本文選題：無(wú)人駕駛汽車 + 單目視覺(jué)��； 參考：《長(zhǎng)安大學(xué)》2016年博士論文

【摘要】：隨著汽車保有量的增長(zhǎng),越來(lái)越多的道路交通事故也給社會(huì)和人民造成了巨大的損失。其中,汽車駕駛?cè)说奈ｋU(xiǎn)駕駛行為是導(dǎo)致道路交通事故頻頻發(fā)生的主要原因。無(wú)人駕駛汽車因其無(wú)需人類駕駛操縱的特點(diǎn)具有廣闊的應(yīng)用前景。在無(wú)人駕駛汽車的行駛過(guò)程中,如何實(shí)時(shí)、魯棒地提取行駛環(huán)境信息,以及在獲得信息的基礎(chǔ)上進(jìn)行合理的運(yùn)動(dòng)決策是實(shí)現(xiàn)其安全、高效自主駕駛的關(guān)鍵,也是無(wú)人駕駛汽車研究中的難點(diǎn)和熱點(diǎn)。論文依托國(guó)家自然科學(xué)基金重大研究計(jì)劃項(xiàng)目(90920305)“無(wú)人駕駛車輛智能測(cè)試環(huán)境研究與開(kāi)發(fā)”和中央高�；饎�(chuàng)新團(tuán)隊(duì)項(xiàng)目(CHD2011TD006)“基于視覺(jué)信息的無(wú)人駕駛智能車輛關(guān)鍵技術(shù)研究”對(duì)無(wú)人駕駛汽車環(huán)境信息提取及運(yùn)動(dòng)決策方法展開(kāi)研究,以實(shí)現(xiàn)無(wú)人駕駛汽車安全、高效、智能地行駛。本文的研究?jī)?nèi)容主要包括:(1)視覺(jué)圖像數(shù)據(jù)采集模型和預(yù)處理研究。以無(wú)人駕駛汽車坐標(biāo)系作為約束條件,建立視覺(jué)圖像數(shù)據(jù)采集模型;針對(duì)圖像采集質(zhì)量易受行駛環(huán)境影響而造成特征難以提取的問(wèn)題,研究多尺度Retinex圖像增強(qiáng)算法和傳統(tǒng)中值濾波算法的改進(jìn)優(yōu)化算法,并進(jìn)行靜態(tài)離線對(duì)比試驗(yàn)。(2)針對(duì)復(fù)雜道路環(huán)境下車道標(biāo)線檢測(cè)算法魯棒性較差的問(wèn)題,提出面向圖像像素點(diǎn)的改進(jìn)道路圖像分割方法以深度挖掘車道標(biāo)線輪廓信息;在此基礎(chǔ)上提出基于抽樣行雙向掃描和成像模型約束候選特征點(diǎn)相結(jié)合的車道標(biāo)線檢測(cè)優(yōu)化算法。為了實(shí)現(xiàn)車道標(biāo)線檢測(cè)與跟蹤模塊的有效切換,建立置信度判別模塊和失效判別模塊。(3)針對(duì)非結(jié)構(gòu)化道路邊界檢測(cè)效率和魯棒性之間難以平衡的問(wèn)題,提出一種基于置信概率的分塊分類方法提取道路邊界的特征點(diǎn),在此基礎(chǔ)上運(yùn)用改進(jìn)的最小二乘法完成非結(jié)構(gòu)化道路模型參數(shù)求解,并進(jìn)行靜態(tài)離線對(duì)比試驗(yàn)。(4)針對(duì)無(wú)人駕駛汽車對(duì)前方車輛識(shí)別定位準(zhǔn)確性及穩(wěn)定性要求高的問(wèn)題,提出一種基于視覺(jué)傳感器和64線三維激光雷達(dá)信息融合的前方車輛識(shí)別算法。通過(guò)融合64線三維激光雷達(dá)提取的障礙物位置信息,確定圖像中前方車輛的感興趣區(qū)域;以類Haar-HOG融合特征作為目標(biāo)車輛描述方法,采用AdaBoost算法離線訓(xùn)練獲得的級(jí)聯(lián)分類器進(jìn)行前方車輛辨識(shí);對(duì)因遮擋問(wèn)題未被識(shí)別出前方車輛的感興趣區(qū)域,提出基于激光雷達(dá)坐標(biāo)系下位置關(guān)系信息的再確認(rèn)方法。(5)無(wú)人駕駛汽車運(yùn)動(dòng)決策建模方法研究。以宏觀行駛規(guī)劃為前提,在環(huán)境信息提取的基礎(chǔ)上,結(jié)合無(wú)人駕駛汽車的自身運(yùn)動(dòng)狀態(tài),對(duì)其在微觀動(dòng)態(tài)交通環(huán)境下的兩類基本運(yùn)動(dòng)模式進(jìn)行深入研究,設(shè)計(jì)無(wú)人駕駛汽車運(yùn)動(dòng)模式的決策條件及對(duì)應(yīng)目標(biāo)量;在此基礎(chǔ)上建立基于決策樹(shù)的運(yùn)動(dòng)決策模型;最后,通過(guò)構(gòu)建微觀動(dòng)態(tài)交通仿真環(huán)境對(duì)其進(jìn)行合理性驗(yàn)證。(6)搭建基于上位機(jī)組件的無(wú)人駕駛汽車平臺(tái),并對(duì)其廣義視覺(jué)傳感系統(tǒng)參數(shù)進(jìn)行標(biāo)定,在此基礎(chǔ)上進(jìn)行道路試驗(yàn),以驗(yàn)證論文提出的環(huán)境信息提取方法的有效性和運(yùn)動(dòng)決策模型的合理性。
[Abstract]:With the increase of car ownership, more and more road traffic accidents have caused great losses to the society and the people. Among them, the dangerous driving behavior of the motorists is the main cause of the frequent occurrence of road traffic accidents. The unmanned vehicle has a broad application prospect because of its characteristics without human driving. In the course of driving a vehicle, how to extract the information of the driving environment in real time, and to make a reasonable decision on the basis of obtaining information is the key to realizing its safety, high efficiency and autonomous driving. It is also a difficult and hot spot in the research of unmanned vehicle. The article relies on the National Natural Science Foundation of the National Science Foundation. Objective (90920305) "research and development of intelligent testing environment for unmanned vehicles" and the central university fund innovation team project (CHD2011TD006) "Research on the key technology of unmanned intelligent vehicle based on visual information" to study the extraction and decision method of