基于视频多目标跟踪的高度测量算法

doi:10.3969/j.issn.0372-2112.2015.03.026

电子学报 ›› 2015, Vol. 43 ›› Issue (3): 591-596.DOI: 10.3969/j.issn.0372-2112.2015.03.026

基于视频多目标跟踪的高度测量算法

姜明新^1,2, 王培昌², 王洪玉¹

1. 大连理工大学信息与通信工程学院, 辽宁大连 116024;
2. 大连民族学院信息与通信工程学院, 辽宁大连 116600

收稿日期:2013-07-15 修回日期:2013-10-09 出版日期:2015-03-25
- 作者简介:
- 姜明新 女,1979年出生于黑龙江省.博士,大连民族学院信息与通信工程学院讲师.研究方向为计算机视觉、智能视频监控. E-mail:jmx@dlnu.edu.cn;王培昌 男,1955年出生于辽宁省大连市.博士,大连民族学院信息与通信工程学院教授.研究方向为计算机视觉、计算机控制与检测技术. E-mail:wpc@dlnu.edu.cn;王洪玉 男,1968年出生.大连理工大学信息与通信工程学院教授,博士生导师.研究方向无线传感器网络、计算机视觉.
- 基金资助:
- 国家自然科学基金项目 (No.61172058,No.61403060); 中央高校自主基金 (No.DC110321); 辽宁省教育厅资助项目 (No.L2012476); 中国博士后科学基金资助项目 (No.2014M551081); 大连民族学院人才引进项目 (No.20136212)

Height Estimation Algorithm Based on Visual Multi-Object Tracking

JIANG Ming-xin^1,2, WANG Pei-chang², WANG Hong-yu¹

1. School of Information and Communication Engineering, Dalian University of Technology, Dalian, Liaoning 116024, China;
2. School of Information and Communication Engineering, Dalian Nationalities University, Dalian, Liaoning 116600, China

Received:2013-07-15 Revised:2013-10-09 Online:2015-03-25 Published:2015-03-25
- Supported by:
- National Natural Science Foundation of China (No.61172058, No.61403060); Initiative Fund for the Central Universities (No.DC110321); Supported by Education Department of Liaoning Province (No.L2012476); Supported by China Postdoctoral Science Foundation (No.2014M551081); Talent Introduction Project of Dalian Minzu University (No.20136212)

摘要/Abstract

摘要：

本文提出了一种基于视频多目标跟踪的高度测量算法.首先,采用码本模型检测前景,利用图割理论实现对多目标的跟踪.然后,提取每一帧中目标的头部特征点和脚部特征点,根据投影几何的约束关系计算每个目标的高度.最后,融合多帧的测量结果进行数据优化.本文提出的算法不需要对相机进行完全标定,只需计算摄像机的灭点和地平面的灭线,降低了计算的复杂度.实验结果表明,本文提出的算法具有较高的测量精度,对遮挡和运动状态变化具有较强的鲁棒性,同时,能够满足实时性要求.

关键词: 高度测量, 视频多目标跟踪, 投影几何约束, 图割

Abstract:

In this paper, we propose a height estimation algorithm based on visual multi-object tracking.Firstly, the foreground is detected by using codebook modeling algorithm, and multi-object tracking is performed by using graph cuts.Then, the head feature points and the feet feature points of objects are extracted in each frame, and the height of every object is computed according to projective geometry constraint.Finally, data optimization is performed by fusing multi-frame measurement results.This method does not require full camera calibration, but require computing the vanishing point of camera and the vanishing line of ground.Using this method, the computational complexity can be reduced.The experimental results demonstrate that our method has higher measurement accuracy, and is robust to occlusion and the changing of motion state.Meanwhile, it can also achieve real-time performance.

Key words: height estimation, visual multi-object tracking, projective geometry constraint, graph cuts

中图分类号:

TP391

姜明新, 王培昌, 王洪玉. 基于视频多目标跟踪的高度测量算法[J]. 电子学报, 2015, 43(3): 591-596.

JIANG Ming-xin, WANG Pei-chang, WANG Hong-yu . Height Estimation Algorithm Based on Visual Multi-Object Tracking[J]. Acta Electronica Sinica, 2015, 43(3): 591-596.

