中國民航大學 電子信息工程學院，天津 300300
摘要：針對多傳感器系統某一時刻融合中心接收到多部傳感器對同一目標的量測數據呈團狀，且大致分布在目標真實值的周圍的現象，為了區分源于不同目標的數據以實現目標跟蹤，提出了一種基于自適應選取初始聚類中心的k-means算法與修正的邏輯法相結合的多傳感器航跡起始算法。算法通過合理選擇度量兩個量測數據不相似性的閾值，自適應的確定聚類數目和初始聚類中心，將多傳感器的航跡起始問題簡化為單傳感器的航跡起始問題；然后對聚類后的數據采用修正的邏輯航跡起始算法起始目標航跡。仿真結果表明，本文所提出的自適應k-means聚類算法能正確的區分不同目標，且識別出的目標與真實目標非常接近，聚類處理后再進行目標航跡起始不僅能有效地濾除部分雜波，降低虛警概率，而且航跡起始效果也較好。
關鍵詞： K-means 聚類；聚類中心；自適應；相似性度量；閾值；航跡起始
Algorithm of Multi-sensor Track Initiation Based on K-means Clustering
GONG Fengxun, DAI Lihua
School of Electronics and Information Engineering, civil aviation university of China, Tianjin 300300, China
Abstract: According to the feature that the measurements of the same target at the same time have spherical shape, an algorithm of track initiation based on adaptive k-means clustering and modified logic-based approach is proposed in this paper. The improved k-means clustering algorithm can determine the cluster number and the initial cluster centers adaptively. Then the center of each cluster is found and taken as the measurement of the targets at this moment. By doing so, the track initiation process is simplified. According to the target’s movement characteristic, a modified logic-based method is used to initiate the target track. Simulation results show that the improved k-means clustering algorithm can recognize the number of targets correctly and the recognized targets are close to the true targets; the modified logic-based approach can effectively suppresses clutter and reduces the probability of false alarm.
Key words: K-means clustering; cluster center; adaptive; similarity measure; threshold; Track initiation
參考文獻：
[1] 吳 丹，馮新喜。多雷達多目標航跡起始算法研究[J]�？哲姽こ檀髮W學報（自然科學版），2006,7(1)：16-19.
[2] Xiaoping Qing, Shijue Zheng. A new method for initialising the K-means clustering algorithm[C]. 2009 Second International Symposium on Knowledge Acquisition and Modeling.
[3] Shi Na, Liu Xumin, Guan Yong. Research on k-means Clustering Algorithm: An Improved k-means Clustering Algorithm[C]. Third International Symposium on Intelligent Information Technology and Security Informatics, 2010.
[4] Gregory A. Wilkin, Xiuzhen Huang. K-Means Clustering Algorithms: Implementation and Comparison[C]. Second International Multi-symposium on Computer and Computational Sciences, 2007.
[5] 周士兵，徐振源，唐旭清。K-means算法最佳聚類數確定方法[J]。計算機應用，2010,30(8)：1995-1998.
[6] 蒲 勇，袁富宇，苗 艷。常用航跡初始化技術分析[J]。指揮控制與仿真，2008,28(1)：98-101.
[7] 蘇 峰，王國宏。修正的邏輯航跡起始算法[J]�，F代防御技術，2004，32(5)： 66-68.
[8] 湯 琦，黃建國，楊旭東。航跡起始算法及性能仿真[J]。系統仿真學報，2007,19(1)：149-152.
[9] Chen Xiaowei, Lin Jiajun, Zhang Jie. Performance Analysis of Track Initiation Algorithm[C]. Proceedings of the 6th World Congress on Intelligent Control and Automation, June 21-23, 2006, Dalian, China.
[10] 何 友，王國宏等。多傳感器信息融合及應用[M]，北京：電子工業出版社，2010.
[11] 何 友，修建娟，張晶煒，關 欣等。雷達數據處理及應用[M]，北京：電子工業出版社，2006.
[12] 金術玲，梁 彥，潘 泉，程永梅�；贖ough變換和聚類的航跡起始算法[J]。系統仿真學報，2009，21(8)：2362-2364.
