本文選題：車(chē)輛識(shí)別　切入點(diǎn)：視覺(jué)檢測(cè)　出處：《南京理工大學(xué)》2016年碩士論文

【摘要】：本文研究了基于單目視覺(jué)的行車(chē)預(yù)警系統(tǒng),分別在白天車(chē)輛檢測(cè)、夜間車(chē)輛檢測(cè)以及車(chē)輛跟蹤三大技術(shù)領(lǐng)域內(nèi)對(duì)國(guó)內(nèi)外各種研究成果進(jìn)行了分析對(duì)比,根據(jù)不同算法的特點(diǎn)以及在實(shí)際場(chǎng)景中遇到的問(wèn)題設(shè)計(jì)了相應(yīng)的改進(jìn)算法。在白天場(chǎng)景下的車(chē)輛檢測(cè)中,針對(duì)傳統(tǒng)的基于Hough變換的車(chē)道線檢測(cè)算法不能提取彎道車(chē)道線的缺點(diǎn),設(shè)計(jì)了基于對(duì)稱(chēng)搜索的四次多項(xiàng)式車(chē)道線擬合算法,減小了擬合誤差。針對(duì)直接將疑似車(chē)輛目標(biāo)結(jié)果輸入到SVM分類(lèi)器進(jìn)行分類(lèi)的方法效率低的特點(diǎn)設(shè)計(jì)了基于PCA降維算法的驗(yàn)證算法,即通過(guò)提取初步檢測(cè)結(jié)果的特征向量簡(jiǎn)化分類(lèi)器的輸入提高算法的檢測(cè)效率。在夜間車(chē)輛檢測(cè)中,針對(duì)傳統(tǒng)算法通過(guò)單一顏色閾值來(lái)分割車(chē)輛尾燈會(huì)誤檢測(cè)出其他發(fā)光背景的情況,分別建立了尾燈紅色光暈以及白色中心的HSV顏色模型,通過(guò)分別提取這兩種顏色來(lái)識(shí)別出車(chē)輛尾燈,并在獲得車(chē)輛尾燈初步檢測(cè)的基礎(chǔ)上利用證據(jù)融合算法來(lái)驗(yàn)證檢測(cè)到的車(chē)輛尾燈。在車(chē)輛跟蹤過(guò)程中,設(shè)計(jì)了基于運(yùn)動(dòng)模型和跟蹤隊(duì)列的車(chē)輛跟蹤算法,通過(guò)運(yùn)動(dòng)模型預(yù)估車(chē)輛目標(biāo)在下一幀中的位置,利用圖像匹配算法在預(yù)估位置周?chē)阉鬈?chē)輛目標(biāo),用搜索結(jié)果對(duì)運(yùn)動(dòng)模型進(jìn)行修正,并通過(guò)建立目標(biāo)的跟蹤隊(duì)列來(lái)完成對(duì)車(chē)輛的跟蹤。通過(guò)對(duì)實(shí)際道路場(chǎng)景上拍攝的視頻進(jìn)行處理的結(jié)果表明,在Windows 10操作系統(tǒng)以及3.2GHz CPU的環(huán)境下,采用本文設(shè)計(jì)的車(chē)輛檢測(cè)與跟蹤方法能夠準(zhǔn)確的檢測(cè)出前方車(chē)輛并且能夠達(dá)到每秒20幀的檢測(cè)速度,能夠滿(mǎn)足實(shí)時(shí)性的要求。
[Abstract]:In this paper, the vehicle warning system based on monocular vision is studied. The research results are analyzed and compared in three technical fields: daytime vehicle detection, night vehicle detection and vehicle tracking. According to the characteristics of different algorithms and the problems encountered in the actual scene, the corresponding improved algorithm is designed. In the daytime vehicle detection, the traditional lane line detection algorithm based on Hough transform can not extract the curve lane line. In this paper, a new algorithm for lane fitting based on symmetric search is proposed. The fitting error is reduced. A verification algorithm based on PCA dimension reduction algorithm is designed for the low efficiency of the method of directly inputting the suspected vehicle target results into the SVM classifier for classification. That is, the detection efficiency of the algorithm is improved by extracting the eigenvector of the preliminary detection results, which simplifies the input of the classifier. Aiming at the situation that the traditional algorithm can detect the other luminous background by using a single color threshold, the HSV color model of the red halo and the white center of the taillight is established. The two colors are extracted to identify the vehicle taillights, and the evidence fusion algorithm is used to verify the detected taillights on the basis of obtaining the initial detection of the vehicle taillights. The vehicle tracking algorithm based on motion model and tracking queue is designed. The motion model is used to estimate the position of vehicle target in the next frame, and the image matching algorithm is used to search the vehicle target around the predicted position. The motion model is modified with the search results, and the vehicle tracking is accomplished by setting up the tracking queue of the target. The results of processing the video taken on the actual road scene show that, In the environment of Windows 10 operating system and 3.2GHz CPU, the vehicle detection and tracking method designed in this paper can accurately detect forward vehicles and achieve 20 frames per second detection speed, which can meet the real-time requirements.
【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】：2016
【分類(lèi)號(hào)】：U463.6;TP277

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 王欣;高煒欣;武曉朦;王征;李華;;基于模糊模式識(shí)別的焊縫缺陷圖像檢測(cè)[J];西安石油大學(xué)學(xué)報(bào)(自然科學(xué)版);2016年04期

2 王威;胡桂明;楊麗;黃東芳;周楊;;基于ELM和PCA的漢語(yǔ)數(shù)字語(yǔ)音識(shí)別研究[J];電聲技術(shù);2015年11期

3 周斌;徐向華;;基于視頻的夜間車(chē)輛檢測(cè)與跟蹤[J];電子技術(shù)與軟件工程;2015年18期

4 王婭;;基于證據(jù)理論與變精度粗集的判斷矩陣的構(gòu)造[J];河南科學(xué);2014年04期

5 錢(qián)志明;楊家寬;段連鑫;;基于視頻的車(chē)輛檢測(cè)與跟蹤研究進(jìn)展[J];中南大學(xué)學(xué)報(bào)(自然科學(xué)版);2013年S2期

6 歐志芳;安吉堯;周芳麗;;利用D-S證據(jù)理論的夜間車(chē)輛檢測(cè)[J];計(jì)算機(jī)應(yīng)用研究;2012年05期

7 齊美彬;楊?lèi)?ài)麗;蔣建國(guó);李莉;;一種基于改進(jìn)碼本的車(chē)輛檢測(cè)與跟蹤方法[J];中國(guó)圖象圖形學(xué)報(bào);2011年03期

8 劉志強(qiáng);宋世亮;汪澎;仲晶晶;;基于視覺(jué)的車(chē)輛側(cè)后方道路圖像檢測(cè)技術(shù)[J];計(jì)算機(jī)工程與設(shè)計(jì);2010年12期

9 張春森;;基于點(diǎn)特征匹配的SUSAN,Harris算子比較[J];西安科技大學(xué)學(xué)報(bào);2007年04期

10 劉勃,周荷琴,魏銘旭;基于顏色和運(yùn)動(dòng)信息的夜間車(chē)輛檢測(cè)方法[J];中國(guó)圖象圖形學(xué)報(bào);2005年02期

相關(guān)博士學(xué)位論文 前1條

1 余天洪;基于機(jī)器視覺(jué)的車(chē)道偏離預(yù)警系統(tǒng)研究[D];吉林大學(xué);2006年

，

本文編號(hào)：1663630