unmanned vehicle environment information and movement, in order to realize the safety of unmanned vehicle. The main contents of this paper are as follows: (1) the model of visual image data acquisition and the research of preprocessing. Using the unmanned vehicle coordinate system as a constraint condition, the visual image data acquisition model is established, and the multi-scale Reti is studied for the problem that the quality of the image acquisition is easily affected by the driving environment and the feature is difficult to extract. NEX image enhancement algorithm and traditional median filter algorithm improved optimization algorithm, and static off-line contrast test. (2) aiming at the problem of poor robustness of lane marking detection algorithm in complex road environment, an improved road image segmentation method oriented to image pixels is proposed to dig the contour information of lane marking in depth. An optimization algorithm for lane marking detection based on combined sampling row bidirectional scanning and imaging model constraint candidate feature points is proposed. In order to realize the effective switching of lane marking detection and tracking module, confidence level discrimination module and failure discrimination module are established. (3) it is difficult to balance the efficiency and robustness of unstructured road boundary detection. In this paper, a block classification method based on confidence probability is proposed to extract the characteristic points of the road boundary. On this basis, the improved least square method is used to solve the parameters of unstructured road model, and the static off-line comparison test is carried out. (4) the requirements for the accuracy and stability of unmanned vehicle for the identification and positioning of the vehicle ahead are high. A new vehicle recognition algorithm based on visual sensor and 64 line 3D laser radar information fusion is proposed. The area of interest in the vehicle in front of the image is determined by integrating the information of the obstacle location extracted by the 64 line 3D laser radar, and the Haar-HOG fusion feature is used as the target vehicle description method and the AdaBoost algorithm is used. The cascade classifier obtained by off-line training is used to identify the vehicle ahead, and a reconfirmation method based on the location relationship information in the laser radar coordinate system is proposed. (5) a research on the modeling method for the decision making of the unmanned vehicle motion. On the basis of this, combined with the self driving state of unmanned vehicle, this paper makes a thorough study of the two basic models of motion in the micro dynamic traffic environment, designs the decision conditions and corresponding targets of the unmanned vehicle movement mode, and builds a decision model based on the decision tree. Finally, the microcosmic model is built. The dynamic traffic simulation environment is proved to be reasonable. (6) to build an unmanned vehicle platform based on the upper computer components, and to calibrate the parameters of its generalized visual sensing system. On this basis, a road test is carried out to verify the validity of the method of extracting environmental information and the rationality of the model of motion decision.

