發(fā)布時(shí)間：2018-04-24 03:04

  本文選題：合成孔徑雷達(dá) + 貝葉斯集成算法�。� 參考：《中國(guó)電子科學(xué)研究院學(xué)報(bào)》2017年01期

【摘要】：SAR圖像目標(biāo)識(shí)別已經(jīng)廣泛的應(yīng)用在眾多領(lǐng)域,但是其對(duì)方位角較強(qiáng)的敏感性,會(huì)對(duì)識(shí)別結(jié)果造成較大的影響。特別地,同一類(lèi)目標(biāo)數(shù)據(jù)可能會(huì)因?yàn)椴煌谋憩F(xiàn)形式產(chǎn)生錯(cuò)誤的識(shí)別的結(jié)果。而貝葉斯集成方法可以對(duì)不同的分類(lèi)個(gè)體進(jìn)行單獨(dú)學(xué)習(xí),并且因此獲得不同的分類(lèi)器,從而可以有效提高SAR圖像識(shí)別準(zhǔn)確率。在本文中,提出的基于一種集成算法的SAR目標(biāo)識(shí)別方法,可以有效的解決上述問(wèn)題。電磁仿真計(jì)算獲得SAR圖像包含多方位角,并從中進(jìn)行特征提取。然后再將原始的訓(xùn)練樣本集進(jìn)行分組,每一個(gè)訓(xùn)練樣本組可作為訓(xùn)練樣本子集。這樣就可以根據(jù)這些子集作為不同個(gè)體,從而得到不同的貝葉斯集成框架。并根據(jù)得到的框架完成識(shí)別,得到最終的識(shí)別結(jié)果。
[Abstract]:SAR image target recognition has been widely used in many fields, but its strong sensitivity to azimuth will have a great impact on the recognition results. In particular, the same class of target data may result in incorrect recognition due to different representations. Bayesian ensemble method can be used to study individual classifiers and obtain different classifiers, which can effectively improve the accuracy of SAR image recognition. In this paper, the proposed SAR target recognition method based on an ensemble algorithm can effectively solve the above problems. The electromagnetic simulation results show that the SAR images contain multiple azimuth angles and extract features from them. Then the original training sample set is grouped, and each training sample group can be used as a training sample subset. In this way, different Bayesian integration framework can be obtained by using these subsets as different individuals. Finally, the final recognition results are obtained according to the obtained framework.
【作者單位】： 中國(guó)電子科學(xué)研究院;
【分類(lèi)號(hào)】：TN957.52

【參考文獻(xiàn)】

相關(guān)期刊論文 前2條

1 王金泉;李欽富;;基于SAR圖像的自動(dòng)目標(biāo)識(shí)別系統(tǒng)設(shè)計(jì)與實(shí)現(xiàn)[J];中國(guó)電子科學(xué)研究院學(xué)報(bào);2012年03期

2 緱水平;焦李成;張向榮;;基于免疫克隆的核匹配追蹤集成圖像識(shí)別算法[J];模式識(shí)別與人工智能;2009年01期

【共引文獻(xiàn)】

相關(guān)期刊論文 前8條

1 陳博;王s，

本文編號(hào)：1794831