本文關(guān)鍵詞：行車環(huán)境下多特征融合的交通標(biāo)識(shí)檢測(cè)與識(shí)別研究　出處：《山東大學(xué)》2016年博士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 稀疏表示 圖像盲復(fù)原 特征融合 交通標(biāo)識(shí)識(shí)別 支持向量機(jī) 極限學(xué)習(xí)機(jī) BoF模型

【摘要】：隨著社會(huì)經(jīng)濟(jì)的發(fā)展,車輛與日俱增,智能交通系統(tǒng)的應(yīng)用受到人們的高度重視。作為智能交通系統(tǒng)的核心關(guān)鍵技術(shù),交通標(biāo)識(shí)自動(dòng)檢測(cè)和識(shí)別獲得越來越多學(xué)者的關(guān)注和研究,并在駕駛員輔助系統(tǒng)、無人駕駛車輛及道路標(biāo)識(shí)的維護(hù)等方面獲得廣泛應(yīng)用。然而,在真實(shí)的復(fù)雜場(chǎng)景中,交通標(biāo)識(shí)會(huì)出現(xiàn)褪色、破損、陰影、遮擋、運(yùn)動(dòng)模糊及顏色與形狀相似物體的干擾,面對(duì)這些問題,很多學(xué)者進(jìn)行了深入的研究,但是研究成果還遠(yuǎn)未達(dá)到成熟。尤其是在我國(guó)人口眾多、私家車日益普及的情況下,交通堵塞和生命安全問題愈發(fā)嚴(yán)重,因此對(duì)交通標(biāo)識(shí)自動(dòng)檢測(cè)與識(shí)別的研究具有非常重要的理論與現(xiàn)實(shí)意義。論文圍繞智能交通系統(tǒng)中交通標(biāo)識(shí)自動(dòng)檢測(cè)與識(shí)別關(guān)鍵技術(shù),重點(diǎn)研究了行車環(huán)境下由于車輛加速或者攝像頭抖動(dòng)造成交通標(biāo)識(shí)模糊的問題,圖像的底層特征融合、交通標(biāo)識(shí)的顏色分割及感興趣區(qū)域提取問題,以及支持向量機(jī)、極限學(xué)習(xí)機(jī)和其它分類器在交通標(biāo)識(shí)檢測(cè)與識(shí)別中的應(yīng)用問題。論文的具體研究工作及成果如下：(1)針對(duì)行車環(huán)境下攝像頭獲取的視覺圖像產(chǎn)生運(yùn)動(dòng)模糊的問題,研究了一種基于稀疏表示和Weber定律的圖像盲復(fù)原算法。該方法首先通過沖擊濾波器來預(yù)測(cè)模糊圖像的顯著邊緣,并用多尺度策略由粗到細(xì)進(jìn)行模糊核的估計(jì)。然后對(duì)圖像盲復(fù)原模型進(jìn)行稀疏正則化約束,并結(jié)合反映人類視覺特性的Weber定律對(duì)圖像進(jìn)行盲復(fù)原。實(shí)驗(yàn)結(jié)果表明,提出的盲復(fù)原算法能獲得較優(yōu)的性能,在圖像紋理上能取得較好的復(fù)原效果,并且該方法降低了復(fù)原圖像的邊界偽影,符合人的視覺感知特性。(2)針對(duì)交通標(biāo)識(shí)檢測(cè)中樣本類別間的不平衡常常導(dǎo)致分類器的檢測(cè)性能弱化的問題,研究了一種基于感興趣區(qū)域和HOG-MBLBP融合特征的交通標(biāo)識(shí)檢測(cè)方法。根據(jù)交通標(biāo)識(shí)鮮亮的顏色特點(diǎn),采用顏色增強(qiáng)技術(shù)分割并提取出自然背景中交通標(biāo)識(shí)所在的感興趣區(qū)域；研究了HOG-MBLBP圖像底層融合特征,并對(duì)交通標(biāo)識(shí)樣本庫提取該融合特征,利用遺傳算法對(duì)SVM交叉驗(yàn)證進(jìn)行參數(shù)的優(yōu)化選取,以此來訓(xùn)練和提升SVM分類器性能；最后將提取的感興趣區(qū)域圖像的HOG-MBLBP特征送入訓(xùn)練好的SVM多分類器,進(jìn)行進(jìn)一步的精確檢測(cè)和定位,剔除誤檢區(qū)域。在自建的SDU_CVPR_A交通標(biāo)識(shí)樣本庫及GTS*德國(guó)交通標(biāo)識(shí)庫上分別進(jìn)行了實(shí)驗(yàn),結(jié)果驗(yàn)證了所提方法的優(yōu)越性。(3)為了準(zhǔn)確快速識(shí)別出檢測(cè)到的交通標(biāo)識(shí),研究了一種基于HOG-MBLBP融合特征和極限學(xué)習(xí)機(jī)的交通標(biāo)識(shí)識(shí)別方法。首先針對(duì)中國(guó)交通標(biāo)識(shí)的特點(diǎn)建立了23類SDU_CVPR_B交通標(biāo)識(shí)識(shí)別樣本庫,然后對(duì)交通標(biāo)識(shí)樣本庫分別提取HOG特征、BLBP特征、MBLBP特征以及HOG-MBLBP融合特征,并將提取特征分別輸入ELM分類器、SVM分類器、KNN分類器以及隨機(jī)森林分類器進(jìn)行分類訓(xùn)練。通過在自建SDU_CVPR_B交通標(biāo)識(shí)識(shí)別庫和GTSRB德國(guó)交通標(biāo)識(shí)識(shí)別庫上進(jìn)行的實(shí)驗(yàn)表明,融合特征結(jié)合ELM分類器可以取得較優(yōu)的識(shí)別效果。(4)鑒于語義特征BoF模型在圖像分類任務(wù)中的廣泛應(yīng)用,為了更好地表達(dá)圖像,建立底層視覺特征與高層語義特征間的關(guān)系,研究了一種基于融合特征BoF模型的金字塔匹配交通標(biāo)識(shí)識(shí)別方法。首先利用K均值聚類方法對(duì)各種局部不變特征進(jìn)行聚類,根據(jù)聚類中心構(gòu)建各自的詞典,然后進(jìn)行BoF模型的圖像直方圖表示,并采用空間金字塔策略以充分利用局部不變特征的空間結(jié)構(gòu)信息,最后進(jìn)行SVM分類器訓(xùn)練。在自建SDU_CVPR_B交通標(biāo)識(shí)庫和GTSRB德國(guó)庫上的實(shí)驗(yàn)結(jié)果表明HOG-MBLBP融合特征的分類效果較優(yōu),且HOG-MBLBP融合特征的BoF模型表示進(jìn)行分類識(shí)別的效果優(yōu)于HOG-MBLBP融合特征進(jìn)行ELM分類識(shí)別的效果。綜上所述,本文主要針對(duì)行車環(huán)境下交通標(biāo)識(shí)圖像的檢測(cè)與識(shí)別環(huán)節(jié)所涉及的一些關(guān)鍵問題進(jìn)行了探索和研究,旨在提高交通標(biāo)識(shí)檢測(cè)和識(shí)別的準(zhǔn)確性與快速性,豐富智能交通系統(tǒng)的理論體系,能夠最大程度的解決我國(guó)現(xiàn)有的交通問題。
[Abstract]:With the development of social economy, the application of intelligent transportation system vehicle grow with each passing day, the affected people's attention. As the key technology of the intelligent transportation system, traffic signs more and more attention and research for automatic detection and recognition, and in driver assistant system, application maintenance and other aspects of the unmanned vehicle and road signs. However, in the complex scene, traffic signs will fade, breakage, shadows, occlusion, motion blur and color and shape similar to object interference, in the face of these problems, many scholars have conducted in-depth research, but the results are far from mature. Especially in our country has a large population, a private car the growing popularity of the situation, traffic congestion and safety problems become more serious, so it has very important theory and the identification of automatic detection and recognition of traffic Practical significance. This dissertation focuses on Key Technologies of automatic detection and recognition of traffic signs in intelligent traffic system, focusing on the traffic environment due to vehicle acceleration or camera jitter caused by traffic identification Fuzzy problem, the fusion of the