[1]龙迎春,冯健业,宋玉春.基于状态分割的运动目标实时跟踪[J].机械与电子,2018,(06):21-24.
LONG Yingchun,FENG Jianye,SONG Yuchun.Real Time Tracking for Moving Objects Based on State Segmentation Method[J].Machinery & Electronics,2018,(06):21-24.
点击复制
基于状态分割的运动目标实时跟踪()
机械与电子[ISSN:1001-2257/CN:52-1052/TH]
- 卷:
-
- 期数:
-
2018年06期
- 页码:
-
21-24
- 栏目:
-
设计与研究
- 出版日期:
-
2018-06-24
文章信息/Info
- Title:
-
Real Time Tracking for Moving Objects Based on State Segmentation Method
- 文章编号:
-
1001-2257(2018)06-0021-04
- 作者:
-
龙迎春; 冯健业; 宋玉春
-
(韶关学院物理与机电工程学院,广东 韶关 512005)
- Author(s):
-
LONG Yingchun; FENG Jianye; SONG Yuchun
-
(School of Physics and Mechanical and Electrical Engineering, Shaoguan University, Shaoguan 512005, China)
-
- Keywords:
-
video surveillance; moving object detection and tracking; state segmentation; background subtraction; Camshift algorithm; OpenCV
- 分类号:
-
TP391.4
- 文献标志码:
-
A
- 摘要:
-
针对基于云台的移动式摄像头视频监控系统,为准确、实时地对运动目标实施检测、跟踪,提出了一种基于状态分割思想的运动目标实时跟踪方法。该方法将运动目标检测跟踪过程按摄像头的运动状态分为静止、运动2个阶段。在摄像头静止阶段,采用基于混合高斯模型的背景差法检测运动目标,提取目标的颜色特征信息;在摄像头运动阶段,采用Camshift算法对运动目标进行跟踪。开发了基于 OpenCV 开源库的算法程序。实验结果表明,在目标颜色特征显著的情况下,该方法实现了移动式摄像头对运动目标的精确跟踪,并具有较好的鲁棒性和实时性。
- Abstract:
-
In order to optimize the video surveillance system for detecting and tracking the moving object accurately, a real-time tracking method for moving object based on state segmentation is proposed. This method divides the tracking process into two phases, namely, the static and motion phases, according to the state of the camera. In the static phase of the camera, the background subtraction based on Gaussian mixture model is used to detect the moving object, and the color features of the object is extracted.?In the camera motion stage,?the Camshift algorithm is applied to track the moving object. An algorithm program based on the OpenCV open source library is also developed in this study.?The experiment shows that the proposed method has good robustness and can accurately track the moving object with significant color features in real-time
参考文献/References:
[1].黄凯奇,陈晓棠,康运锋等.智能视频监控技术综述[J].计算机学报,2015,38(6):1093-1118.
[2].陈杏源,郑烈心,裴海龙.基于Camshift和SURF的目标跟踪系统[J].计算机工程与设计,2016,37(4):902-906.
[3].兰红,周伟,齐彦丽.动态背景下的稀疏光流目标提取与跟踪[J].中国图象图形学报,2016,21(6):771-780.
[4].崔智高,王华,李艾华等.动态背景下基于光流场分析的运动目标检测算法[J].物理学报,2017,66(8):116-123.
[5].于明,孙炜烨,阎刚等.动态场景下基于精确背景补偿的运动目标检测[J].计算机应用与软件,2013,30(10):139-141198.
[6].王文胜,翟尚礼,白俊奇.基于SSDA的图像匹配跟踪算法[J].指挥信息系统与技术,2016,7(6):77-80.
[7].Lowe D G.Distinctive image features from scale-invariant keypoints[J].International journal of computer vision,2004,60(2):91-110.
[8].Kalia R,Lee K D,Samir B V R,et al.An analysis of the effect of different image preprocessing techniques on the performance of SURF: Speeded up robust features[C]//17th Korea-Japan Joint Workshop on Frontiers of computer Vision,2001:1-6.
[9].施家栋,王建中.动态场景中运动目标检测与跟踪[J].北京理工大学学报,2009,29(10):858-860876.
[10].Stauffer C, Grimson W.Adaptive background mixture models for real-time tracking [C]//Proceedings of the 1999 IEEE Conference on Computer Vision and Pattern Recognition,1999: 246-252.
[11].Comaniciu D,Ramesh V,Meer P. Real-time tracking of non-rigid objects using mean shift//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2000:142-149.
[12].梁锡宁,杨刚,余学才等.一种动态模板匹配的卡尔曼滤波跟踪方法[J]. 光电工程,2010,37(10): 29-33.
[13].李轩, 张红.基于粒子滤波的检测前跟踪算法的改进[J].科学技术与工程,201717(30) :227-232.
[14].Bradski G R.Real time face and object tracking as a component of a perceptual user interface[C]//Proceedings of the fourth IEEE workshop on applications of computer vision,1998:214-219.
[15].李振伟,陈翀,赵有.基于OpenCV的运动目标跟踪及其实现[J].现代电子技术,2008(20):128-130,138.
备注/Memo
- 备注/Memo:
-
收稿日期:2018-03-08
基金项目: 广东省高校国际暨港澳台合作创新平台项目广东省大学生创新创业训练计划项目
作者简介:龙迎春(197),男,副教授,研究方向为机电系统控制及智能化技术。
更新日期/Last Update:
2019-10-30