自然場景下交通標(biāo)志檢測和分類算法研究
發(fā)布時(shí)間：2018-08-12 09:32
【摘要】：交通標(biāo)志作為重要的道路安全附屬設(shè)施,在規(guī)范交通行為、指示道路狀況、保障道路功效、引導(dǎo)行人和安全駕駛等方面起到重要作用。為了確保交通標(biāo)志的信息能夠及時(shí)、準(zhǔn)確的傳達(dá),交通標(biāo)志自動(dòng)識(shí)別系統(tǒng)(TSR)受到各國學(xué)者的重視。基于影像的道路交通標(biāo)志檢測和分類是交通標(biāo)志自動(dòng)識(shí)別系統(tǒng)的兩個(gè)關(guān)鍵技術(shù)環(huán)節(jié),經(jīng)過多年的發(fā)展,在理論研究和實(shí)用系統(tǒng)方面均取得了 一定的成果。交通標(biāo)志長期暴露在戶外,標(biāo)志本身會(huì)發(fā)生顏色退化、污損以及形變;在視頻和圖像的采集過程中,光照變化會(huì)導(dǎo)致交通標(biāo)志顏色失真,視角傾斜會(huì)引起交通標(biāo)志形狀變化;在復(fù)雜環(huán)境下交通標(biāo)志會(huì)被其它物體遮擋而形成不完整的邊緣,這些都給交通標(biāo)志的檢測帶來挑戰(zhàn)。交通標(biāo)志的分類是TSR中另一個(gè)關(guān)鍵技術(shù),交通標(biāo)志類別眾多,是典型的多分類問題,追求分類算法的魯棒性和有效性仍然是尚未有效解決的熱點(diǎn)問題。針對上述不足,本文在交通標(biāo)志顏色處理、交通標(biāo)志檢測和分類等方面進(jìn)行了研究,主要研究工作如下:(1)針對交通標(biāo)志的顏色特征,提出顏色分布模型和改進(jìn)的顏色對比度模型,以突出圖像中的交通標(biāo)志區(qū)域。顏色分布模型通過計(jì)算交通標(biāo)志主體顏色在Lab空間中的分布概率,得到輸入圖像相對于每種顏色的特征圖,在特征圖中突出相應(yīng)顏色的區(qū)域。改進(jìn)的顏色對比度模型則根據(jù)人眼視覺機(jī)制中存在的顏色對抗性,突出紅色、藍(lán)色和黃色區(qū)域。在實(shí)驗(yàn)階段對比了這兩種模型和其他常用的顏色處理算法在交通標(biāo)志數(shù)據(jù)集上的運(yùn)行結(jié)果。實(shí)驗(yàn)證明,本文提出的改進(jìn)的顏色對比度模型在保證最短運(yùn)行時(shí)間的同時(shí)取得了最高的檢測率。(2)在研究交通標(biāo)志快速檢測算法的基礎(chǔ)上,提出一種基于旋轉(zhuǎn)對稱投影的快速多邊形檢測算法。該方法以圖像的邊緣梯度為特征,選擇滿足特定旋轉(zhuǎn)對稱角度的點(diǎn)進(jìn)行投影,得到圖像中可能存在的多邊形,之后采用多邊形分類方法得到其具體類別。該算法時(shí)間復(fù)雜度較低,實(shí)驗(yàn)表明每幅圖像的平均處理時(shí)間為55ms,能夠滿足交通標(biāo)志檢測的實(shí)時(shí)需求。(3)在分析現(xiàn)有交通標(biāo)志形狀檢測算法的基礎(chǔ)上,針對部分遮擋和視角傾斜的交通標(biāo)志提出了基于連接分布(LD)模型的多邊形檢測方法。LD模型將多邊形看作中心到邊界點(diǎn)連接的集合,每個(gè)連接可用連接的長度、連接與水平線的夾角、邊界點(diǎn)的邊緣方向表示。在交通標(biāo)志發(fā)生視角傾斜和邊緣部分缺失的情況下,連接間的順序和鄰接關(guān)系不變,因此該算法能夠有效檢測視角傾斜和邊緣不完整的多邊形。在公開數(shù)據(jù)集上的實(shí)驗(yàn)表明,該算法在禁令、警告和指示標(biāo)志上的檢測率分別為98.63%、95.24%和94.40%,優(yōu)于大多數(shù)國際先進(jìn)算法。(4)針對復(fù)雜環(huán)境下交通標(biāo)志檢測結(jié)果不理想的情況,提出一種基于視覺顯著性的交通標(biāo)志檢測算法。該算法將自底向上和自上而下的顯著性結(jié)合在一起,完成對交通標(biāo)志的檢測。自底向上的顯著性算法在顏色聚簇劃分和區(qū)域分割的基礎(chǔ)上,計(jì)算區(qū)域之間的對比度和區(qū)域所屬聚簇的顏色分布緊致性,以此作為該區(qū)域的顯著性度量。每一類交通標(biāo)志均有特定的顏色特征,可形成類別相關(guān)的顯著圖,即自上而下的顯著性檢測。和自底向上的顯著圖相結(jié)合,完成復(fù)雜環(huán)境中交通標(biāo)志的檢測。實(shí)驗(yàn)證明該方法可以有效檢測禁令、指示和警告標(biāo)志,在公開數(shù)據(jù)集上取得了較高的檢測率。此外,該方法能夠檢測白色交通標(biāo)志,不需要額外的處理。(5)在分析我國交通標(biāo)志特點(diǎn)的基礎(chǔ)上,提出一種逐級細(xì)化的交通標(biāo)志分類方法。首先根據(jù)顏色和形狀特征將交通標(biāo)志分為五個(gè)大類,即禁令標(biāo)志、警告標(biāo)志、指示標(biāo)志、解除禁令標(biāo)志和其它標(biāo)志。在粗分類中,分別利用HOG和CN描述子表示每類標(biāo)志的形狀和顏色特征,采用線性SVM分類器得到感興趣區(qū)域所屬的大類。然后分析詞袋模型中顏色和形狀特征的融合方式,采用CN和SIFT特征早融合的方式表示感興趣區(qū)域,最后利用高斯核SVM分類器得到每個(gè)感興趣區(qū)域的最終類別標(biāo)記。該算法在公開數(shù)據(jù)集上的交通標(biāo)志分類正確率為99.15%,優(yōu)于人工分類結(jié)果,在所有公開的分類結(jié)果中排名第二。
[Abstract]:Traffic signs, as an important accessory facility of road safety, play an important role in regulating traffic behavior, indicating road conditions, ensuring road efficacy, guiding pedestrians and driving safely. Detection and classification of road traffic signs based on images are two key technologies of automatic traffic sign recognition system. After years of development, some achievements have been made in both theoretical research and practical systems. In the process of acquisition, illumination changes will lead to color distortion of traffic signs, and angle tilt will cause shape changes of traffic signs; in complex environment, traffic signs will be blocked by other objects and form incomplete