本文關(guān)鍵詞： 交通標(biāo)志檢測(cè)與識(shí)別 最大穩(wěn)定極值區(qū)域 感興趣區(qū)域提取 多特征融合 SVM分類(lèi)　出處：《山東大學(xué)》2017年碩士論文　論文類(lèi)型：學(xué)位論文

【摘要】：據(jù)相關(guān)機(jī)構(gòu)統(tǒng)計(jì)全世界每年有130萬(wàn)人左右因?yàn)榈缆方煌ㄊ鹿识鴨适д滟F的生命,其中與駕駛員自身因素相關(guān)的酒后或疲勞駕駛、超速行駛等成為了這些交通安全事故的主要誘因。交通事故不僅會(huì)造成巨大的經(jīng)濟(jì)損失,更重要的是會(huì)無(wú)情地奪取人類(lèi)寶貴的生命,因此道路交通安全問(wèn)題已不再是某個(gè)國(guó)家面臨的問(wèn)題,而是需要全世界各國(guó)共同解決的。為了有效提高道路交通安全和運(yùn)輸效率,降低事故發(fā)生頻率,保障人們的人身財(cái)產(chǎn)安全,智能交通系統(tǒng)應(yīng)運(yùn)而生。交通標(biāo)志識(shí)別系統(tǒng)是智能交通系統(tǒng)諸多先進(jìn)技術(shù)領(lǐng)域中的一個(gè)重要分支,在無(wú)人駕駛車(chē)輛、智能機(jī)器人、輔助駕駛系統(tǒng)、輔助道路標(biāo)志規(guī)劃、導(dǎo)盲機(jī)器人等方面都具有廣闊的發(fā)展和應(yīng)用前景。因此對(duì)于交通標(biāo)志識(shí)別系統(tǒng)相關(guān)技術(shù)的研究和探索非常具有學(xué)術(shù)意義和實(shí)用價(jià)值。本文以城市道路中常見(jiàn)的指示、禁令以及警告標(biāo)志為研究對(duì)象,針對(duì)大場(chǎng)景自然環(huán)境下的道路交通標(biāo)志的檢測(cè)與識(shí)別問(wèn)題展開(kāi)研究和討論,主要從高分辨率大場(chǎng)景下的快速交通標(biāo)志檢測(cè)、多類(lèi)別交通標(biāo)志的魯棒識(shí)別和交通標(biāo)志識(shí)別系統(tǒng)平臺(tái)的設(shè)計(jì)與搭建這三個(gè)方面作了深入研究和探索。在交通標(biāo)志檢測(cè)方面,為解決傳統(tǒng)的基于機(jī)器學(xué)習(xí)的交通標(biāo)志檢測(cè)方法需要對(duì)每一個(gè)待檢測(cè)子窗口進(jìn)行處理而導(dǎo)致算法實(shí)時(shí)性欠佳的問(wèn)題,提出了顏色增強(qiáng)下的MSER提取標(biāo)志候選區(qū)域結(jié)合線(xiàn)性SVM的快速交通標(biāo)志檢測(cè)方法。該方法根據(jù)標(biāo)志的顏色進(jìn)行顏色增強(qiáng),對(duì)增強(qiáng)圖像提取MSER得到交通標(biāo)志感興趣區(qū)域,然后在大場(chǎng)景高分辨率圖像的多尺度滑動(dòng)遍歷檢測(cè)搜索過(guò)程中僅對(duì)包含交通標(biāo)志候選區(qū)域的滑動(dòng)窗口進(jìn)行HOG特征的提取和SVM分類(lèi)判別,而對(duì)非標(biāo)志候選區(qū)域的滑動(dòng)窗口則不進(jìn)行特征提取和分類(lèi)判別。實(shí)驗(yàn)結(jié)果表明:改進(jìn)的MSER+HOG+SVM方法在獲得了較高的檢測(cè)準(zhǔn)確率以及較低的誤檢率的前提下,運(yùn)算速度上有較大提升,且魯棒性較好。在多類(lèi)別交通標(biāo)志識(shí)別方面,提出了融合全局特征和局部特征的多特征交通標(biāo)志分類(lèi)識(shí)別方法,有效地提升了識(shí)別度。該方法首先分別提取能夠描述標(biāo)志圖像內(nèi)部紋理信息的LBP特征、表示標(biāo)志圖像形狀信息的HOG特征以及描述圖像粗略輪廓信息的全局Gist特征,然后采用線(xiàn)性組合方式,實(shí)現(xiàn)特征融合互補(bǔ),并通過(guò)主成分分析方法進(jìn)行數(shù)據(jù)降維,最后采用支持向量機(jī)分類(lèi)器進(jìn)行交通標(biāo)志訓(xùn)練與識(shí)別。實(shí)驗(yàn)結(jié)果表明:相對(duì)于提取單一特征的交通標(biāo)志識(shí)別方法,基于多特征融合的算法獲得了更高的識(shí)別精確度,同時(shí)也滿(mǎn)足實(shí)時(shí)性要求。最后,本文以輪式機(jī)器人為主要硬件基礎(chǔ),利用Microsoft Visual Studio 2010結(jié)合OpenCV開(kāi)源視覺(jué)庫(kù)設(shè)計(jì)了基于MFC對(duì)話(huà)框的交通標(biāo)志識(shí)別系統(tǒng)應(yīng)用程序以模擬行車(chē)駕駛環(huán)境。系統(tǒng)平臺(tái)主要集成了圖像采集與實(shí)時(shí)處理、標(biāo)志檢測(cè)、標(biāo)志識(shí)別和機(jī)器人運(yùn)動(dòng)控制等功能模塊。
[Abstract]:According to the statistics of relevant organizations, there are about 1.3 million people in the world who lose their precious lives because of road traffic accidents every year, including drunk or fatigue driving related to drivers' own factors. Speeding has become the main cause of these traffic safety accidents. Traffic accidents will not only cause huge economic losses, more importantly, will ruthlessly take away the precious lives of human beings. Therefore, the problem of road traffic safety is no longer a problem faced by a certain country, but needs to be solved by all countries all over the world. In order to effectively improve road traffic safety and transport efficiency, reduce the frequency of accidents. The intelligent transportation system (its) emerges as the times require. Traffic sign recognition system is an important branch in many advanced fields of intelligent transportation system, which is used in driverless vehicles and intelligent robots. Auxiliary driving system, auxiliary road sign planning. Blind robot has a broad prospect of development and application. Therefore, the research and exploration of traffic sign recognition system is of great academic significance and practical value. Show. Ban and warning signs as the research object, the detection and recognition of road traffic signs under the large scene environment is studied and discussed, mainly from the high resolution of the rapid traffic signs detection. The design and construction of robust recognition and traffic sign recognition system platform for multi-class traffic signs are studied and explored in detail. In order to solve the problem that the traditional traffic sign detection method based on machine learning needs to deal with every sub-window to be detected, which leads to poor real-time algorithm. A fast traffic sign detection method based on MSER and linear SVM is proposed, which is based on the color of the sign. The area of interest is obtained by extracting MSER from enhanced image. Then in the search process of multi-scale sliding traversal detection of large scene high-resolution images, only the HOG feature extraction and SVM classification are carried out on the sliding window containing traffic sign candidate area. But the sliding window of unmarked candidate region is not extracted and classified. The experimental results show that the improved MSER HOG is improved. The SVM method can obtain higher detection accuracy and lower false detection rate. In the aspect of multi-class traffic sign recognition, a multi-feature traffic sign classification and recognition method combining global features and local features is proposed. The recognition degree is improved effectively. Firstly, the LBP features which can describe the internal texture information of the logo image are extracted separately. The HOG features representing the shape information of the logo image and the global Gist features describing the rough contour information of the image are presented. Then the features are fused and complemented by linear combination. Finally, the support vector machine classifier is used to train and recognize traffic signs. The experimental results show that the traffic sign recognition method is relative to extracting a single feature. The algorithm based on multi-feature fusion achieves higher recognition accuracy and meets the real-time requirements. Finally, this paper takes wheeled robot as the main hardware base. Using Microsoft Visual Studio. In order to simulate the driving environment, the application program of traffic sign recognition system based on MFC dialog box is designed based on OpenCV open source visual library in 2010. The system platform mainly integrates image acquisition and real-time processing. Sign detection, sign recognition and robot motion control and other functional modules.
【學(xué)位授予單位】：山東大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：U463.6;U495;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 王斌;常發(fā)亮;劉春生;;基于多特征融合的交通標(biāo)志分類(lèi)[J];山東大學(xué)學(xué)報(bào)(工學(xué)版);2016年04期

