本文選題：單目視覺(jué) + 車(chē)道線檢測(cè)　； 參考：《哈爾濱工程大學(xué)》2014年碩士論文

【摘要】：隨著社會(huì)的不斷進(jìn)步,汽車(chē)正為越來(lái)越多的人所使用,而相應(yīng)的,交通事故也越來(lái)越多。為解決這一問(wèn)題,越來(lái)越多國(guó)家開(kāi)始研究智能交通系統(tǒng)。而智能交通的核心基礎(chǔ)就是要檢測(cè)和跟蹤道路上的車(chē)輛,根據(jù)車(chē)輛位置信息來(lái)避免交通事故的發(fā)生。本文正是采用基于視覺(jué)的方法檢測(cè)和跟蹤前方車(chē)輛的。車(chē)輛檢測(cè)通常分為兩個(gè)步驟。首先確定車(chē)輛可能存在的區(qū)域,這其中包括路旁樹(shù)木等留下的虛假車(chē)輛陰影。接下來(lái)就要剔除虛假的車(chē)輛陰影,確定車(chē)輛的具體位置。正常情況下最有可能會(huì)與本車(chē)發(fā)生碰撞的前方車(chē)輛在本車(chē)道內(nèi),所以本文首先檢測(cè)車(chē)道線,根據(jù)車(chē)道線縮小車(chē)輛檢測(cè)的范圍,提高檢測(cè)效率和精度。在提取車(chē)道線的基礎(chǔ)上,利用車(chē)輛底部在道路上的陰影與路面灰度值的對(duì)比度較大,確定車(chē)輛可能存在的區(qū)域。再融合圖像熵等紋理特征剔除虛假的車(chē)輛陰影,準(zhǔn)確檢測(cè)出前方車(chē)輛。本文的主要工作如下:1.改進(jìn)了基于OTSU大津閾值法的自適應(yīng)二值化方法,采用通過(guò)統(tǒng)計(jì)道路樣本區(qū)域灰度值特性的方式來(lái)估算道路區(qū)域灰度值,這樣可以避免傳統(tǒng)OTSU對(duì)整幅圖像統(tǒng)計(jì)灰度值時(shí)計(jì)算量大且有非路面區(qū)域干擾的缺點(diǎn),提高算法實(shí)時(shí)性和準(zhǔn)確性。2.在車(chē)道線檢測(cè)算法中,運(yùn)用了形態(tài)學(xué)方法和邊緣提取方法后,設(shè)計(jì)了搜索車(chē)道線內(nèi)側(cè)邊緣的掃描算法,并通過(guò)對(duì)比霍夫變換的算法性能,采用了最小二乘法的擬合車(chē)道線方法。為進(jìn)一步提高算法效率,本文采用了車(chē)道線跟蹤算法,在前一幀圖像的車(chē)道線位置左右各擴(kuò)展50像素范圍內(nèi)搜索,大大降低了車(chē)道線檢測(cè)算法時(shí)間。根據(jù)檢測(cè)到的車(chē)道線結(jié)果,本文計(jì)算了每幀圖像車(chē)輛的偏航角,當(dāng)偏航角超過(guò)給定閾值時(shí)即表明車(chē)輛即將偏離本車(chē)道,此時(shí)可發(fā)出光聲等信號(hào)提醒司機(jī)采取措施。3.在車(chē)輛檢測(cè)與跟蹤算法中,本文在基于陰影檢測(cè)的算法基礎(chǔ)上,結(jié)合圖像熵值和灰度圖像對(duì)稱(chēng)性排除虛假車(chē)輛區(qū)域,檢測(cè)出車(chē)輛在圖像中位置信息,并采用基于卡爾曼濾波的跟蹤方法,在保證檢測(cè)精度的同時(shí)提高了檢測(cè)效率,增強(qiáng)了算法的實(shí)時(shí)性。4.本文建立了安全車(chē)距的防碰撞模型,即相對(duì)車(chē)速與最大制動(dòng)距離之間的關(guān)系,并且給出了基于視覺(jué)的測(cè)距模型,根據(jù)圖像中檢測(cè)到的車(chē)輛坐標(biāo)即可計(jì)算出車(chē)距,進(jìn)而估算出碰撞時(shí)間。本文使用C++語(yǔ)言利用視覺(jué)處理庫(kù)OpenCV1.0編寫(xiě)了前方車(chē)輛檢測(cè)系統(tǒng)軟件,并采集了多段道路視頻進(jìn)行實(shí)驗(yàn)。實(shí)驗(yàn)結(jié)果表明本文算法滿(mǎn)足實(shí)時(shí)性要求,在光照條件良好路段能穩(wěn)定的跟蹤前方車(chē)輛目標(biāo),對(duì)于路況復(fù)雜情況也具有一定魯棒性。
[Abstract]:With the development of society, more and more people are using cars, and accordingly, more and more traffic accidents. In order to solve this problem, more and more countries begin to study its. The core of Intelligent Transportation (its) is to detect and track vehicles on the road and to avoid traffic accidents according to the information of vehicle location. In this paper, vision-based methods are used to detect and track forward vehicles. Vehicle testing is usually divided into two steps. First, identify areas where the vehicle may exist, including false vehicle shadows left by roadside trees and so on. The next step is to remove the false shadow of the vehicle and determine the exact location of the vehicle. Under normal circumstances, the front vehicle most likely to collide with the vehicle is in the driveway, so this paper first detects the lane line, narrows the range of vehicle detection according to the lane line, and improves the detection efficiency and accuracy. Based on the extraction of the lane line, the contrast between the shadow at the bottom of the vehicle on the road and the gray value of the road surface is great, and the possible area of the vehicle is determined. Then fusion the image entropy and other texture features to eliminate the false shadow of the vehicle and accurately detect the vehicle ahead. The main work of this paper is as follows: 1. An adaptive binarization method based on Otsu Otsu threshold method is improved to estimate the gray value of road area by statistics of the gray value characteristics of road sample area. In this way, the traditional OTSU can avoid the disadvantages of large computation and non-road area interference when the whole image is calculated by using OTSU, and improve the real-time and accuracy of the algorithm. In the lane line detection algorithm, after using morphological method and edge extraction method, a scanning algorithm is designed to search the inner edge of lane line. By comparing the performance of Hough transform, the least square method is used to fit the lane line. In order to further improve the efficiency of the algorithm, a lane tracking algorithm is adopted in this paper, which searches within the range of 50 pixels about the location of the lane line of the previous frame image, which greatly reduces the time of the lane line detection algorithm. Based on the detected lane line results, this paper calculates the yaw angle of the vehicle in each frame image. When the yaw angle exceeds the given threshold, it indicates that the vehicle is about to deviate from the driveway. At this time, the driver can be warned to take action by means of light and sound signals. In the vehicle detection and tracking algorithm, based on the shadow detection algorithm, combined with the image entropy and gray image symmetry to eliminate the false vehicle area, the vehicle position information in the image is detected. The tracking method based on Kalman filter is used to ensure the detection accuracy and improve the detection efficiency, and enhance the real-time performance of the algorithm. In this paper, the anti-collision model of safe vehicle distance is established, that is, the relation between relative speed and maximum braking distance, and the distance measurement model based on vision is given. The distance can be calculated according to the vehicle coordinates detected in the image. Then the collision time is estimated. In this paper, we use C language and OpenCV1.0 to compile the software of the vehicle detection system in front, and collect the video of many sections of the road to carry on the experiment. The experimental results show that the proposed algorithm can meet the real-time requirements and can track the vehicle targets stably in good lighting conditions. It is also robust to complex road conditions.
【學(xué)位授予單位】：哈爾濱工程大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類(lèi)號(hào)】：U495;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前7條