参考文献

[1] Shao J, Zhou S K, Chellappa R.Robust height estimation of moving objects from uncalibrated videos[J].IEEE Transactions on Image Processing, 2010, 19(8):2221-2232.
[2] 董秋雷, 吴毅红, 胡占义.基于视频的实时自动人体高度测量[J].自动化学报, 2009, 35(2):137-144. Dong Q L, Wu Y H, Hu Zh Y.Video-based real-time automatic measurement for the height[J].Acta Automatica Sinica, 2009, 35(2):137-144.(in Chinese)
[3] Chellappa R, Turaga P K.Recent advances in age and height estimation from still images and video[A].IEEE International Conference on Automatic Face & Gesture Recognition[C].Santa Barbara, California:IEEE, 2011.91-96.
[4] Guo F, Chellappa R.Video metrology using a single camera[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(7):1329-1335.
[5] 魏玮, 吕艳, 石可红.监控视频关键帧的人体高度测量算法[J].计算机系统应用, 2012, 21(6):195-198. Wei W, Lv Y, Shi K H.Body height measurement algorithm in key frame from surveillance video[J].Computer Systems & Applications, 2012, 21(6):195-198.(in Chinese)
[6] Benabdelkader C, Yacoob Y.Statistical body height estimation from a single image[A].IEEE International Conference on Automatic Face & Gesture Recognition[C].Amsterdam, Netherlands:IEEE, 2008.1-7.
[7] Chen Z, Pears N, Liang B.A method of visual metrology from uncalibrated images[J].Pattern Recognition Letters, 2006, 27(13):1447-1456.
[8] Momeni-K M, Diamantas S Ch, Ruggiero F, Siciliano B.Height estimation from a single camera view[A].Proceedings of the International Conference on Computer Vision Theory and Applications(Volume 1)[C].Rome, Italy:SciTe Press, 2012.358-364.
[9] Park S W, Kim T, Choi J S.Robust estimation of heights of moving people using a single camera[A].Proceedings of the International Conference on IT Convergence and Security[C].Pyeong Chang, Korea:Springer, 2012.389-405.
[10] Boykov Y, Veksler O, Zabih R.Fast approximate energy minimization via graph cuts[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(11):1222-1239.
[11] Papadakis N, Bugeau A.Tracking with Occlusions via Graph Cuts [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(1):144-157.
[12] Boykov Y, Kolmogorov V.An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(9):1124-1137.
[13] Kim K, Chalidabhongse T H, Harwood D, Davis L.Real-Time foreground-background segmentation using codebook model[J].Real-Time Imaging, 2005, 11(3):167-256.
[14] Criminisi A, Reid I, Zisserman A.Single view metrology[J].International Journal Computer Vision, 2000, 40(2):123-148.
[15] 吴朝福著.计算机视觉中的数学方法[M]:北京:科学出版社, 2008.68-80.
[16] Hartley R, Zisserman A.Multipleview geometry in computer vision[M].Second Edition.Cambridge:Cambridge University Press, 2003.363-406.
[17] Rother C.A new approach for vanishing point detection in architectural environments[J].Image and Vision Computing, 2002, 20(9):647-655.
[18] Lv F, Zhao T, Nevatia R.Camera calibration from video of a walking human[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(9):1513-1518.

基于视频多目标跟踪的高度测量算法

Height Estimation Algorithm Based on Visual Multi-Object Tracking

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 8

编辑推荐

Metrics

[1]	袁红星, 安鹏, 吴少群, 郑悠. 具有容错能力的L₁最优化半自动2D转3D[J]. 电子学报, 2018, 46(2): 447-455.
[2]	葛婷, 牟宁, 李黎. 基于softmax回归与图割法的脑肿瘤分割算法[J]. 电子学报, 2017, 45(3): 644-649.
[3]	李磊, 董卓莉, 张德贤, 费选. 基于区域限制的EM和图割的非监督彩色图像分割方法[J]. 电子学报, 2016, 44(6): 1349-1354.
[4]	施文灶, 毛政元. 基于图割与阴影邻接关系的高分辨率遥感影像建筑物提取方法[J]. 电子学报, 2016, 44(12): 2849-2854.
[5]	吴少群, 袁红星, 安鹏, 程培红. 软分割约束边缘保持插值的半自动2D转3D[J]. 电子学报, 2015, 43(11): 2218-2224.
[6]	李昱川;田铮;刘向增;徐海霞. SAR图像多尺度配准的小波域最小割模型方法[J]. 电子学报, 2010, 38(9): 2122-2127.
[7]	吴亚东, 孙世新, 张红英, 韩永国, 陈波. 一种基于图割的全变差图像去噪算法[J]. 电子学报, 2007, 35(2): 265-268.
[8]	王年, 范益政, 鲍文霞, 韦穗, 梁栋. 基于图割的图像匹配算法[J]. 电子学报, 2006, 34(2): 232-236.