本文關(guān)鍵詞： 車輛識(shí)別 圖像質(zhì)量 高斯擬合 熵權(quán)法　出處：《計(jì)算機(jī)科學(xué)與探索》2017年01期 　論文類型：期刊論文

【摘要】：針對(duì)目前車輛識(shí)別方法在動(dòng)態(tài)變化的復(fù)雜環(huán)境中車輛識(shí)別正確率低的問(wèn)題,提出了一種基于動(dòng)態(tài)自適應(yīng)閾值的車輛識(shí)別方法。該方法首先利用基于熵權(quán)法的圖像質(zhì)量量化算法計(jì)算交通流視頻中背景圖像的質(zhì)量值;然后通過(guò)對(duì)樣本交通流設(shè)置的車輛檢測(cè)閾值和基于該閾值識(shí)別車輛的正確率進(jìn)行多項(xiàng)式擬合,獲得該樣本的車輛最佳檢測(cè)閾值;最后對(duì)樣本背景圖像的質(zhì)量值和樣本車輛的最佳檢測(cè)閾值進(jìn)行高斯擬合,得到自適應(yīng)閾值計(jì)算模型。該方法采用高斯混合模型實(shí)時(shí)獲取交通流視頻中的背景圖像,計(jì)算背景圖像的質(zhì)量值,并輸入到自適應(yīng)閾值計(jì)算模型得到實(shí)時(shí)的車輛最佳檢測(cè)閾值以識(shí)別車輛。實(shí)驗(yàn)和理論分析表明,該方法能根據(jù)動(dòng)態(tài)變化的環(huán)境實(shí)時(shí)更新車輛檢測(cè)閾值,有效地提高了車輛識(shí)別的正確率。
[Abstract]:In view of the problem that the current vehicle recognition methods have low accuracy in the dynamic and complex environment, A vehicle recognition method based on dynamic adaptive threshold is proposed. Firstly, the image quality quantization algorithm based on entropy weight is used to calculate the quality of background image in traffic flow video. Then by polynomial fitting the vehicle detection threshold set by the sample traffic flow and the correct rate of the vehicle recognition based on the threshold, the optimal detection threshold of the vehicle is obtained. Finally, Gao Si fitting the quality value of the sample background image and the optimal detection threshold of the sample vehicle, the adaptive threshold calculation model is obtained, and the background image in the traffic flow video is obtained in real time by the Gao Si mixed model. The quality value of the background image is calculated, and the real-time optimal vehicle detection threshold is obtained by inputting the adaptive threshold calculation model to identify the vehicle. The experimental and theoretical analysis shows that the method can update the vehicle detection threshold in real time according to the dynamic changing environment. The accuracy of vehicle recognition is improved effectively.
【作者單位】： 海南大學(xué)信息科學(xué)技術(shù)學(xué)院;海南大學(xué)南海海洋資源利用國(guó)家重點(diǎn)實(shí)驗(yàn)室;國(guó)防科學(xué)技術(shù)大學(xué)高性能計(jì)算國(guó)家重點(diǎn)實(shí)驗(yàn)室;
【基金】：國(guó)家自然科學(xué)基金 海南省自然科學(xué)基金 海南大學(xué)博士啟動(dòng)基金;海南大學(xué)青年基金~~
【分類號(hào)】：TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 張瑩;朱軍;;自動(dòng)車輛識(shí)別系統(tǒng)的設(shè)計(jì)與實(shí)現(xiàn)[J];儀表技術(shù)與傳感器;2006年01期

2 高軍偉;劉召燕;蔡國(guó)強(qiáng);劉新;賈利民;;基于面積法的車輛識(shí)別統(tǒng)計(jì)研究[J];青島大學(xué)學(xué)報(bào)(工程技術(shù)版);2008年04期

3 逯鵬;婁亞飛;劉奉哲;李玉松;黃石磊;湯玉合;;稀疏超完備車輛識(shí)別與統(tǒng)計(jì)[J];應(yīng)用科學(xué)學(xué)報(bào);2014年01期

4 ;國(guó)內(nèi)信息[J];中國(guó)自動(dòng)識(shí)別技術(shù);2007年04期

5 李文藝;孔金生;周永年;;基于信息融合團(tuán)隊(duì)一致法的車輛識(shí)別方法[J];微計(jì)算機(jī)信息;2008年31期

6 劉懷愚;李t，

本文編號(hào)：1534163