1 辛英;于靜;;自適應(yīng)卡爾曼濾波算法改進(jìn)與仿真[J];中國(guó)科技信息;2011年22期

2 王偉;;評(píng)智能汽車(chē)時(shí)代的雷達(dá)模擬前端——ADI公司單個(gè)IC實(shí)現(xiàn)自適應(yīng)巡航控制和盲點(diǎn)檢測(cè)[J];電子技術(shù)應(yīng)用;2011年07期

3 胡穎;崔偉峰;;Otsu多閾值分割算法的研究[J];鄭州輕工業(yè)學(xué)院學(xué)報(bào)(自然科學(xué)版);2010年02期

4 孫英慧;蒲東兵;;基于拉普拉斯算子的邊緣檢測(cè)研究[J];長(zhǎng)春師范學(xué)院學(xué)報(bào)(人文社會(huì)科學(xué)版);2009年12期

5 程軍娜;姬光榮;馮晨;;基于數(shù)學(xué)形態(tài)學(xué)的藻細(xì)胞圖像預(yù)處理[J];中國(guó)海洋大學(xué)學(xué)報(bào)(自然科學(xué)版);2008年03期

6 楊紅梅;馬茂冬;;PLC系統(tǒng)中的數(shù)字濾波技術(shù)[J];自動(dòng)化技術(shù)與應(yīng)用;2007年12期

7 張旭明,徐濱士,董世運(yùn),甘小明;自適應(yīng)中值-加權(quán)均值混合濾波器[J];光學(xué)技術(shù);2004年06期

相關(guān)博士學(xué)位論文 前2條

1 王楠;基于多視覺(jué)特征融合的后方車(chē)輛檢測(cè)技術(shù)研究[D];東北大學(xué)　;2009年

2 胡銦;基于單目視覺(jué)的運(yùn)動(dòng)目標(biāo)檢測(cè)與跟蹤算法研究[D];南京理工大學(xué);2008年

相關(guān)碩士學(xué)位論文 前10條

1 閆巧云;基于單目視覺(jué)與多特征的前方車(chē)輛檢測(cè)算法研究[D];中南大學(xué);2012年

2 王孝艷;基于卡爾曼濾波的動(dòng)目標(biāo)視覺(jué)跟蹤方法研究[D];沈陽(yáng)理工大學(xué);2012年

3 肖剛;車(chē)道偏離預(yù)警系統(tǒng)的設(shè)計(jì)與實(shí)現(xiàn)[D];廣東工業(yè)大學(xué);2011年

4 劉鋁;基于內(nèi)容的圖像檢索方法的研究與實(shí)現(xiàn)[D];湖南大學(xué);2011年

5 呂欣;基于智能車(chē)輛視覺(jué)導(dǎo)航的道路檢測(cè)技術(shù)的研究[D];青島科技大學(xué);2010年

6 陳光華;強(qiáng)噪聲信號(hào)的數(shù)字分析與處理及其在FPGA上的實(shí)現(xiàn)[D];電子科技大學(xué);2010年

7 楊萬(wàn)挺;基于局部信息特征的霧天圖像增強(qiáng)算法研究[D];合肥工業(yè)大學(xué);2010年

8 吳林成;基于視覺(jué)的高速公路車(chē)道線檢測(cè)算法研究[D];合肥工業(yè)大學(xué);2010年

9 徐楊;基于視頻序列的運(yùn)動(dòng)目標(biāo)檢測(cè)和跟蹤算法研究[D];合肥工業(yè)大學(xué);2010年

10 趙保佑;基于視覺(jué)的車(chē)輛檢測(cè)與跟蹤技術(shù)研究[D];武漢理工大學(xué);2009年

，

本文編號(hào)：2025893