本文關(guān)鍵詞：基于深度學(xué)習(xí)的車型識別分析與研究　出處：《山東師范大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 車型識別 車臉圖像 特征提取 SIFT 卷積神經(jīng)網(wǎng)絡(luò)

【摘要】：隨著城市交通復(fù)雜狀況的愈漸加深,公安、交警的工作量也日益繁重,因而,智能交通系統(tǒng)的進(jìn)一步發(fā)展變得尤為重要。車輛識別系統(tǒng)是目前比較熱門且已經(jīng)廣泛應(yīng)用于市場的一類智能交通系統(tǒng),它依賴于車牌識別、車標(biāo)識別和車型識別等核心技術(shù)。其中,車牌識別的研究已經(jīng)比較成熟,許多研究成果在企業(yè)車庫、小區(qū)等場所廣泛應(yīng)用。對于車標(biāo)識別,由于車標(biāo)區(qū)域太小,研究此類識別需要較高質(zhì)量的圖像,道路交通系統(tǒng)中的設(shè)備不能得到高質(zhì)量的車輛圖像的情況下,車標(biāo)識別往往不能達(dá)到很好的識別效果。而傳統(tǒng)的車型識別只能將車輛分成貨車、客車、小汽車等幾個大類,隨著智能化發(fā)展愈來愈快,這類系統(tǒng)已經(jīng)不能滿足交通系統(tǒng)的需要,對如何識別車輛具體型號的研究在實(shí)際應(yīng)用中將會有重要價值。類比于人臉識別,本文圍繞車臉圖像的識別進(jìn)行了一系列研究。首先,由于缺少直接用于研究的車臉圖像數(shù)據(jù),本文截取車輛圖像中的車臉部分進(jìn)行尺度歸一化,使用平移旋轉(zhuǎn)、亮度調(diào)整、運(yùn)動模糊等操作模擬現(xiàn)實(shí)中可能出現(xiàn)的幾種因素進(jìn)行數(shù)據(jù)擴(kuò)增,保證數(shù)據(jù)的多樣性,最終建立了一個包含31個子型號的車臉圖像數(shù)據(jù)庫�；趫D像處理模式的圖像識別方式,其核心是檢測提取圖像特征的算法,通過分析比較各種常用的特征提取算法,本文選擇了在車輛識別領(lǐng)域最常用也是效果最好的SIFT特征提取算法,詳細(xì)闡述了它的工作原理,并針對其生成的描述子過于復(fù)雜的缺點(diǎn),在檢測極值點(diǎn)時引入SUSAN角點(diǎn)檢測算子進(jìn)行改進(jìn),成功提取到了較簡單且準(zhǔn)確的車臉特征并結(jié)合k-鄰近分類器進(jìn)行分類。最后,本文引入了目前深度學(xué)習(xí)領(lǐng)域非常熱門的卷積神經(jīng)網(wǎng)絡(luò)對車臉圖像的特征進(jìn)行自主學(xué)習(xí)、提取。首先是構(gòu)建卷積神經(jīng)網(wǎng)絡(luò)模型,本文從網(wǎng)絡(luò)層數(shù)、卷積核大小、下采樣方法、激活函數(shù)類型等方面入手,分析不同的網(wǎng)絡(luò)設(shè)定情況下卷積神經(jīng)網(wǎng)絡(luò)的訓(xùn)練時間、特征維度、特征提取時間等系統(tǒng)評價參數(shù)的變化,從中選取最優(yōu)值,確定出卷積神經(jīng)網(wǎng)絡(luò)模型,將本文圖像數(shù)據(jù)庫中的圖像輸入網(wǎng)絡(luò),提取到最終的特征向量,輸入k-鄰近分類器進(jìn)行實(shí)驗(yàn),最終得出了較為理想的識別結(jié)果。與SIFT算法、SUSAN-SIFT算法相比,本文基于卷積神經(jīng)網(wǎng)絡(luò)的車型識別方法在速度與準(zhǔn)確率方面都有所提升。
[Abstract]:With the city traffic situation more complex gradually deepened, public security, traffic police work is also increasingly heavy, therefore, the further development of the intelligent transportation system has become particularly important. Vehicle recognition system is currently more popular and has been widely used in the market for a class of intelligent transportation system, it depends on the license plate recognition, vehicle logo recognition and vehicle recognition core study on license plate recognition technology. Among them, have been mature, many research achievements in enterprises widely used in residential garage, etc. for vehicle logo recognition, the logo area is too small, the image of this recognition requires a higher quality of the road traffic system of the equipment can be vehicle images of high quality under the condition of vehicle logo recognition often can not achieve good recognition effect. And the traditional vehicle recognition only the vehicle is divided into passenger cars, trucks, and several other categories, with the development of intelligent More and more, this kind of system has been unable to meet the needs of the transportation system, have important value to study how to identify the vehicle specific models in practical applications. In analogy to the face recognition, the face image recognition around the car carried out a series of research. First of all, because of the lack of direct data on the face image for the car, car face this part of the interception of the vehicle image are normalized using scale, translation and rotation, brightness adjustment, motion blur operation simulation, several factors may occur in the reality of data amplification, ensure the diversity of the data, finally established a consists of 31 sub models face image database. The image recognition method based on image processing mode. Its core is the detection of image feature extraction algorithm, through the analysis and comparison of various commonly used feature extraction algorithm, we choose the most commonly used also in vehicle identification SIFT is the best feature extraction algorithm, expounds its working principle, and the generation of descriptors complicated, SUSAN corner detection operator is introduced in the detection limit point is improved and the successful extraction of the car face feature is simple and accurate and combined classifier. Finally, near k- at present, this paper introduces the characteristics of deep learning convolutional neural network is very popular field of car face image for autonomous learning extraction. First to construct the convolutional neural network model, this article from the network layer, the convolution kernel size, sampling method, activation function types and other aspects, analysis of different network settings for convolutional neural network case the training time, dimensionality, change feature extraction time and system parameters, selects the optimal value in determining the convolution neural network model, this paper image database The image input of the network, to extract the final feature vector, input k- neighbor classifier experiment, finally obtained satisfactory recognition results. Compared with the SIFT algorithm, SUSAN-SIFT algorithm, the vehicle recognition method based on convolutional neural network in speed and accuracy are improved.