edges, which bring challenges to traffic signs detection. Traffic signs classification is another key technology in TSR, traffic signs. It is a typical multi-classification problem that there are many classifications. The pursuit of robustness and effectiveness of classification algorithm is still a hot issue that has not been effectively solved. A color distribution model and an improved color contrast model are proposed to highlight the traffic sign area in the image. The color distribution model calculates the probability of the main color distribution in the Lab space and obtains the feature map of the input image relative to each color. The corresponding color region is highlighted in the feature map. The model highlights the red, blue and yellow regions according to the color antagonism in the human visual mechanism. The experimental results of the two models and other commonly used color processing algorithms on the traffic sign data sets are compared. The experimental results show that the improved color contrast model proposed in this paper guarantees the shortest running time. (2) On the basis of studying the fast detection algorithm of traffic signs, a fast polygon detection algorithm based on rotational symmetry projection is proposed, which is characterized by the edge gradient of the image and selects the points satisfying the specific rotational symmetry angle for projection to obtain the possible polygons in the image. The algorithm has a low time complexity, and the average processing time of each image is 55ms, which can satisfy the real-time requirement of traffic sign detection. (3) Based on the analysis of existing traffic sign shape detection algorithms, traffic signs with partial occlusion and oblique view angle are proposed. A polygon detection method based on connection distribution (LD) model is proposed. LD model regards polygons as a set of connections from center to boundary point. Each connection can be represented by the length of the connection, the angle between the connection and the horizontal line, and the edge direction of the boundary point. Experiments on open datasets show that the detection rates of prohibition, warning and indication signs are 98.63%, 95.24% and 94.40%, respectively, which are superior to most international advanced algorithms. (4) Traffic signs detection in complex environments. A traffic sign detection algorithm based on visual saliency is proposed, which combines bottom-up saliency with top-down saliency to detect traffic signs. Each type of traffic signs has a specific color feature, which can form a class-related saliency map, i.e. top-down saliency detection. Combining with bottom-up saliency map, traffic signs detection in complex environments is completed. Experiments show that the method is effective. In addition, the method can detect white traffic signs without additional processing. (5) Based on the analysis of the characteristics of traffic signs in China, a new classification method of traffic signs is proposed. First, according to the color and shape characteristics. Traffic signs are classified into five categories: prohibition signs, warning signs, indication signs, lifting prohibition signs and other signs. In