本文關(guān)鍵詞： 交通標(biāo)志識(shí)別 兩階段 稀疏表示 HOG特征 LBP特征 SVM分類器 特征融合　出處：《南京理工大學(xué)》2015年碩士論文　論文類型：學(xué)位論文

【摘要】：交通標(biāo)志識(shí)別是智能交通系統(tǒng)(ITS)中的一個(gè)重要組成部分。經(jīng)過國內(nèi)外學(xué)者幾十年的研究,交通標(biāo)志識(shí)別領(lǐng)域的理論和實(shí)踐體系逐漸形成,并取得了很多突破性的進(jìn)展。然而自然場景具有復(fù)雜性以及交通標(biāo)志種類繁多,使得交通標(biāo)志的識(shí)別依然具備挑戰(zhàn)性。本文主要針對(duì)交通標(biāo)志的多類別,研究通過兩階段的方法識(shí)別交通標(biāo)志。首先,從交通標(biāo)志的功能類別出發(fā),設(shè)計(jì)了基于PCA-LDA的兩階段交通標(biāo)志識(shí)別方法。功能相近的交通標(biāo)志一般具有相似的圖案設(shè)計(jì),因此,根據(jù)功能類別將交通標(biāo)志劃分為限速、警告、指示以及無規(guī)則四個(gè)相似的子類進(jìn)行識(shí)別。首先采用結(jié)合PCA與LDA的方法對(duì)交通標(biāo)志進(jìn)行快速的預(yù)分類,即得到交通標(biāo)志的所屬子類；然后采用稀疏表示的方法進(jìn)行子類內(nèi)類別識(shí)別,得到交通標(biāo)志具體所屬的類別。實(shí)驗(yàn)表明,基于PCA-LDA的兩階段交通標(biāo)志識(shí)別方法在識(shí)別準(zhǔn)確率上要優(yōu)于PCA與LDA結(jié)合的方法以及基于局部字典的兩階段稀疏表示等方法。然后,根據(jù)交通標(biāo)志的形狀以及顏色特征對(duì)交通標(biāo)志的子類劃分進(jìn)行了調(diào)整,分為了紅色圓形、紅色正三角形、藍(lán)色圓形、白色圓形以及無規(guī)則五個(gè)相似的子類。在第一階段中采用HOG特征與SVM分類器對(duì)交通標(biāo)志進(jìn)行預(yù)分類；第二階段中提出了相似類核心區(qū)域的提取方法,并采用稀疏表示的方法進(jìn)行子類內(nèi)類別識(shí)別。通過實(shí)驗(yàn)表明,在使用相同特征提取方法的基礎(chǔ)上,基于顏色與形狀的相似子類劃分方案要優(yōu)于基于功能類別的子類劃分方案,而在同種相似子類劃分的基礎(chǔ)上,基于HOG特征方法的子類識(shí)別效果要優(yōu)于基于PCA-LDA方法,同時(shí)在最終的兩階段識(shí)別上也取得了更好的效果。最后,提出了基于多特征融合的兩階段交通標(biāo)志識(shí)別。在第一階段識(shí)別過程中,可以分別以顏色特征與邊緣特征作為依據(jù)進(jìn)行子類的識(shí)別,然而單一特征難以全面描述交通標(biāo)志,因此在第一階段中采用融合顏色直方圖以及HOG邊緣特征的方法對(duì)交通標(biāo)志進(jìn)行預(yù)分類；第二階段中采用融合LBP紋理特征與HOG邊緣特征對(duì)交通標(biāo)志各子類內(nèi)的類別進(jìn)行識(shí)別。實(shí)驗(yàn)表明,特征融合方法能夠獲得更高的識(shí)別率以及更好的魯棒性,識(shí)別率達(dá)到96.9%。
[Abstract]:Traffic sign recognition is an important part of Intelligent Transportation system (its). After decades of research by domestic and foreign scholars, the theory and practice system of traffic sign recognition has gradually formed. A lot of breakthrough progress has been made. However, the complexity of natural scenes and the variety of traffic signs make the recognition of traffic signs still challenging. This paper mainly focuses on the multi-category of traffic signs. This paper studies the identification of traffic signs by a two-stage method. First of all, it starts from the functional categories of traffic signs. This paper designs a two-stage traffic sign recognition method based on PCA-LDA. Traffic signs with similar functions generally have similar pattern design. Therefore, traffic signs are divided into speed limit and warning according to the function category. First, the method of combining PCA and LDA is used to pre-classify traffic signs quickly, that is to say, the subclasses of traffic signs are obtained. Then the sparse representation method is used to identify the class within the subclass, and the specific category of traffic sign is obtained. The two-stage traffic sign recognition method based on PCA-LDA is superior to the combination of PCA and LDA in recognition accuracy and two-stage sparse representation based on local dictionary. Then. According to the shape and color characteristics of traffic signs, the subcategories of traffic signs are divided into red circle, red square triangle and blue circle. White circular and irregular five similar subclasses. In the first stage, HOG features and SVM classifier are used to pre-classify traffic signs. In the second stage, the method of extracting the core region of similar classes is proposed, and the sparse representation method is used to recognize the subclass. The experiments show that the same feature extraction method is used on the basis of the method. The similar subclass partition scheme based on color and shape is superior to the subclass partition scheme based on function category, but on the basis of the same similar subclass partition. The subclass recognition effect based on HOG feature method is better than that based on PCA-LDA method. At the same time, better results are obtained in the final two-stage recognition. Finally. A two-stage traffic sign recognition based on multi-feature fusion is proposed. In the first stage, the color feature and edge feature can be used as the basis for sub-class recognition. However, it is difficult to describe traffic signs in a single feature, so in the first stage, the method of combining color histogram and HOG edge features is used to pre-classify traffic signs. In the second stage, LBP texture features and HOG edge features are used to identify the subclasses of traffic signs. The feature fusion method can obtain higher recognition rate and better robustness, and the recognition rate reaches 96.9.
【學(xué)位授予單位】：南京理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：U495;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前2條

1 王坤明,許忠仁;基于不變矩和神經(jīng)網(wǎng)絡(luò)的交通標(biāo)志識(shí)別方法研究[J];計(jì)算機(jī)應(yīng)用研究;2004年03期

2 王永明,尹紅麗;基于Hu不變矩?cái)U(kuò)展的交通標(biāo)志識(shí)別[J];曲靖師范學(xué)院學(xué)報(bào);2004年06期

，

本文編號(hào)：1462309