本文選題：夜間交通視頻　切入點(diǎn)：中遠(yuǎn)景車燈　出處：《天津工業(yè)大學(xué)》2017年碩士論文

【摘要】：近幾年來(lái),由于夜間事故的頻發(fā)和其環(huán)境的復(fù)雜性,夜間車輛檢測(cè)作為系統(tǒng)中的一部分,加上智能交通系統(tǒng)車輛檢測(cè)技術(shù)越發(fā)嫻熟,對(duì)該方面的研究越來(lái)越受國(guó)內(nèi)外學(xué)者以及企業(yè)的關(guān)注和重視。夜間交通環(huán)境下,照明條件不足,導(dǎo)致車輛如輪廓、顏色等信息的丟失,這些因素極大的限制了夜間車輛的檢測(cè)。車輛在運(yùn)動(dòng)過(guò)程中,車燈的相對(duì)于車輛其它特征信息而言較為穩(wěn)定、可靠,因此目前關(guān)于夜間車輛的檢測(cè)大多數(shù)以車燈作為研究的主要特征選擇。但是由于夜間場(chǎng)景中環(huán)境光及車燈強(qiáng)反射光的干擾,以及視野遠(yuǎn)處的車輛車燈容易粘連。針對(duì)以上的這些問(wèn)題,本文提出了基于大氣散射原理構(gòu)建模型檢測(cè)夜間交通視頻多景深車燈的方法,以解決提高檢測(cè)率的基礎(chǔ)上延長(zhǎng)車輛車燈的檢測(cè)范圍。我們主要是通過(guò)對(duì)夜間場(chǎng)景下所有光源及其對(duì)圖像成像過(guò)程中的影響進(jìn)行了分析,并根據(jù)大氣散射原理構(gòu)建了車燈復(fù)原模型,以實(shí)現(xiàn)夜間車輛的檢測(cè)。通過(guò)所構(gòu)建的模型對(duì)夜間交通視頻的車燈復(fù)原時(shí),需要先對(duì)模型中透射率、環(huán)境光以及場(chǎng)景景深等參量的估計(jì):透射率的估計(jì)是通過(guò)對(duì)原始圖像取反歸一化得到.,本文中所定義的環(huán)境光不僅是指夜間場(chǎng)景中如路燈、廣告牌等光源形成的環(huán)境光,還有車輛行駛過(guò)程中車燈的本身散射以及車燈在路面的反射光引起場(chǎng)景光源變化的環(huán)境光,即背景環(huán)境光和車燈區(qū)域環(huán)境光,然后對(duì)圖像經(jīng)相應(yīng)的處理之后分別通過(guò)暗原色通道原理估計(jì)得到;在同一場(chǎng)景中不同景深的車燈在傳輸過(guò)程中經(jīng)大氣散射的程度不同,本文在模型中引入了場(chǎng)景景深參量,并根據(jù)透射率公式估計(jì)該參量。最后通過(guò)復(fù)原模型得到了車燈復(fù)原結(jié)果。由于場(chǎng)景中強(qiáng)反射光與車燈的亮度值相近,會(huì)同車燈一起被復(fù)原,因此需要進(jìn)一步篩選。本文考慮到不同景深對(duì)車燈的影響,車燈的特征信息也會(huì)因不同景深而不同,所以劃分區(qū)域分別對(duì)相應(yīng)區(qū)域的光斑進(jìn)行篩選,使車燈與路面強(qiáng)反射光分離,從而達(dá)到車燈檢測(cè)的目的。通過(guò)對(duì)9段視頻,共14492幀進(jìn)行測(cè)試,結(jié)果表明,在延長(zhǎng)了檢測(cè)距離的同時(shí),本文所提模型與同類先進(jìn)算法相比,平均檢測(cè)率提高了 31.39%,平均漏檢率降低了 20.93%,平均誤檢率降低了 10.46%。
[Abstract]:In recent years, due to the frequent occurrence of night accidents and the complexity of its environment, nighttime vehicle detection as a part of the system, plus the intelligent transportation system vehicle detection technology, has become more and more skillful. The research on this aspect has been paid more and more attention by domestic and foreign scholars and enterprises. Under the traffic environment at night, the lighting conditions are insufficient, resulting in the loss of information such as the outline and color of the vehicle, etc. These factors greatly limit the detection of vehicles at night. In the course of vehicle movement, the lights of vehicles are relatively stable and reliable in comparison with other characteristic information of vehicles. Therefore, at present, most of the detection of nighttime vehicles is based on vehicle lights. However, due to the interference of the ambient light and the strong reflected light of the vehicle lights in the night scene, In view of these problems, this paper presents a model based on atmospheric scattering theory to detect multi-field vehicle lights in night traffic video. In order to solve the problem of increasing the detection rate, we extend the detection range of vehicle lights. We mainly analyze all the light sources in the night scene and their influence on the image imaging process. According to the principle of atmospheric scattering, the vehicle light restoration model is constructed to detect the night vehicle. The transmissivity of the model is needed to restore the vehicle lights of the night traffic video through the built model. Estimation of environmental light and scene depth of field: the estimation of transmittance is obtained by reverse-normalization of the original image. The ambient light defined in this paper not only refers to the ambient light formed by light sources such as street lights and billboards in the night scene. There is also the background ambient light and the regional ambient light of the vehicle lamp, which is caused by the scattering of the vehicle lights and the reflected light of the vehicle lights on the road. Then the image is estimated by the principle of dark primary channel after the corresponding processing. In the same scene, the different depth of field lights in the transmission of different degrees of atmospheric scattering, this paper introduced the scene depth parameters in the model. The parameters are estimated according to the transmittance formula. Finally, the restoration results of the vehicle lamp are obtained by the restoration model. Because the strong reflected light in the scene is close to the luminance value of the vehicle lamp, it is restored together with the vehicle lamp. Therefore, further screening is needed. Considering the influence of different depth of field on vehicle lamp, the characteristic information of vehicle lamp will also be different according to different depth of field. The vehicle lamp is separated from the road surface strongly reflected light, and the purpose of vehicle lamp detection is achieved. Through the test of 9 video segments, 14492 frames are tested. The results show that the model proposed in this paper is compared with the similar advanced algorithm while prolonging the detection distance. The average detection rate increased 31.39 percent, the average missed detection rate decreased 20.93 percent and the average false detection rate decreased 10.46 percent.
【學(xué)位授予單位】：天津工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：U495;TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前4條

