本文關(guān)鍵詞：基于多視角特征的車型識別方法　出處：《北京交通大學(xué)》2014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 多視角 自適應(yīng) 水平集 圖像分割 降維 支持向量機

【摘要】：車型識別是智能交通系統(tǒng)(Intelligent Transportation System, ITS)的關(guān)鍵技術(shù)之一�？v觀國內(nèi)外關(guān)于車型識別的研究,多數(shù)基于某一個或一種特征對車型進行分類,其識別準確率僅在特定情況下具有穩(wěn)定性,并且為獲得較高識別精度,需進行大量的數(shù)據(jù)分析,但冗余信息較多,影響到了目標識別的實時性。同時,識別分類方法的自適應(yīng)優(yōu)化學(xué)習(xí)機制也有待進一步完善。 針對上述問題,本論文提出了一種基于多視角特征的車型識別方法,旨在更加快速、準確地完成車型的識別。論文的主要研究內(nèi)容包括： 1、多視角多維特征參數(shù)體系的建立。本文建立了包含前視角、側(cè)視角、尾視角的多視角的多維特征混合樹形結(jié)構(gòu)體系,并提出了一種基于自適應(yīng)顯著性水平集的輪廓模型用于對體系中不同視角的區(qū)域分割,該模型采用基于二維凸包的顯著性初始輪廓曲線自適應(yīng)定位算法來獲取演化曲線的初始位置,同時采用正則化的P-M方程替代原Li模型中的高斯濾波。在此基礎(chǔ)上,完成了對不同視角的優(yōu)化特征參數(shù)的定義及量化處理。 2、特征參數(shù)優(yōu)化方法的研究。本文研究了一種基于改進型核獨立成分分析的特征參數(shù)降維優(yōu)化方法,該方法通過KICA算法獲取圖像多維特征的獨立基元以構(gòu)造獨立基子空間,采用2DPCA算法完成圖像去二階相關(guān)和進一步降維處理。同時,本文提出了基于Amari誤差和平均相關(guān)度作為評價標準的降維效果評價方法。對比仿真實驗表明,該參數(shù)優(yōu)化方法能夠完成對多維特征參數(shù)的有效降維約簡。 3、基于改進型支持向量機分類識別模型的提出。本文提出了一種基于組合核函數(shù)的自適應(yīng)支持向量機分類模型,該模型研究了組合核函數(shù)以及組合超參數(shù)組的確定,在此基礎(chǔ)上,采用雙角度約束以提高分類識別的效率和精度,即一方面設(shè)計基于馬氏距離和“aσ-原則”實現(xiàn)對樣本數(shù)據(jù)進行自動優(yōu)化分選,并結(jié)合加權(quán)判別算法加快支持向量機的訓(xùn)練測試速度；另一方面設(shè)計了基于先驗知識的迭代最優(yōu)參數(shù)自適應(yīng)搜索算法用于核函數(shù)參數(shù)的設(shè)定,以提高分類器的分類識別精度。 仿真實驗結(jié)果表明,基于自適應(yīng)顯著性水平集的輪廓模型分割方法的準確率穩(wěn)定在95%以上；基于改進型KICA模型的特征參數(shù)優(yōu)化方法的Amari誤差低于6%,平均相關(guān)度穩(wěn)定在97%以上；基于組合核函數(shù)的自適應(yīng)支持向量機分類模型對不同車型的識別率為97.926%,其訓(xùn)練、測試時間分別為1.9s和44.7ms。證明本文改進模型能夠滿足車型識別分類的需求,具有識別速度快、準確率高等優(yōu)點,這對于智能交通系統(tǒng)及車型識別系統(tǒng)的發(fā)展具有重要的理論及實際意義。
[Abstract]:Vehicle recognition is the intelligent transportation system (Intelligent Transportation System, ITS) is one of the key technologies. Research on vehicle recognition at home and abroad, the majority of one or a feature based on the classification model, the recognition accuracy rate only has stability under specific circumstances, and in order to obtain a higher recognition accuracy, need analysis a large amount of data, but more redundant information, affect the real-time target recognition. At the same time, the classification method of adaptive learning mechanism is to be further improved.
To solve the above problems, a vehicle recognition method based on multi view features is proposed in this paper, aiming to identify vehicle types more quickly and accurately.
1, establish the parameters system of multi angle multi-dimensional characteristics. This paper built a front view, side view, tail angle multidimensional mixed tree structure system, and proposed an adaptive level set based on the contour model for segmentation of different regions from the perspective of system, the model adopts the initial position get the evolution curve based on significant initial contour adaptive localization algorithm of two-dimensional convex hull, while using P-M equation regularization to replace the original Li model of Gauss filter. On this basis, completed the definition and quantitative optimization parameters of different perspective.
2, research on the optimization method of parameters. In this paper a dimensionality reduction method improved feature parameter analysis based on kernel independent components, the image acquisition methods of multidimensional KICA algorithm through independent primitives to construct independent basis subspace, using 2DPCA algorithm to complete the image to two order correlation and further reduction. At the same time, this paper proposes a Amari error and average correlation degree as the evaluation standard evaluation method based on dimension reduction effect. The simulation results show that the optimization method can complete the multidimensional characteristic parameters of Jane dimension reduce.
3, this paper presents an improved support vector machine classification based on model. This paper proposes an adaptive combination of kernel function of support vector machine classification model based on the model of combination of kernel function and parameter combination of super group, on the basis of this, using double angle constraint to improve the efficiency and accuracy of classification, i.e. a design of Mahalanobis distance and a sigma principle realize automatic optimization of sorting based on the sample data, and combined with the weighted algorithm to accelerate the training speed of testing support vector machine; on the other hand, the design of search algorithm for kernel parameters based on adaptive iterative optimal parameters a priori knowledge of the set, in order to improve the classification accuracy classifier.
Simulation results show that the segmentation method of contour model adaptive level set accuracy rate is more than 95% based on improved KICA model; feature parameter optimization method based on the Amari error is less than 6%, the average correlation stable above 97%; adaptive combination of kernel function of support vector machine classification model to identify the different models of the rate 97.926%, based on the training and testing time are respectively 1.9s and 44.7ms. prove that the improved model can meet the vehicle classification requirements, high recognition speed, high accuracy, it has important theoretical and practical significance for the development of intelligent transportation system and vehicle recognition system.

