【摘要】：運(yùn)動(dòng)車輛的檢測(cè)與跟蹤技術(shù)一直以來都是智能交通系統(tǒng)中的一個(gè)重點(diǎn)研究?jī)?nèi)容,目前在車輛的檢測(cè)和跟蹤問題上還有著很多有待解決的問題。其中動(dòng)態(tài)場(chǎng)景中運(yùn)動(dòng)車輛的檢測(cè)由于存在著車輛與背景兩個(gè)相互獨(dú)立的運(yùn)動(dòng)而使車輛的提取更加困難,在車輛檢測(cè)的準(zhǔn)確性上,有著很大的研究空間。論文首先對(duì)目前的光流檢測(cè)方法中存在的錯(cuò)誤光流難以完全去除的問題進(jìn)行了詳細(xì)的研究和探討,并提出了一種有效的解決方法。同時(shí)采用聚類的方法準(zhǔn)確的從動(dòng)態(tài)場(chǎng)景中提取出車輛。最后研究了車輛跟蹤技術(shù),對(duì)車輛的遮擋問題進(jìn)行了詳細(xì)的討論,并通過算法的改進(jìn),有效的解決了此問題。 在車輛檢測(cè)的問題中,采用Harris算子計(jì)算圖像的特征點(diǎn),再通過金字塔Lucas-Kanade光流(L-K光流)法計(jì)算圖像的特征點(diǎn)光流場(chǎng)。隨后引入矢量量化的思想對(duì)圖像的光流場(chǎng)進(jìn)行聚類,并提出了結(jié)合歐式距離和相似系數(shù)作為相似性測(cè)度的方法提高了聚類的準(zhǔn)確性。最后計(jì)算各個(gè)類別中角點(diǎn)的分布方差,通過RANSAC方法對(duì)光流場(chǎng)中的錯(cuò)誤光流進(jìn)行粗剔除,再依據(jù)類內(nèi)方差值進(jìn)行精剔除。最后再依據(jù)類內(nèi)方差值的大小實(shí)現(xiàn)車輛的提取。 在車輛跟蹤的問題中,深入研究了Camshift和Kalman濾波相結(jié)合的方法在車輛跟蹤中的應(yīng)用,并對(duì)目前的跟蹤算法中普遍存在的遮擋問題進(jìn)行了詳細(xì)的討論,最后通過增加區(qū)域面積約束,對(duì)算法進(jìn)行改進(jìn),提高了車輛在被遮擋和有顏色干擾的情況下的跟蹤的準(zhǔn)確性。 通過具體的實(shí)驗(yàn)表明,檢測(cè)算法能夠準(zhǔn)確的從動(dòng)態(tài)場(chǎng)景中檢測(cè)出運(yùn)動(dòng)的車輛,對(duì)單個(gè)運(yùn)動(dòng)車輛的檢測(cè)準(zhǔn)確度可達(dá)93%,多車輛的情況下,在車輛數(shù)量較少且較為分散的情況下能達(dá)到80%,具有較高的準(zhǔn)確性。同時(shí),算法也表現(xiàn)出了很好的跟蹤效果,在車輛被遮擋時(shí)間較短的情況下,仍然實(shí)現(xiàn)能夠穩(wěn)定的跟蹤。且算法基本上能達(dá)到實(shí)時(shí)性的要求。
[Abstract]:The detection and tracking technology of moving vehicles has always been an important research content in Intelligent Transportation system. At present, there are still many problems to be solved in the detection and tracking of vehicles. The detection of moving vehicles in dynamic scene makes it more difficult to extract vehicles due to the existence of two independent movements of vehicle and background. There is a great space for research on the accuracy of vehicle detection. In this paper, the problem that the wrong optical flow is difficult to be completely removed in the current optical flow detection methods is studied and discussed in detail, and an effective solution is proposed. At the same time, the method of clustering is used to extract the vehicle from the dynamic scene accurately. Finally, the vehicle tracking technology is studied, and the occlusion problem is discussed in detail, and the algorithm is improved to solve the problem effectively. In the problem of vehicle detection, the Harris operator is used to calculate the feature points of the image, and then the image characteristic point optical flow field is calculated by the pyramid Lucas-Kanade optical flow (L-K optical flow) method. Then the idea of vector quantization is introduced to cluster the optical flow field of the image, and the accuracy of clustering is improved by combining Euclidean distance and similarity coefficient as similarity measure. Finally, the distribution variance of corner points in each category is calculated, and the error optical flow in the optical flow field is eliminated rough by RANSAC method, and then refined elimination is carried out according to the intra-class variance value. Finally, the extraction of vehicles is realized according to the value of intra-class variance. In the problem of vehicle tracking, the application of Camshift and Kalman filtering in vehicle tracking is deeply studied, and the common occlusion problem in the current tracking algorithm is discussed in detail. Finally, the area constraint is added to the tracking algorithm. The algorithm is improved to improve the accuracy of vehicle tracking under occlusion and color interference. The experimental results show that the detection algorithm can accurately detect moving vehicles from the dynamic scene, and the detection accuracy of single moving vehicle can reach 933%, in the case of multiple vehicles, When the number of vehicles is small and scattered, it can reach 80% and has high accuracy. At the same time, the algorithm also shows a good tracking effect, in the case of vehicle occlusion time is short, still can achieve stable tracking. And the algorithm can basically achieve the requirement of real-time.
【學(xué)位授予單位】：中國(guó)科學(xué)技術(shù)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：U495

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 史新宏,蔡伯根,穆建成;智能交通系統(tǒng)的發(fā)展[J];北方交通大學(xué)學(xué)報(bào);2002年01期

2 施家棟;王建中;王紅茹;;基于光流的人體運(yùn)動(dòng)實(shí)時(shí)檢測(cè)方法[J];北京理工大學(xué)學(xué)報(bào);2008年09期

3 宋寅卯;李曉娟;劉磊;;圖像噪聲濾波的研究方法及進(jìn)展[J];電腦開發(fā)與應(yīng)用;2010年04期

4 李俊韜,張海,范躍祖,王力;復(fù)雜場(chǎng)景條件下的運(yùn)動(dòng)目標(biāo)檢測(cè)算法[J];光電工程;2004年S1期

5 李智華,王玉文;卡爾曼濾波在圖象識(shí)別中的應(yīng)用[J];哈爾濱師范大學(xué)自然科學(xué)學(xué)報(bào);2005年03期

6 王宏,何克忠,張鈸;智能車輛的自主駕駛與輔助導(dǎo)航[J];機(jī)器人;1997年02期

7 楊建榮;曲仕茹;;基于單目視覺的障礙物檢測(cè)方法研究[J];計(jì)算機(jī)仿真;2009年02期

8 郭慶昌;蔡劏;郭盛雨;;基于均值移動(dòng)算法的圖像分割的研究[J];計(jì)算機(jī)仿真;2010年02期

9 郭磊;李克強(qiáng);王建強(qiáng);連小珉;;一種基于特征的車輛檢測(cè)方法[J];汽車工程;2006年11期

10 周志宇,汪亞明,黃文清,曹麗,周海英;基于熵的運(yùn)動(dòng)目標(biāo)檢測(cè)[J];微計(jì)算機(jī)信息;2003年05期

，

本文編號(hào)：2336110