low-level features of image segmentation and extracting regions of interest in traffic sign colors, and support vector machine, application of extreme learning machine and other classifier in traffic sign detection and recognition. The specific research work and achievements of the thesis are as follows: (1) motion blur problem for visual image traffic environment to access the camera, on a blind image restoration algorithm based on sparse representation and Weber law. The first method to predict significant edge blur the image through the shock filter, and multi-scale strategy from coarse to fine estimation kernel. Then the image blind restoration model The sparse regularization constraint, and combined with the law reflect Weber human visual characteristics of image restoration. The experimental results show that the proposed blind restoration algorithm can obtain better performance, can obtain the good restoration effect on the image texture, and this method reduces the boundary artifact image, in line with the characteristics of human vision perception. (2) for the unbalanced data traffic sign detection in between categories often leads to weakening of the detection performance of classifier problem, studies a method of traffic sign detection region of interest and HOG-MBLBP fusion based on feature. According to the characteristics of the traffic signs color bright, the color segmentation enhancement technology and extract traffic signs where the interest in natural background areas; study of HOG-MBLBP image fusion feature, and the traffic signs sample extract the feature fusion, using the genetic algorithm to the SVM cross Optimal selection of validation parameters, in order to train and enhance the SVM performance of the classifier; HOG-MBLBP feature extraction finally the ROI image into the trained SVM classifier, accurate detection and positioning further, to eliminate the error regions. The experiments were conducted in a self built SDU_CVPR_A traffic signs and traffic in Germany GTS* sample database the logo, results show the superiority of the proposed method. (3) in order to quickly and accurately identify the detected traffic signs, on a pass identification method of HOG-MBLBP feature fusion and extreme learning machine. Based on the first established 23 types of SDU_CVPR_B traffic identification database according to the characteristics of China traffic signs then, HOG feature extraction of traffic sign sample library BLBP feature, MBLBP feature and HOG-MBLBP feature fusion, feature extraction and input of ELM classifier, SVM Classifier, KNN classifier and random forest classifier training. Through the self SDU_CVPR_B traffic identification library and GTSRB library on the German traffic sign recognition experiments show that the combination of the ELM classifier can achieve better recognition effect of feature fusion. (4) in view of wide application of semantic features of BoF model in image classification task, in order to better express the image, establish relationship between low-level visual features and high-level semantic features between the study of a new matching traffic sign recognition feature fusion method of BoF model based on Pyramid. The first use of K mean value clustering method of local invariant feature clustering, according to the dictionary to construct a cluster center, and then the image histogram BoF model said the Pyramid strategy to make full use of the information of spatial structure of local invariant features. Finally, SVM classifier training In traffic sign practice. Self SDU_CVPR_B library and GTSRB Library in Germany. The experimental results show that the classification results of HOG-MBLBP fusion feature is better than the BoF model and the HOG-MBLBP fusion feature representation feature fusion classification is better than the HOG-MBLBP ELM classification results. To sum up, this paper mainly focuses on some key issues of detection and recognition link traffic sign image traffic environment to explore and research, in order to improve the accuracy of traffic sign detection and recognition and speediness, enrich the theoretical system of the intelligent transportation system, can solve the maximum traffic problems existing in our country.

