【摘要】：智能交通系統(tǒng)(Intelligent Transportation Systems,ITS)涵蓋了交通領(lǐng)域的方方面面,基于視頻圖像的交通流數(shù)據(jù)采集與交通行為自動分析順應(yīng)了ITS的發(fā)展,成為ITS的熱點研究領(lǐng)域�；趫D像處理的車輛前景提取作為這一研究中基礎(chǔ)而又重要的步驟之一,在ITS發(fā)展中,有著重要的理論研究意義和潛在的應(yīng)用價值。本文將車輛前景提取分為車輛運動檢測和車輛陰影消除兩個步驟,以車輛前景提取為目的,對車輛運動檢測和車輛陰影消除進(jìn)行分析與研究。首先,詳細(xì)分析混合高斯模型(Gaussian Mixture Model,GMM)原理并闡述GMM缺陷及其原因。針對GMM背景建模簡單,易受初始時刻車輛前景干擾的問題,本文引入格拉布斯異常值判別準(zhǔn)則,提出了基于時域約束平均的GMM背景建模方法;依據(jù)改進(jìn)的幀間差分法和GMM背景更新原理,提出了基于四分區(qū)自適應(yīng)GMM的車輛運動檢測算法,以此解決傳統(tǒng)GMM存在的車輛空洞問題、ghost問題和車輛停車誤檢測問題。然后,在對陰影分析的基礎(chǔ)上,指出本文車輛陰影消除是指對行駛車輛投射陰影的消除。針對單一采用顏色特征進(jìn)行陰影消除的不足,本文通過Log域差分,弱化陰影,得到肯定是車輛前景的區(qū)域,以此對基于HSV顏色空間特征的陰影消除方法進(jìn)行約束,提出了基于Log域差分和HSV顏色空間特征的車輛陰影消除方法。最后,對所提算法進(jìn)行仿真實驗分析,并依據(jù)基本的數(shù)學(xué)知識,定義了空洞填補(bǔ)率,以此對車輛空洞問題的解決程度進(jìn)行量化分析。實驗結(jié)果表明,所提出的改進(jìn)GMM算法可以克服原GMM缺陷,所提出的車輛陰影消除方法性能良好。驗證了本文通過車輛運動檢測和車輛陰影消除來提取車輛前景的可靠性。
[Abstract]:Intelligent Transportation system (Intelligent Transportation Systems,ITS) covers all aspects of traffic field. Traffic flow data acquisition and traffic behavior automatic analysis based on video image conform to the development of ITS and become a hot research field of ITS. As one of the basic and important steps in this research, vehicle prospect extraction based on image processing has important theoretical research significance and potential application value in the development of ITS. In this paper, vehicle foreground extraction is divided into two steps: vehicle motion detection and vehicle shadow elimination. For the purpose of vehicle foreground extraction, vehicle motion detection and vehicle shadow elimination are analyzed and studied. First of all, the principle of mixed Gao Si model (Gaussian Mixture Model,GMM is analyzed in detail, and the defects of GMM and its causes are expounded. In order to solve the problem that the background modeling of GMM is simple and vulnerable to the disturbance of vehicle prospect at the initial time, this paper introduces the Grabbs anomaly criterion, and proposes a GMM background modeling method based on time-domain constrained average. According to the improved inter-frame difference method and GMM background updating principle, a vehicle motion detection algorithm based on four-partition adaptive GMM is proposed to solve the vehicle hole problem, ghost problem and vehicle parking error detection problem existing in traditional GMM. Then, on the basis of shadow analysis, it is pointed out that the shadow elimination of the vehicle in this paper refers to the elimination of the shadow cast on the driving vehicle. In order to solve the problem of shadow elimination by using color features alone, this paper weakens the shadow by Log domain difference, and obtains the area which is sure to be the foreground of the vehicle, so as to constrain the shadow elimination method based on the color space feature of HSV. A vehicle shadow elimination method based on log domain difference and HSV color space feature is proposed. Finally, the proposed algorithm is analyzed by simulation experiments, and the filling rate of voids is defined according to the basic mathematical knowledge, so as to quantitatively analyze the degree of solving the problem of vehicle voids. The experimental results show that the improved GMM algorithm can overcome the defects of the original GMM, and the proposed vehicle shadow elimination method has good performance. The reliability of vehicle prospect extraction through vehicle motion detection and vehicle shadow elimination is verified.
【學(xué)位授予單位】：長安大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2015
【分類號】：U495;TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 魏厚明;劉冬香;曹衛(wèi)群;楊剛;;布告板云樹木模型的陰影快速生成與繪制[J];計算機(jī)輔助設(shè)計與圖形學(xué)學(xué)報;2011年05期

