發(fā)布時(shí)間：2018-10-13 19:55

【摘要】：車(chē)輛自動(dòng)識(shí)別技術(shù)是智能交通系統(tǒng)（ITS）的重要組成部分，通過(guò)對(duì)車(chē)輛進(jìn)行自動(dòng)識(shí)別，可以為交通管理、收費(fèi)、調(diào)度、統(tǒng)計(jì)提供數(shù)據(jù)。車(chē)型識(shí)別是智能交通領(lǐng)域的研究熱點(diǎn)和難點(diǎn)之一，目前我國(guó)的車(chē)型識(shí)別率還難以滿(mǎn)足使用要求，對(duì)車(chē)型識(shí)別率提高算法的研究勢(shì)在必行,本文研究的就是基于車(chē)臉圖像特征的車(chē)型識(shí)別率提高算法。 本文首先對(duì)車(chē)輛進(jìn)行檢測(cè)與中值濾波，建立車(chē)輛樣本庫(kù)。然后截取了車(chē)臉圖像，并分別采用灰度特征、Canny邊緣特征、Sobel邊緣特征和HOG特征來(lái)表示圖像，，通過(guò)支持向量機(jī)訓(xùn)練并檢測(cè)樣本，獲得各自的識(shí)別率，比較并分析其結(jié)果。接著通過(guò)一種投票提升算法，將24種識(shí)別率不高的Gabor特征組合起來(lái)進(jìn)行車(chē)型識(shí)別，以提高識(shí)別率。 本文使用華碩A43EI235SD-SL筆記本電腦，在Windows7操作系統(tǒng)中，用OpenCV和VS2008搭建實(shí)驗(yàn)平臺(tái)。實(shí)驗(yàn)共采集了100類(lèi)車(chē)型，每類(lèi)車(chē)型各1張訓(xùn)練和測(cè)試樣本，車(chē)臉圖像尺寸為192*64。實(shí)驗(yàn)中利用灰度特征的識(shí)別率為53%，平均識(shí)別時(shí)間為39.47ms/張；采用Canny邊緣特征，識(shí)別率為55%，平均識(shí)別時(shí)間為47.85ms/張；采用Sobel邊緣特征，識(shí)別率為69%，平均識(shí)別時(shí)間為46.37ms/張；采用HOG特征，識(shí)別率為78%，平均識(shí)別時(shí)間為59.82ms/張；將24種gabor特征識(shí)別結(jié)果投票提升，識(shí)別率可以達(dá)到81%，識(shí)別平均時(shí)間85.24ms/張。 實(shí)驗(yàn)結(jié)果表明，本文使用的投票提升算法，識(shí)別率不僅優(yōu)于單個(gè)gabor特征，也優(yōu)于前面幾種特征表示法，代價(jià)是增加了一定的時(shí)間消耗。
[Abstract]:Automatic vehicle recognition is an important part of Intelligent Transportation system (ITS). It can provide data for traffic management, charge, scheduling and statistics through automatic identification of vehicles. Vehicle recognition is one of the research hotspots and difficulties in the field of intelligent transportation. At present, the vehicle recognition rate in our country is still difficult to meet the requirements of application, so it is imperative to study the algorithm of improving vehicle recognition rate. In this paper, the vehicle recognition rate improvement algorithm based on vehicle face image features is studied. First of all, vehicle detection and median filtering are carried out to establish the vehicle sample bank. Then, the images are captured and represented by gray level feature, Canny edge feature, Sobel edge feature and HOG feature, respectively. The recognition rate is obtained by training and detecting samples by support vector machine (SVM), and the results are compared and analyzed. Then 24 Gabor features with low recognition rate are combined to improve the recognition rate by a voting lifting algorithm. This paper uses Asus A43EI235SD-SL notebook computer, in Windows7 operating system, using OpenCV and VS2008 to build the experimental platform. A total of 100 kinds of vehicle models were collected, with one training and testing sample for each type of vehicle. The image size of the face of the vehicle was 1922 ~ (64). In the experiment, the recognition rate of gray feature is 53 and the average recognition time is 39.47ms/ sheet; using Canny edge feature, the recognition rate is 55 and the average recognition time is 47.85ms/ sheet; using Sobel edge feature, the recognition rate is 69 and the average recognition time is 46.37ms/ sheet; using HOG feature, The recognition rate is 78 and the average recognition time is 59.82ms/, and the result of 24 gabor features can be improved by voting, the recognition rate can reach 81 and the average recognition time is 85.24ms/. The experimental results show that the recognition rate of the proposed voting lifting algorithm is better than that of the single gabor feature and several previous feature representations at the cost of a certain amount of time consumption.
【學(xué)位授予單位】：西安電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類(lèi)號(hào)】：U495;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 彭玉樓,胡小兵;一種基于小波、分形與神經(jīng)網(wǎng)絡(luò)的汽車(chē)車(chē)型識(shí)別方法[J];長(zhǎng)沙電力學(xué)院學(xué)報(bào)(自然科學(xué)版);2001年04期

2 趙偉;數(shù)字圖像處理技術(shù)的優(yōu)勢(shì)[J];廣西公安管理干部學(xué)院學(xué)報(bào);2001年02期

3 陳愛(ài)斌;基于特征車(chē)的汽車(chē)車(chē)型識(shí)別[J];信息技術(shù);2004年05期

4 葉敬福,詹永照;基于Gabor小波變換的人臉表情特征提取[J];計(jì)算機(jī)工程;2005年15期

5 胡煒煒;李樹(shù)廣;吳舟舟;;基于邊緣輪廓特征的實(shí)時(shí)車(chē)型分類(lèi)[J];計(jì)算機(jī)工程;2007年13期

6 王亮,胡衛(wèi)明,譚鐵牛;人運(yùn)動(dòng)的視覺(jué)分析綜述[J];計(jì)算機(jī)學(xué)報(bào);2002年03期

7 徐建閩,賀敬凱;車(chē)型與車(chē)牌自動(dòng)識(shí)別技術(shù)分析[J];交通與計(jì)算機(jī);2002年02期

8 易平,陳福生,鄒紅艷;圖像處理中消除噪聲的方法[J];計(jì)算機(jī)應(yīng)用與軟件;2003年05期

9 戚大方;吳成東;;基于Gabor小波變換與支持向量機(jī)的人臉識(shí)別[J];科技信息;2009年35期

10 季晨光;張曉宇;白相宇;;基于視頻圖像中的車(chē)型識(shí)別[J];遼寧工業(yè)大學(xué)學(xué)報(bào)(自然科學(xué)版);2010年01期

相關(guān)博士學(xué)位論文 前1條

1 劉亞楠;多模態(tài)特征融合和變量選擇的視頻語(yǔ)義理解[D];浙江大學(xué);2010年

本文編號(hào)：2269726