[1]赵 雷,陈万忠,韩双双.一种改进的运动目标跟踪与轨迹记录算法[J].智能系统学报,2008,3(02):145-149.
 ZHAO Lei,CHEN Wan-zhong,HAN Shuang-shuang.An improved algorithm for tracking and recording moving targets[J].CAAI Transactions on Intelligent Systems,2008,3(02):145-149.
点击复制

一种改进的运动目标跟踪与轨迹记录算法(/HTML)
分享到:

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

卷:
第3卷
期数:
2008年02期
页码:
145-149
栏目:
出版日期:
2008-04-25

文章信息/Info

Title:
An improved algorithm for tracking and recording moving targets
文章编号:
1673-4785(2008)02-0145-05
作者:
赵  雷 陈万忠 韩双双
吉林大学通信工程学院, 吉林长春130025
Author(s):
ZHAO Lei CHEN Wan-zhong HAN Shuang-shuang
College of Communication Engineering, Jilin University, Changchun 130025, Chin a
关键词:
运动轨迹记录跟踪主动轮廓算法三帧差分算法Hau sdorff匹配算法
Keywords:
recording and tracking of moving objects Snake algorithm threeframe differencing Hausdorff matching
分类号:
TP391
文献标志码:
A
摘要:
针对目前运动目标的跟踪与记录方法占用存储空间较大的缺点,提出了一种减少存储空间的记录算法,即先用三帧差分算法和Snake算法相结合检出运动物体的轮廓,再利用H ausdorff算法对提出的轮廓进行匹配,并将匹配后的轮廓和运动轨迹以文本文件存储,大大降低了运动目标轨迹记录存储容量.实际运用表明,改进后的记录存储空间相当于通常视频文件的万分之一.该算法适于长时间记录运动目标轨迹.
Abstract:
At present,data from tracking moving targets consumes too much memory. An improved recording algorithm is proposed that reduces memory requirements. First, initial points are obtained by using a threeframe difference algorithm. Then the Snake algorithm is used to extend the initial points to determine the object’s contour. Finally, the Hausdorff distance measurement matches contours to standard figures and the results are saved in a text file. The improved algorithm uses approximately 0.01% of the usual memory required, so it is suitable for storing data from longterm tracking.

参考文献/References:

[1]丁贵宝. 多媒体数据压缩标准化的现状与发展[J].计算机工程与应用, 2002 , 38(1):104107.
DING Guibao. The present situation and development of the multimedia data comp ression standard[J]. Computer Engineering and Applications, 2002, 38(1):1041 07.
[2]王兴国. 压缩域MPEG2到MPEG4视频转码中不匹配宏块的复原算法[J].电子学报, 2002, 30(9):14051408.
 WANG Xingguo. Robust mode mismatch macroblock retrieval algorithm for transcodin g MPEG2 to MPEG4 in compression domain[J]. Acta Electronica Sinica, 2002, 30(9):14051408.
 [3]胡炯炯. 基于形态学约束的BSnake模型的细胞图像自动分割方法[J].中国图象图形学报, 2005, 10(1):585589.
 HU Jiongjiong. Automatic cell image segmentation based on BSnake model with co nstraint of morpholog[J]. Journal of Image and Graphicsy, 2005, 10(1): 58558 9. 
[4]郭礼华. 基于直方图的Snake视频对象跟踪算法[J].中国图象图形学报, 200 5, 10( 2):197202.
 GUO Lihua. Video object tracking method based on snake model using object’s hist ogram information[J] .Journal of Image and Graphics, 2005, 10(2):197202.
[5]王成儒. 基于差分交集的视频对象分割与跟踪算法[J].中国图象图形学报, 2004, 30(9):564570.
 WANG Chengru. Video object segmentation and tracking algorithm based on differen ce and intersection[J].Journal of Image and Graphics, 2004, 30(9):564570.
[6]张文涛. 高速运动可视多目标精确检测研究[J].电子与信息学报, 2001, 23 (4):354359.
ZHANG Wentao. Accurate regiou detection of highspeed multitarget visual syst em[J]. Journal of Electronics and Information Technology, 2001, 23(4):354359 .
[7]张良国. 基于Haudorff距离的手势识别[J].中国图象图形学报, 2002, 7(11 ):11441150.
 ZHANG Liangguo. Hand gesture recognition based on Hausdorff distance[J]. Journ al of Image and Graphics, 2002, 7(11):11441150.
[8]LESAGE F. Experimenting level setbased snakes for contour segmentation i n radar imagery[C]// Conference Visual Information Processing IX. Orlando,USA,2000 :40414044.

相似文献/References:

[1]赵雷,陈万忠,韩双双,等.一种改进的运动目标跟踪与轨迹记录算法[J].智能系统学报,2008,3(02):54.[doi:CNKI:SUN:ZNXT.0.2008-02-014]
 ZHAO Lei,CHEN Wan-zhong,HAN Shuang-shuangCollege of Communication Engineering,et al.[J].CAAI Transactions on Intelligent Systems,2008,3(02):54.[doi:CNKI:SUN:ZNXT.0.2008-02-014]

备注/Memo

备注/Memo:
收稿日期:2007-10-26.
基金项目:吉林省科技发展计划资助项目(20060531)
作者简介:
赵 雷,男,1982年生,硕士研究生,主要研究方向为信号与信息处理.
陈万忠,男,1963年生,教授,教育部电子信息类教学协作委员会委员,主要研究方向为信号与信息处理及其应用技术,获2006年汽车工业科学技术进步奖1项,近3年发表论文12篇,EI检索3篇,ISTP检索3篇,主编教材1部.
 韩双双,男,1983年生,硕士研究生,主要研究方向为信号与信息处理.
通讯作者:韩双双.E-mail:shuang1017@163.com.
更新日期/Last Update: 2009-05-11