基于Hough变换和聚类的舰艇编队队形识别算法
Warship Formation Recognition Algorithm Based on Hough Transform and Clustering
查看参考文献12篇
|
文摘
|
编队队形识别技术是反舰导弹武器系统目标识别领域中的一项重要研究内容,具有队形识别能力的反舰导弹可以有效增强对密集型舰艇编队当中重要目标的选择能力,进而直接提升导弹的命中概率和作战效能。基于Hough变换技术研究了一种舰艇编队队形识别算法,在无探测噪声影响时具有很好的识别率。当目标信息受污染较严重时,进一步采用了改进的K均值聚类算法对Hough变换后得到的积累矩阵局部峰值进行聚类处理,根据峰值聚类的结果准确提取出待识别队形的参数,从而有效抑制了探测噪声带来的不利影响。仿真结果表明,采用该算法可以正确识别出舰艇编队队形,在目标信息受污染较严重时也具有较好的识别效果,具有较好的鲁棒性。对该算法复杂度及目标指示误差对算法精度的影响进行了分析。 |
|
其他语种文摘
|
Formation recognition is an important research task in the area of target recognition for anti-ship missile weapon systems. Perfect formation recognition capability can improve the target selection of anti-ship missiles for compact warship formation, thus enhancing the hit probability and operational effectiveness of anti-ship missiles. The formation recognition algorithm is researched base on Hough transform, which has higher recognition rate without the influence of detection noise. If the target information is polluted badly, the improved K-means clustering algorithm is used to cluster the local peaks in an accumulation matrix. The shape parameters of formation to be recognized can be extracted from the clustering results so that the adverse influence due to detection noise is restrained effectively. Even though the target information is polluted badly, the algorithm has better recognition accuracy and robustness. The complexity of the algorithm and the effect of target designation error on the accuracy of the algorithm are analyzed. The simulation results show that the proposed algorithm has the perfect capability of formation recognition. |
|
来源
|
兵工学报
,2016,37(4):648-655 【核心库】
|
|
DOI
|
10.3969/j.issn.1000-1093.2016.04.011
|
|
关键词
|
飞行器控制、导航技术
;
队形识别
;
Hough变换
;
改进K均值聚类
;
峰值聚类
|
|
地址
|
海军大连舰艇学院导弹系, 辽宁, 大连, 116018
|
|
语种
|
中文 |
|
文献类型
|
研究性论文 |
|
ISSN
|
1000-1093 |
|
学科
|
自动化技术、计算机技术 |
|
基金
|
海军装备部军内科研项目
|
|
文献收藏号
|
CSCD:5720289
|
参考文献 共
12
共1页
|
|
1.
沈建锋. 舰艇队形识别目标选择算法.
火力与指挥控制,2010,35(9):98-100
|
CSCD被引
3
次
|
|
|
|
|
2.
乔冰. 基于模板匹配的战斗舰艇队形自动识别研究.
计算机仿真,2006,23(9):4-6
|
CSCD被引
7
次
|
|
|
|
|
3.
蔡益朝. 一种基于Hough变换的线型群体队型识别方法.
国防科技大学学报,2006,28(2):124-130
|
CSCD被引
3
次
|
|
|
|
|
4.
Paulino A A. Latent fingerprint matching using descriptor-based Hough transform.
IEEE Transactions on Information Forensics and Security,2013,8(1):31-45
|
CSCD被引
5
次
|
|
|
|
|
5.
Rodriguez L A F. Obstacle detection over rails using Hough transform.
2012 XVII Symposium of Image, Signal Processing, and Artificial Vision(STSIVA),2012:317-322
|
CSCD被引
1
次
|
|
|
|
|
6.
Hough P V C.
A method and means of recognizing complex patterns: US, 3069645,1962
|
CSCD被引
1
次
|
|
|
|
|
7.
Ebrahimpour R. Vanishing point detection in corridors: using Hough transform and K-means clustering.
IET Computer Vision,2012,6(1):40-51
|
CSCD被引
4
次
|
|
|
|
|
8.
Zhou T H. Enhancing the randomized Hough transform with k-means clustering to detect mutually-occluded ellipses.
Proceedings of 19th Mediterranean Conference on Control & Automation,2011:1358-1363
|
CSCD被引
1
次
|
|
|
|
|
9.
Yu S. Optimized data fusion for kernel K-means clustering.
IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(5):1031-1039
|
CSCD被引
20
次
|
|
|
|
|
10.
钮建伟. 基于形状的三维头面型聚类分析.
兵工学报,2009,30(8):1084-1088
|
CSCD被引
1
次
|
|
|
|
|
11.
杨善林. K-means算法中的k值优化问题研究.
系统工程理论与实践,2006,26(2):97-101
|
CSCD被引
68
次
|
|
|
|
|
12.
祁亚芳. 一种改进的随机Hough变换检测圆的方法.
数学的实践与认识,2014,44(17):189-195
|
CSCD被引
1
次
|
|
|
|
|
了解气象卫星更多信息，请访问