:
10.11992/tis.201709003
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。
Abstract:
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.

参考文献/References:

[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 ?1 minimization[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 of 2016 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.

相似文献/References:

[1]李龙,尹辉,许宏丽,等.一种鲁棒的Multi-Egocentric视频中的多目标检测及匹配算法[J].智能系统学报,2016,11(5):619.[doi:10.11992/tis.201603050]
 LI Long,Yin Hui,XU Hongli,et al.A robust multi-object detection and matching algorithmfor multi-egocentric videos[J].CAAI Transactions on Intelligent Systems,2016,11(02):619.[doi:10.11992/tis.201603050]

备注/Memo

备注/Memo:
收稿日期:2017-09-05。
基金项目:国家自然科学基金项目(61472029,61473031);科技部国家重点研发计划项目(2017YFB1201104,2016YFB1200100);中央高校基本科研业务费专项资金项目(2016JBZ005).
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。
通讯作者:尹辉.E-mail:hyin@bjtu.edu.cn
更新日期/Last Update: 2019-04-25