rough classification, the shape and color features of each type of signs are represented by HOG and CN descriptors, and the regions of interest are classified by linear SVM classifier. In the fusion method of shape features, the region of interest is represented by the early fusion of CN and SIFT features. Finally, the final class markers of each region of interest are obtained by using Gaussian kernel SVM classifier. The classification accuracy of traffic signs on public data sets is 99.15%, which is better than that of manual classification. Among all the public classification results, the proposed algorithm is superior to manual classification. Ranked second.
【學(xué)位授予單位】：南京理工大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2015
【分類號(hào)】：U495;TP391.41
本文編號(hào)：2178650
[Abstract]:Traffic signs, as an important accessory facility of road safety, play an important role in regulating traffic behavior, indicating road conditions, ensuring road efficacy, guiding pedestrians and driving safely. Detection and classification of road traffic signs based on images are two key technologies of automatic traffic sign recognition system. After years of development, some achievements have been made in both theoretical research and practical systems. In the process of acquisition, illumination changes will lead to color distortion of traffic signs, and angle tilt will cause shape changes of traffic signs; in complex environment, traffic signs will be blocked by other objects and form incomplete edges, which bring challenges to traffic signs detection. Traffic signs classification is another key technology in TSR, traffic signs. It is a typical multi-classification problem that there are many classifications. The pursuit of robustness and effectiveness of classification algorithm is still a hot issue that has not been effectively solved. A color distribution model and an improved color contrast model are proposed to highlight the traffic sign area in the image. The color distribution model calculates the probability of the main color distribution in the Lab space and obtains the feature map of the input image relative to each color. The corresponding color region is highlighted in the feature map. The model highlights the red, blue and yellow regions according to the color antagonism in the human visual mechanism. The experimental results of the two models and other commonly used color processing algorithms on the traffic sign data sets are compared. The experimental results show that the improved color contrast model proposed in this paper guarantees the shortest running time. (2) On the basis of studying the fast detection algorithm of traffic signs, a fast polygon detection algorithm based on rotational symmetry projection is proposed, which is characterized by the edge gradient of the image and selects the points satisfying the specific rotational symmetry angle for projection to obtain the possible polygons in the image. The algorithm has a low time complexity, and the average processing time of each image is 55ms, which can satisfy the real-time requirement of traffic sign detection. (3) Based on the analysis of existing traffic sign shape detection algorithms, traffic