發(fā)布時間：2018-10-08 16:29

【摘要】：針對低檢測概率下多目標(biāo)跟蹤時,概率假設(shè)密度濾波器難以正確估計當(dāng)前目標(biāo)個數(shù)以及目標(biāo)狀態(tài)問題,提出一種基于多幀融合的高斯混合概率假設(shè)密度濾波算法。根據(jù)不同時刻目標(biāo)權(quán)值構(gòu)造目標(biāo)多幀權(quán)值記錄集及目標(biāo)狀態(tài)抽取標(biāo)志。當(dāng)某些時刻目標(biāo)被漏檢時,依據(jù)目標(biāo)狀態(tài)抽取標(biāo)志,并結(jié)合目標(biāo)多幀權(quán)值記錄集中權(quán)值信息估計丟失目標(biāo)的狀態(tài)。仿真實驗表明,算法有效地提高了低檢測概率下現(xiàn)有相關(guān)算法的目標(biāo)狀態(tài)和數(shù)目估計精度。
[Abstract]:In order to solve the problem that it is difficult for the probability assumption density filter to estimate the number of targets and the state of the target under low detection probability, a new algorithm of Gao Si hybrid probability assumption density filter based on multi-frame fusion is proposed. According to the target weights at different times, the target multi-frame weight record set and the target state extraction mark are constructed. When the target is missed at some time, the state of the lost target is estimated by extracting the target state and combining the weight information of the target multiple frame weight record set. Simulation results show that the algorithm can effectively improve the target state and number estimation accuracy of the existing algorithms under low detection probability.
【作者單位】： 商丘職業(yè)技術(shù)學(xué)院;
【基金】：河南省高等學(xué)校重點科研基金資助項目(16A520066;17A520052)
【分類號】：TN713

【相似文獻(xiàn)】

相關(guān)期刊論文 前3條

1 程源;多幀疊加及中值濾波在微光圖像降噪中的應(yīng)用[J];無線電通信技術(shù);1997年03期

2 李懷瓊;陳錢;隋修寶;劉強(qiáng);;多幀累加平均技術(shù)在紅外實時圖像處理中的應(yīng)用[J];激光與紅外;2005年12期

3 劉艷萍;;基于X光機(jī)的多幀PCB圖像去噪算法的研究[J];現(xiàn)代計算機(jī)(專業(yè)版);2012年25期

，

本文編號：2257461