【學(xué)位授予單位】：北京交通大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2014
【分類號】：U495;TP391.41

【參考文獻】

相關(guān)期刊論文 前10條

1 秦曉薇;;區(qū)域填充算法的研究[J];赤峰學(xué)院學(xué)報(自然科學(xué)版);2011年06期

2 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

3 陳炳權(quán);劉宏立;;基于支持向量機與結(jié)構(gòu)矩的車型識別實時魯棒算法[J];湖南師范大學(xué)自然科學(xué)學(xué)報;2010年04期

4 葛廣英;;基于SVM的車型檢測和識別算法[J];計算機工程;2007年06期

5 歐衛(wèi)華;劉建國;孫勇;;一種改進的支持向量機及其應(yīng)用[J];計算技術(shù)與自動化;2009年01期

6 周奔;何傳江;原野;;結(jié)合自適應(yīng)變化停止函數(shù)的邊緣活動輪廓模型[J];計算機應(yīng)用研究;2012年01期

7 張穎新;范東啟;楊迪;楊燦;;車型自動識別系統(tǒng)研究[J];交通與運輸(學(xué)術(shù)版);2006年01期

8 李文舉;孫娟紅;韋麗華;李俠;;基于2DPCA-ICA和SVM的車標識別新方法[J];遼寧師范大學(xué)學(xué)報(自然科學(xué)版);2011年02期

9 孫林凱;金家善;耿俊豹;;基于加權(quán)精度的ε-SVR組合參數(shù)優(yōu)化[J];系統(tǒng)工程與電子技術(shù);2011年08期

10 孔銳,施澤生,郭立,張國宣;利用組合核函數(shù)提高核主分量分析的性能[J];中國圖象圖形學(xué)報;2004年01期

，

本文編號：1423200