signs with partial occlusion and oblique view angle are proposed. A polygon detection method based on connection distribution (LD) model is proposed. LD model regards polygons as a set of connections from center to boundary point. Each connection can be represented by the length of the connection, the angle between the connection and the horizontal line, and the edge direction of the boundary point. Experiments on open datasets show that the detection rates of prohibition, warning and indication signs are 98.63%, 95.24% and 94.40%, respectively, which are superior to most international advanced algorithms. (4) Traffic signs detection in complex environments. A traffic sign detection algorithm based on visual saliency is proposed, which combines bottom-up saliency with top-down saliency to detect traffic signs. Each type of traffic signs has a specific color feature, which can form a class-related saliency map, i.e. top-down saliency detection. Combining with bottom-up saliency map, traffic signs detection in complex environments is completed. Experiments show that the method is effective. In addition, the method can detect white traffic signs without additional processing. (5) Based on the analysis of the characteristics of traffic signs in China, a new classification method of traffic signs is proposed. First, according to the color and shape characteristics. Traffic signs are classified into five categories: prohibition signs, warning signs, indication signs, lifting prohibition signs and other signs. In rough classification, the shape and color features of each type of signs are represented by HOG and CN descriptors, and the regions of interest are classified by linear SVM classifier. In the fusion method of shape features, the region of interest is represented by the early fusion of CN and SIFT features. Finally, the final class markers of each region of interest are obtained by using Gaussian kernel SVM classifier. The classification accuracy of traffic signs on public data sets is 99.15%, which is better than that of manual classification. Among all the public classification results, the proposed algorithm is superior to manual classification. Ranked second.
【學(xué)位授予單位】：南京理工大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2015
【分類號(hào)】：U495;TP391.41
【相似文獻(xiàn)】
相關(guān)期刊論文 前8條
1 ;產(chǎn)品介紹[J];電氣開關(guān);1997年03期
2 ;企業(yè)之窗[J];電氣時(shí)代;1997年03期
3 江厥中 ,楊公俠;略論室內(nèi)建筑色彩[J];建筑學(xué)報(bào);1983年07期
4 郝同枝;;為視障學(xué)生創(chuàng)設(shè)無障礙的校園環(huán)境[J];內(nèi)蒙古教育;2010年02期
5 方榮國;;電影特效藍(lán)/綠屏拍攝解析[J];現(xiàn)代電影技術(shù);2011年01期
6 范樹奇;有機(jī)玻璃瓶裝寄生蟲標(biāo)本制作的改進(jìn)[J];哈爾濱醫(yī)科大學(xué)學(xué)報(bào);1987年05期
7 徐和德;利用背景的幾種技巧[J];照相機(jī);2005年04期
8 ;[J];;年期
相關(guān)會(huì)議論文 前1條
1 許宗惠;林仲賢;潘廣鉞;;不同色光照明后相同白光色貌的色位移——相繼顏色對比[A];全國第六屆心理學(xué)學(xué)術(shù)會(huì)議文摘選集[C];1987年
相關(guān)重要報(bào)紙文章 前3條
1 德先;拍銀杏的“非常規(guī)”技法[N];中國攝影報(bào);2013年
2 戴定國;愛爾蘭狗年發(fā)行導(dǎo)盲犬盲文郵票[N];中國集郵報(bào);2006年
3 記者 聶根鵬;盤活萬畝森林 開啟農(nóng)民致富之門[N];昆明日報(bào);2013年
相關(guān)博士學(xué)位論文 前1條
1 徐丹;自然場景下交通標(biāo)志檢測和分類算法研究[D];南京理工大學(xué);2015年
相關(guān)碩士學(xué)位論文 前1條
1 譚珊;基于顏色對比和各向異性擴(kuò)散分割的顯著性區(qū)域檢測[D];大連理工大學(xué);2013年
，本文編號(hào)：2178650
本文鏈接：http://sikaile.net/kejilunwen/daoluqiaoliang/2178650.html
最近更新
教材專著