1 楊祖貴,陳仲林;大氣散射方向指數(shù)函數(shù)研究[J];照明工程學(xué)報(bào);1998年02期

2 楊祖貴,陳仲林;大氣散射方向指數(shù)函數(shù)研究[J];重慶建筑大學(xué)學(xué)報(bào);1998年06期

3 張巖岫;王志清;劉立武;梁冬明;徐天野;;大氣散射對(duì)激光制導(dǎo)武器對(duì)抗態(tài)勢(shì)構(gòu)建影響研究[J];現(xiàn)代電子技術(shù);2012年21期

4 ;[J];;年期

相關(guān)會(huì)議論文 前1條

1 徐耀坤;劉偉濤;張二峰;黎全;陳平形;;大氣散射對(duì)關(guān)聯(lián)成像的影響[A];第十六屆全國(guó)量子光學(xué)學(xué)術(shù)報(bào)告會(huì)報(bào)告摘要集[C];2014年

相關(guān)重要報(bào)紙文章 前1條

1 王乃仙;月球上的晝和夜[N];北京科技報(bào);2000年

相關(guān)碩士學(xué)位論文 前3條

1 徐耀坤;大氣散射對(duì)關(guān)聯(lián)成像的影響[D];國(guó)防科學(xué)技術(shù)大學(xué);2014年

2 林祥清;基于大氣散射原理構(gòu)建模型檢測(cè)夜間交通視頻多景深車燈[D];天津工業(yè)大學(xué);2017年

3 王少游;地球靜止軌道區(qū)域凝視光學(xué)系統(tǒng)成像性能分析[D];哈爾濱工業(yè)大學(xué);2009年

，

本文編號(hào)：1663871