[1]盛平,倪冬玮,张净.动态目标跟踪与自动特写快照系统的设计及实现[J].东南大学学报(自然科学版),2011,41(5):967-972.[doi:10.3969/j.issn.1001-0505.2011.05.014]
 Sheng Ping,Ni Dongwei,Zhang Jing.Design and realization of dynamic target tracking and automatic close-up snapshot[J].Journal of Southeast University (Natural Science Edition),2011,41(5):967-972.[doi:10.3969/j.issn.1001-0505.2011.05.014]
点击复制

动态目标跟踪与自动特写快照系统的设计及实现()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
41
期数:
2011年第5期
页码:
967-972
栏目:
计算机科学与工程
出版日期:
2011-09-20

文章信息/Info

Title:
Design and realization of dynamic target tracking and automatic close-up snapshot
作者:
盛平1倪冬玮2张净3
(1 江苏大学计算机科学与通信工程学院,镇江 212013)
(2 镇江江大科茂信息系统有限责任公司,镇江 212001)
(3 江苏大学电气信息工程学院,镇江 212013)
Author(s):
Sheng Ping1Ni Dongwei2Zhang Jing3
(1 School of Computer Science and Telecommunications Engineering, Jiangsu University, Zhenjiang 212013, China)
(2 Zhengjiang Jiangda Kemao Information System Co., Ltd, Zhenjiang 212001, China)
(3 School of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013, China)
关键词:
智能视频监控运动目标背景差分PTZ跟踪快照
Keywords:
intelligent video surveillance moving object background difference PTZ tracking snapshot
分类号:
TP391.4;TN991.73
DOI:
10.3969/j.issn.1001-0505.2011.05.014
摘要:
针对现有动态跟踪和快照系统难以同时满足清晰、可靠、实时、准确的跟踪抓拍要求的缺点,提出了一种复杂度较低的新型实用动态跟踪和快照系统.采用一种快速的混合高斯背景差分法分割出运动目标,并使用投影法实现目标的精确定位; 然后采用Kalman滤波与模板匹配的方法,结合摄像机标定结果进行云台控制实现动态跟踪; 同时,在PTZ跟踪过程中,提出一种基于梯度极值结合目标实际运动矢量的方法实现目标快照的抓拍.在VC++环境中,以人体为运动目标进行测试,实验结果表明该系统实现了运动目标的动态跟踪与快照,并且具有很好的鲁棒性、实时性和清晰度.
Abstract:
The existing dynamic target tracking and snapshot system is difficult to meet the requirements of clear, reliable, real-time and accurate tracking capture simultaneously. To solve the problem, this paper proposes a new dynamic target tracking and snapshot system which is more practical and less complex. A fast mixture Gaussian background difference method is adopted to segment the moving object, and accurate target positioning is obtained by the project method. Besides, in order to achieve the purpose of dynamic tracking, the methods of Kalman filter and template matching are both applied by combining with the method of pan-tilt-zoom (PTZ) camera calibration. Meanwhile, in the PTZ tracking process, on the basis of the extreme value of gradient and the actual motion vector of the target, a method to realize the adaptive capture of clear snapshot of objectives is proposed. In VC++environment, the human body is taken as the moving target for testing. The experimental results indicate that this system has realized the purpose of dynamic target tracking and snapshot, and also has advantages of real-time, clarity and robustness.

参考文献/References:

[1] 樊尚春,周游,刘长庭.基于DSP和FPGA技术的细胞图像采集系统的设计[J].北京航空航天大学学报,2008,34(6):707-710.
  Fan Shangchun,Zhou You,Liu Changting.Design of video capture system based on FPGA[J].Journal of Beijing University of Aeronautics and Astronautics,2008,34(6):707-710.(in Chinese)
[2] Saegusa T,Maruyama T,Yamaguchi Y.How fast is an FPGA in image processing[J].IEICE Technical Report,2008,108(48):83-88.
[3] Chen S H Y,Huang Y W,Hsieh B Y.Fast video segmentation algorithm with shadow cancellation,global motion compensation and adaptive threshold techniques[J].IEEE Transactions on Multimedia,2004,6(5):732-748.
[4] 盛平,张净,倪冬玮,等.基于单运动目标的PTZ检测跟踪系统设计[J].江苏大学学报:自然科学版,2010,31(6):710-715.
  Sheng Ping,Zhang Jing,Ni Dongwei,et al.Design of PTZ detection and tracking system based on single moving object[J].Journal of Jiangsu University:Natural Science Edition,2010,31(6):710-715.(in Chinese)
[5] 王永忠,梁颜,潘泉,等.基于自适应混合高斯模型的时空背景建模[J].自动化学报,2009,35(4):371-378.
  Wang Yongzhong,Liang Yan,Pan Quan,et al.Spatiotemporal background modeling based on adaptive mixture of Gaussians[J].Acta Automatica Sinica,2009,35(4):371-378.(in Chinese)
[6] Jonathan L,Joseph A,Terveen G,et al.Evaluating collaborative filtering recommender systems[J].ACM Transactions on Information Systems,2004,22(1):5-53.
[7] Kato J,Watanabe T,Joga S,et al.An HMM/MRF based stochastic framework for robust vehicle tracking[J].IEEE Transactions on Intelligent Transportation Systems,2004,5(3):142-154.
[8] 王阿琴,杨万扣,孙长根.基于子图像的尺寸自适应mean shift 目标跟踪[J].东南大学学报:自然科学版,2010,40(sup1):131-135.
  Wang Aqin,Yang Wankou,Sun Changgen.Scale adaptable mean shift object tracking based on image fragments[J].Journal of Southeast University:Natural Science Edition,2010,40(sup1):131-135.(in Chinese)
[9] Rad R,Jamzad M.Real time classification and tracking of multiple vehicles in highways [J].Pattern Recognition Letters,2005,26(10):1597-1607.
[10] 张辉,王强,徐光祐,等.运动目标的快速检测、跟踪和判别[J].清华大学学报:自然科学版,2002,42(10):1401-1404.
  Zhang Hui,Wang Qiang,Xu Guangyou,et al.Fast detection,tracking and classification of moving objects[J].Journal of Tsinghua University:Science and Technology,2002,42(10):1401-1404.(in Chinese)

备注/Memo

备注/Memo:
作者简介:盛平(1957—),男,硕士,高级工程师,pingsheng@jlonline.com.
基金项目:江苏省社发基金资助项目(BS2005046)、镇江市产学研计划资助项目(zjczcxy200708).
引文格式: 盛平,倪冬玮,张净.动态目标跟踪与自动特写快照系统的设计及实现[J].东南大学学报:自然科学版,2011,41(5):967-972.[doi:10.3969/j.issn.1001-0505.2011.05.014]
更新日期/Last Update: 2011-09-20