基于颜色传递的双波段目标跟踪算法研究

何永强; 周云川; 任宏岩; 师立青

基于颜色传递的双波段目标跟踪算法研究

1.
军械工程学院光学与电子工程系,河北石家庄 050003;
2.
军械工程学院研究生管理大队,河北石家庄 050003

详细信息

通讯作者:
何永强（1966-），男，辽宁盖县人，博士，副教授，主要从事光电对抗理论与应用研究工作。

中图分类号: TN209
计量
- 文章访问数: 3183
- HTML全文浏览量: 114
- PDF下载量: 417
- 被引次数: 0
出版历程
- 刊出日期: 2012-02-15

Dual-band target tracking based on color transfer technique

1.
Department of Optics and Electronic Engineering,Ordnance Engineering College,Shijiazhuang,050003,China;
2.
Company of Postgraduate Management,Ordnance Engineering College,Shijiazhuang,050003,China

摘要

摘要: 针对复杂背景下Camshift算法容易丢失目标的情况，提出一种基于YCBCR空间将红外与可见光融合图像与彩色参考图像进行颜色传递后，采用Camshift进行目标跟踪的算法。该算法在颜色传递时充分利用双波段图像信息，得到的目标对比度高并且颜色空间较其周围背景突出，增强了目标的颜色概率图，提高了Camshift算法效率。实验表明，通过对可见光图像、经颜色传递后的红外图像以及传统颜色传递方法得到的图像采用相同跟踪算法进行定性分析，在该算法得到的图像中，跟踪窗口中心相对于目标质心仅有3个像素的误差，跟踪精度远远优于对比实验图像的跟踪结果，并且算法的跟踪时间为每帧20.6 ms，达到了实时性的要求。
- 颜色传递 /
- 目标跟踪 /
- Camshift /
- 颜色直方图
Abstract: Since Camshift algorithm is easy to lose tracked object in complex background, this paper puts forward a tracking method based on Camshift algorithm, before which a color transfer technique is used between color reference image and fused image in YCBCR space. During color transfer, the proposed method used information of dual-band image effectively, and the target not only had the excellence of high contrast, but also enhanced the drawing of color probability distribution, the proposed method improved the efficiency of Camshift. The comparison of the visual image, color transferred infrared image and the traditional color transferred image was made using the same tracking method, a group of experimental results demonstrate that the distance between the center of tracking window and target centroid is just 3 pixels in the pictures based on proposed method, tracking precision outperforms the results of contrast experiment pictures. At the same time, the tracking time of the proposed method is 20.6 ms, which meets the real time requirement.
- color transfer /
- target tracking /
- Camshift /
- color histogram

HTML全文

参考文献(1)

［1］PEREZ P,HUE C,VERMAAK J,et al.Color-based probabilistic tracking［C］.Berlin:Springer-Verlag,2002.
［2］COMANICIU D,RAMESH V,MEER P. Kernel based object tracking［J］. IEEE Trans Pattern Analysis Machine Intelligence,2003,25(5):564-575.
［3］钱永青,谢勤岚. 结合Camshift和Kalman预测的运动目标跟踪［J］. 计算机工程与科学,2010,32(8):81-83.
QIAN Yong-qing,XIE Qin-lan. Camshift and Kalman predicting based on moving target tracking［J］. Computer Engineering & Science, 2010,32(8):81-83.(in Chinese with an English abstract)
［4］曲巨宝,王淑娟,林宏基. 利用Camshift 算法实现运动目标自动跟踪［J］.湖南工业大学学报,2010,24(5):58-62.
QU Ju-bao,WANG Shu-juan,LIN Hong-ji. Using Camshift algorithm to track moving objects automatically［J］. Journal of Hunan University of Technology, 2010,24(5):58-62.(in Chinese with an English abstract)
［5］吴良健,况璐,邓庆林,等. 基于 Camshift 和 Kalman 滤波结合的改进多目标跟踪算法［J］.现代科学仪器,2010,2(1):29-33.
WU Liang-jian, KUANG Lu, DENG Qing-lin, et al. Improved tracking algorithm for multiple targets based on Camshift algorithm combined with Kalman filter［J］.Modern Scientific Instruments, 2010,2(1):29-33.(in Chinese with an English abstract)
［6］李光鑫,徐抒岩,赵运隆,等.颜色传递技术的快速彩色图像融合［J］.光学精密工程,2010,18(7):1637-1645.
LI Guang-xin,XU Shu-yan,ZHAO Yun-long,et al. Fast color image fusion based on color transfer technique［J］. Optics and Precision Engineering, 2010,18(7):1637-1645.(in Chinese with an English abstract)
［7］TOET A.Natural colour mapping for multiband nightvision imagery［J］.Information Fusion,2003,4(3):155-166.
［8］童刚,陈灵芝.基于Camshift的跟踪系统的设计［J］.计算机技术与发展,2008,18(10):194-196.
TONG Gang，CHEN Ling-zhi. A tracking system design based on Camshift［J］. Computer Technology and Development,2008,18(10):194-196.(in Chinese with an English abstract)
［9］杨红颖,吴俊峰,于永健,等. 一种基HSV空间的彩色边缘图像检索方法［J］. 中国图像图形学报,2008,13(10):2035-2038.
YANG Hong-ying,WU Jun-feng,YU Yong-jian,et al. Content based image retrieval using color edge histogram in HSV color space［J］.Journal of Image and Graphics, 2008,13(10):2035-2038.(in Chinese with an English abstract)
［10］于永健,王向阳,吴俊峰. 基于颜色复杂度的加权颜色直方图图像检索算法［J］.小型微型计算机系统,2009,30(3):507-511.
YU Yong-jian,WANG Xiang-yang,WU Jun-fen. Weighted histogram color image retrieval based on color complexity measure［J］. Journal of Chinese Computer Systems,2009,30(3): 507-511.(in Chinese with an English abstract)

施引文献

资源附件(0)

访问统计