【學(xué)位授予單位】：山東大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP391.41

【相似文獻(xiàn)】

相關(guān)會(huì)議論文 前1條

1 董方曉;;推行精細(xì)化管理 創(chuàng)建文明樣板路[A];全國(guó)城市公路學(xué)會(huì)第十九次學(xué)術(shù)年會(huì)論文集[C];2010年

相關(guān)重要報(bào)紙文章 前10條

1 通訊員 李會(huì)香;市公汽公司努力營(yíng)造良好行車環(huán)境[N];四平日?qǐng)?bào);2008年

2 記者 劉建業(yè)邋通訊員 朱興月;日東高速管理處創(chuàng)和諧行車環(huán)境[N];濟(jì)寧日?qǐng)?bào);2008年

3 記者 尹昊 實(shí)習(xí)生 魏彬 劉賽;市交通局創(chuàng)造安全、和諧行車環(huán)境迎奧運(yùn)[N];衡水日?qǐng)?bào);2008年

4 鐘俊鋒;營(yíng)造周圍是景行車環(huán)境[N];韶關(guān)日?qǐng)?bào);2007年

5 記者 高博漸;山西省高管局積極備戰(zhàn)“煤博會(huì)”[N];現(xiàn)代物流報(bào);2007年

6 葉偉峰 本報(bào)實(shí)習(xí)記者 杜芳群;我市公路綠地覆蓋長(zhǎng)度達(dá)500公里[N];撫州日?qǐng)?bào);2006年

7 記者 翟相哲　通訊員 陳合永;我市強(qiáng)化公路“三亂”治理和糾風(fēng)治理[N];邯鄲日?qǐng)?bào);2009年

8 本報(bào)記者 董學(xué)宏　通訊員 孟雙;“專業(yè)精細(xì)創(chuàng)新”保平安暢通公路[N];淄博日?qǐng)?bào);2011年

9 馬春祥 莫言;播種文明 收獲安全 享受暢通[N];中國(guó)經(jīng)濟(jì)導(dǎo)報(bào);2008年

10 本報(bào)記者 程雪梅　本報(bào)通訊員 許建東;暢安舒美迎“國(guó)檢”[N];廊坊日?qǐng)?bào);2010年

相關(guān)博士學(xué)位論文 前1條

1 劉成云;行車環(huán)境下多特征融合的交通標(biāo)識(shí)檢測(cè)與識(shí)別研究[D];山東大學(xué);2016年

，

本文編號(hào)：1414712