2 王斌;常發(fā)亮;劉春生;;基于MSER和SVM的快速交通標(biāo)志檢測(cè)[J];光電子·激光;2016年06期

3 胡曉光;程承旗;李德仁;;基于視覺(jué)認(rèn)知的禁令交通標(biāo)志檢測(cè)[J];北京大學(xué)學(xué)報(bào)(自然科學(xué)版);2015年06期

4 戈俠;于鳳芹;陳瑩;;基于分塊自適應(yīng)融合特征的交通標(biāo)志識(shí)別[J];計(jì)算機(jī)工程與應(yīng)用;2017年03期

5 徐超;高夢(mèng)珠;查宇鋒;曹利民;;基于HOG和SVM的公交乘客人流量統(tǒng)計(jì)算法[J];儀器儀表學(xué)報(bào);2015年02期

6 劉威;段成偉;遇冰;柴麗穎;袁淮;趙宏;;基于后驗(yàn)HOG特征的多姿態(tài)行人檢測(cè)[J];電子學(xué)報(bào);2015年02期

7 趙娜;袁家斌;徐晗;;智能交通系統(tǒng)綜述[J];計(jì)算機(jī)科學(xué);2014年11期

8 丁文銳;康傳波;李紅光;劉碩;;基于MSER的無(wú)人機(jī)圖像建筑區(qū)域提取[J];北京航空航天大學(xué)學(xué)報(bào);2015年03期

9 賈永紅;胡志雄;周明婷;姬偉軍;;自然場(chǎng)景下三角形交通標(biāo)志的檢測(cè)與識(shí)別[J];應(yīng)用科學(xué)學(xué)報(bào);2014年04期

10 張麗霞;劉濤;潘福全;郭濤;劉瑞昌;;駕駛員因素對(duì)道路交通事故指標(biāo)的影響分析[J];中國(guó)安全科學(xué)學(xué)報(bào);2014年05期

相關(guān)博士學(xué)位論文 前2條

1 劉春生;復(fù)雜大背景下交通標(biāo)志快速魯棒的檢測(cè)和識(shí)別研究[D];山東大學(xué);2016年

2 王剛毅;交通標(biāo)志檢測(cè)與分類(lèi)算法研究[D];哈爾濱工業(yè)大學(xué);2013年

相關(guān)碩士學(xué)位論文 前3條

1 歐陽(yáng)維力;基于單目視覺(jué)的交通標(biāo)志檢測(cè)與識(shí)別算法研究[D];湖南大學(xué);2014年

2 黃翠;交通標(biāo)志檢測(cè)與識(shí)別算法研究[D];山東大學(xué);2014年

3 張潘潘;道路交通標(biāo)志檢測(cè)與識(shí)別算法的研究[D];山東大學(xué);2012年

，

本文編號(hào)：1442293