2 山深聞;;關(guān)于陰影檢驗中的兩個問題[J];光學(xué)儀器;1988年01期

3 楊宏烈;建筑陰影構(gòu)成藝術(shù)淺識[J];華中建筑;1998年01期

4 章曼;呂偉偉;吳恩華;;高次冪函數(shù)逼近的陰影圖反走樣算法[J];計算機(jī)輔助設(shè)計與圖形學(xué)學(xué)報;2010年01期

5 李勝亮;管莉;張凌;潘偉;郝重陽;;基于陰影映射的實時軟陰影算法及實現(xiàn)[J];彈箭與制導(dǎo)學(xué)報;2007年01期

6 任鴻翔;尹勇;金一丞;;大規(guī)模場景中實時陰影的繪制[J];大連海事大學(xué)學(xué)報;2008年01期

7 曾曉一;何援軍;;軟陰影算法及實現(xiàn)[J];工程圖學(xué)學(xué)報;2010年04期

8 沈笠;楊寶光;馮結(jié)青;;多層陰影圖輪廓邊背投軟影算法[J];計算機(jī)輔助設(shè)計與圖形學(xué)學(xué)報;2013年09期

9 王榮本,紀(jì)壽文,郭克友,徐友春;識別陰影中智能車輛導(dǎo)航路徑的神經(jīng)網(wǎng)絡(luò)方法研究[J];公路交通科技;2002年05期

10 張方彥;楊猛;劉金剛;;一種改進(jìn)的實時軟陰影算法的設(shè)計與實現(xiàn)[J];空軍工程大學(xué)學(xué)報(自然科學(xué)版);2012年02期

相關(guān)會議論文 前6條

1 薛光琦;;陰影地形法的技術(shù)問題及應(yīng)用[A];中國地質(zhì)科學(xué)院礦床地質(zhì)研究所文集（27）[C];1994年

2 劉元瓊;雷海樂;趙學(xué)森;;背光陰影成像技術(shù)初步研究[A];第十屆中國核靶技術(shù)學(xué)術(shù)交流會摘要集[C];2009年

3 曹雪峰;萬剛;李鋒;李科;;三維地形仿真場景中實時陰影反走樣技術(shù)[A];第十屆中國科協(xié)年會論文集（一）[C];2008年

4 安寧宇;袁春;鐘玉琢;;一種對象空間的軟陰影實時渲染方法[A];第六屆和諧人機(jī)環(huán)境聯(lián)合學(xué)術(shù)會議（HHME2010)、第19屆全國多媒體學(xué)術(shù)會議（NCMT2010）、第6屆全國人機(jī)交互學(xué)術(shù)會議（CHCI2010）、第5屆全國普適計算學(xué)術(shù)會議（PCC2010）論文集[C];2010年

5 陳皓;劉曉平;;基于投影距離的改進(jìn)軟陰影生成算法[A];全國第19屆計算機(jī)技術(shù)與應(yīng)用（CACIS）學(xué)術(shù)會議論文集（下冊）[C];2008年

6 韓志q，

本文編號：2480492