【學(xué)位授予單位】：長(zhǎng)安大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2016
【分類號(hào)】：U463.6

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 林一平;無(wú)人駕駛汽車逐步進(jìn)入實(shí)用化[J];專用汽車;2000年02期

2 林一平;新世紀(jì)的無(wú)人駕駛汽車[J];交通與運(yùn)輸;2000年02期

3 閆民;無(wú)人駕駛汽車的研究現(xiàn)狀及發(fā)展方向[J];汽車維修;2003年02期

4 林一平;不斷創(chuàng)新發(fā)展的現(xiàn)代無(wú)人駕駛汽車[J];專用汽車;2003年01期

5 薛福連;;自動(dòng)控制高速公路上的無(wú)人駕駛汽車[J];汽車運(yùn)用;2006年04期

6 喬維高;徐學(xué)進(jìn);;無(wú)人駕駛汽車的發(fā)展現(xiàn)狀及方向[J];上海汽車;2007年07期

7 李勇;;功能強(qiáng)大的無(wú)人駕駛汽車[J];駕駛園;2008年03期

8 ;英推出新款無(wú)人駕駛汽車[J];中國(guó)科技產(chǎn)業(yè);2009年08期

9 呂宏;劉大力;孫嘉燕;;從無(wú)人駕駛汽車奔赴世博會(huì)看未來(lái)汽車[J];機(jī)電產(chǎn)品開(kāi)發(fā)與創(chuàng)新;2010年06期

10 李崇寒;彭鑫;;無(wú)人駕駛汽車:可行還是不可行?[J];今日科苑;2011年12期

相關(guān)重要報(bào)紙文章 前10條

1 高釩;無(wú)人駕駛汽車問(wèn)世：終結(jié)“馬路殺手”？[N];新華每日電訊;2007年

2 東方汽車特約撰稿人 顏光明;“無(wú)人駕駛汽車”浮出水面的現(xiàn)實(shí)意義[N];東方早報(bào);2010年

3 記者 涂亞卓　通訊員 卓越;漢產(chǎn)“無(wú)人駕駛汽車”問(wèn)世[N];湖北日?qǐng)?bào);2010年

4 黃敏;無(wú)人駕駛汽車“獨(dú)自”駛上德國(guó)街頭[N];新華每日電訊;2011年

5 記者 秦勉;無(wú)人駕駛汽車上路,準(zhǔn)備好了么？[N];北京科技報(bào);2012年

6 嘉卉;2040年無(wú)人駕駛汽車將占75%[N];人民郵電;2012年

7 本報(bào)記者 張曉鳴;無(wú)人駕駛汽車在路上[N];文匯報(bào);2012年

8 華凌;豐田推出新款無(wú)人駕駛汽車[N];科技日?qǐng)?bào);2013年

9 記者 陳一鳴 劉軍國(guó) 黃發(fā)紅;無(wú)人駕駛汽車從銀幕駛?cè)氍F(xiàn)實(shí)[N];人民日?qǐng)?bào);2013年

10 特約撰稿 賽迪智庫(kù)工業(yè)安全生產(chǎn)研究所 胡文志;無(wú)人駕駛汽車近了[N];中國(guó)電子報(bào);2013年

相關(guān)博士學(xué)位論文 前1條

1 武歷穎;無(wú)人駕駛汽車環(huán)境信息提取及運(yùn)動(dòng)決策方法研究[D];長(zhǎng)安大學(xué);2016年

相關(guān)碩士學(xué)位論文 前10條

1 王詩(shī)源;與匝道車輛交互的無(wú)人駕駛汽車避撞系統(tǒng)研究[D];北京理工大學(xué);2015年

2 高玲玲;基于Multi-agents的自動(dòng)駕駛算法研究[D];遼寧科技大學(xué);2016年

3 耿以才;基于動(dòng)態(tài)人工勢(shì)場(chǎng)法無(wú)人駕駛汽車路徑規(guī)劃研究[D];上海工程技術(shù)大學(xué);2016年

4 潘魯彬;無(wú)人駕駛汽車的路徑規(guī)劃與跟隨控制算法研究[D];湖南大學(xué);2016年

5 任超;基于遺傳算法的無(wú)人駕駛汽車路徑規(guī)劃技術(shù)研究[D];天津大學(xué);2015年

6 蘭韻;無(wú)人駕駛汽車決策系統(tǒng)的規(guī)則建模與代碼生成方法[D];國(guó)防科學(xué)技術(shù)大學(xué);2014年

7 李陸浩;面向無(wú)人駕駛汽車的車道級(jí)導(dǎo)航研究[D];吉林大學(xué);2014年

8 許安玲;汽車無(wú)人導(dǎo)駕系統(tǒng)的研究[D];山東科技大學(xué);2008年

9 賈超;基于駕駛員模型的無(wú)人駕駛汽車路徑跟蹤控制[D];東北大學(xué);2012年

10 趙萬(wàn)里;基于雷達(dá)的智能車多目標(biāo)檢測(cè)與跟蹤技術(shù)研究[D];中南大學(xué);2011年

，

本文編號(hào)：1874052