一种基于聚类的深空红外多目标快速检测算法

叶有时; 唐林波; 赵保军

doi:10.3724/SP.J.1146.2010.00175

一种基于聚类的深空红外多目标快速检测算法

doi: 10.3724/SP.J.1146.2010.00175

基金项目:

国家863计划项目(2008AA8012320B)资助课题

计量
- 文章访问数: 3509
- HTML全文浏览量: 98
- PDF下载量: 915
- 被引次数: 0
出版历程
- 收稿日期: 2010-03-01
- 修回日期: 2010-06-28
- 刊出日期: 2011-01-19

A Fast Deep-space Infrared Multi-target Detection Algorithm Based on Clustering

摘要

摘要: 该文提出一种基于行扫描点线目标聚类合并的快速实时多目标检测算法。该方法首先对原始图像进行自适应阈值分割，然后采用外接矩补形，点线目标提取和聚类合并对二值图像单帧目标进行全视场检测并编号标记，精度达到像素级，避免了帧差法，投影法等传统检测算法带来的漏检。最后应用五点二次滤波预测目标位置，并构造代价函数进行关联匹配完成目标确认，有效解决了检测中目标分裂，交叉，因重合而暂时消失等问题，提高了系统检测能力。在基于SOPC的硬件平台进行验证，实验结果表明该算法能够准确实时地检测深空目标。
- 深空多目标检测 /
- 外接矩补形 /
- 聚类合并 /
- 片上可编程系统
Abstract: This paper presents a fast real-time multi-target detection algorithm based on line target clustering. Adaptive threshold is applied to image segmentation; And then enclosing rectangle prosthetics, line target extraction and clustering merger are utilized for the binary image to implement full-field pixel-level targets detection and conduct ID tag. So undetected problems caused by the traditional detection algorithm can be avoid; Finally, a five points square predictor and cost function are constructed for trajectory matching, by which the problems of multi-target division, cross, temporarily lost due to overlap and so on are effectively resolved. The experiments are carried on SOPC hardware platform and the results show that the proposed algorithm can perform real-time detection accurately for the deep-space objects.
- Deep-space multi-target detection /
- Enclosing rectangle prosthetics /
- Clustering merger /
- SOPC (System On Programmable Chip)

HTML全文

参考文献(1)

李毅, 孙正兴, 远博. 一种改进的帧差和背景减相结合的运动检测方法[J]. 中国图象图形学报, 2009, 14(6): 1162-1168.Li Yi, Sun Zheng-xing, and Yuan Bo. An improved method for motion detection by frame difference and background subtraction [J]. Journal of Image and Graphics, 2009, 14(6): 1162-1168.[2]王兆魁, 张育林. 一种CCD星图星点快速定位算法[J]. 空间科学学报, 2006, 26(3): 209-214.Wang Zhao-kui and Zhang Yu-lin. Algorithm for CCD star image rapid locating[J]. Chinese Journal of Space Science, 2006, 26(3): 209-214.[3]Fejes S and Davis L S. What can projections of flow fields tell us about the visual motion [C]. Proceeding of International Conference on Computer Vision, Bombay, India, 1998: 979-986.[4]王勇，赵保军. 复杂背景下低信噪比点目标的实时检测算法及实现[J]. 系统工程与电子技术, 2002, 24(12): 18-21.Wang Yong and Zhao Bao-jun. A real-time detection algorithm for low SNR point targets in a complex background [J]. Systems Engineering and Electronics, 2002, 24(12): 18-21.[5]孙吉贵, 刘杰, 赵连宇. 聚类算法研究[J]. 软件学报, 2008, 19(1): 48-61.Sun Ji-gui, Liu Jie, and Zhao Lian-yu. Clustering algorithms research [J].Journal of Software.2008, 19(1):48-61[6]王春歆, 沈同圣, 张玉叶. 基于层次聚类的弱小目标检测算法[J]. 计算机工程与应用, 2008, 44(19): 24-27.Wang Chun-xin, Shen Tong-sheng, and Zhang Yu-ye. Small targets detection based on hierarchical clustering [J]. Computer Engineering and Applications, 2008, 44(19): 24-27.[7]Murat T. A. Digital Video Processing [M]. New York: Prentice-Hall Press, 1996: 206-218.[8]蔡征, 黄瑞光. 运动图像序列的多目标跟踪技术及实现[J]. 计算机与数字工程, 2006, 34(9): 140-143.Cai Zheng and Huang Rui-guang. The research and implementation on multi-target tracking in image sequences[J].Computer Digital Engineering.2006, 34(9):140-143[9]刘玉琏. 数学分析: 下册 [M]. 北京: 高等教育出版社, 2008: 189-208.

施引文献

资源附件(0)

访问统计