本文選題：機(jī)動(dòng)目標(biāo)跟蹤　切入點(diǎn)：支持向量回歸　出處：《南京理工大學(xué)學(xué)報(bào)》2017年02期

【摘要】：針對(duì)強(qiáng)機(jī)動(dòng)性車輛目標(biāo)的運(yùn)動(dòng)建模、控制輸入建模和噪聲建模的不精確導(dǎo)致的汽車?yán)走_(dá)目標(biāo)跟蹤濾波精度低的問題,該文提出了基于支持向量回歸(SVR)的機(jī)動(dòng)目標(biāo)跟蹤濾波新方法。在常加速度(CA)模型的基礎(chǔ)上,對(duì)理論新息協(xié)方差與實(shí)際新息協(xié)方差殘差的Frobenius范數(shù)在線學(xué)習(xí),獲得過程噪聲協(xié)方差的自適應(yīng)調(diào)節(jié)因子,實(shí)時(shí)調(diào)整運(yùn)動(dòng)模型。對(duì)汽車?yán)走_(dá)目標(biāo)跟蹤系統(tǒng)的仿真實(shí)驗(yàn)表明,該文算法降低了汽車?yán)走_(dá)目標(biāo)跟蹤濾波對(duì)車輛運(yùn)動(dòng)模型和噪聲模型的依賴程度,在強(qiáng)機(jī)動(dòng)目標(biāo)跟蹤濾波性能上優(yōu)于CA模型,比Singer模型具有更強(qiáng)的機(jī)動(dòng)適應(yīng)性和更高的精度。
[Abstract]:Aiming at the problem of low filtering accuracy caused by imprecision of control input modeling and noise modeling, which is caused by the motion modeling of vehicle targets with strong maneuverability, In this paper, a new method of maneuvering target tracking filtering based on support vector regression (SVR) is proposed. On the basis of constant acceleration model, the Frobenius norm of theoretical innovation covariance and real innovation covariance residuals is studied online. The adaptive adjustment factor of process noise covariance is obtained, and the motion model is adjusted in real time. The simulation results of vehicle radar target tracking system show that, The algorithm reduces the dependence of vehicle radar target tracking filtering on vehicle motion model and noise model, and is superior to CA model in strong maneuvering target tracking performance, and has stronger maneuverability and higher precision than Singer model.
【作者單位】： 南京理工大學(xué)計(jì)算機(jī)科學(xué)與工程學(xué)院;
【基金】：國家“863”高技術(shù)研究計(jì)劃資助項(xiàng)目(2015AA8106043) 國家自然科學(xué)基金(61402237;61302156)
【分類號(hào)】：TP181;U463.6;U495

【相似文獻(xiàn)】

相關(guān)期刊論文 前1條

1 鄭黎義,潘旭東,陳興無,宋海峰;機(jī)動(dòng)目標(biāo)跟蹤的自適應(yīng)相互作用多模型算法[J];強(qiáng)激光與粒子束;2005年09期

，

本文編號(hào)：1688235