【學(xué)位授予單位】：山東師范大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：U495;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 徐淵;許曉亮;李才年;姜梅;張建國;;結(jié)合SVM分類器與HOG特征提取的行人檢測[J];計(jì)算機(jī)工程;2016年01期

2 郟東耀;艾艷可;黃軻;;基于最優(yōu)參數(shù)搜索的車輛中網(wǎng)識別方法研究[J];電子與信息學(xué)報;2014年06期

3 余凱;賈磊;陳雨強(qiáng);徐偉;;深度學(xué)習(xí)的昨天、今天和明天[J];計(jì)算機(jī)研究與發(fā)展;2013年09期

4 盧曉靜;陳華華;;基于HOG—LBP特征提取的人臉識別研究[J];杭州電子科技大學(xué)學(xué)報;2013年03期

5 金茂菁;;我國智能交通系統(tǒng)技術(shù)發(fā)展現(xiàn)狀及展望[J];交通信息與安全;2012年05期

6 閻沖;;基于SIFT算法的目標(biāo)特征檢測與提取技術(shù)研究[J];傳感器世界;2012年09期

7 丁世飛;齊丙娟;譚紅艷;;支持向量機(jī)理論與算法研究綜述[J];電子科技大學(xué)學(xué)報;2011年01期

8 劉卓;;K-最鄰近算法在文本自動分類中的應(yīng)用[J];蘇州市職業(yè)大學(xué)學(xué)報;2010年02期

9 馬蓓;張樂;;基于紋理特征的汽車車型識別[J];電子科技;2010年02期

10 陳麗莉;;基于SUSAN算法的角點(diǎn)檢測[J];現(xiàn)代計(jì)算機(jī)(專業(yè)版);2009年05期

相關(guān)博士學(xué)位論文 前1條

1 左奇;交通圖象檢測與處理方法研究[D];西北工業(yè)大學(xué);2003年

相關(guān)碩士學(xué)位論文 前6條

1 王冠群;基于SUSAN算子的特征檢測方法研究[D];陜西師范大學(xué);2015年

2 謝寶劍;基于卷積神經(jīng)網(wǎng)絡(luò)的圖像分類方法研究[D];合肥工業(yè)大學(xué);2015年

3 汪海波;基于深度學(xué)習(xí)的人臉識別方法研究[D];合肥工業(yè)大學(xué);2014年

4 陳先昌;基于卷積神經(jīng)網(wǎng)絡(luò)的深度學(xué)習(xí)算法與應(yīng)用研究[D];浙江工商大學(xué);2014年

5 汪松;基于SIFT算法的圖像匹配方法研究[D];西安電子科技大學(xué);2013年

6 于曉晶;圖像濾波方法的探討及其MATLAB實(shí)現(xiàn)[D];華東師范大學(xué);2008年

，

本文編號：1440489