發(fā)布時(shí)間：2018-08-06 19:52

【摘要】：高速公路分流區(qū)是高速公路安全瓶頸,為有效評(píng)價(jià)分流區(qū)安全服務(wù)水平,本文借助D-Lab人因數(shù)據(jù)采集與分析系統(tǒng)對(duì)分流區(qū)眼動(dòng)數(shù)據(jù)進(jìn)行采集、分析,利用交通沖突技術(shù)提取車輛軌跡,構(gòu)建考慮視覺特性的分流區(qū)換道風(fēng)險(xiǎn)評(píng)估模型。具體研究?jī)?nèi)容如下:(1)提出獲取視覺特性的試驗(yàn)方案。選取共25位駕駛員開展平行式有可選車道的單車道類型分流區(qū)實(shí)車試驗(yàn),獲取眼動(dòng)數(shù)據(jù),并利用參照物將注視點(diǎn)的像素坐標(biāo)轉(zhuǎn)換為唯一固定的二維坐標(biāo)。(2)實(shí)現(xiàn)興趣區(qū)域下眼動(dòng)數(shù)據(jù)分析。從基本眼動(dòng)、目標(biāo)注視、視線轉(zhuǎn)移三特征分析試驗(yàn)數(shù)據(jù),利用二元變量分析將注視點(diǎn)分布劃分為兩類,選取資深駕駛員注視點(diǎn)分布利用近鄰傳播聚類算法,通過調(diào)控阻尼系數(shù)λ與偏向參數(shù)p確立聚類數(shù)目,依照聚類結(jié)果將興趣區(qū)劃分為7部分,其中前窗采用放射線劃分,以此分析不同駕駛行為間視覺差異,共選取11類差異性顯著數(shù)據(jù)。(3)構(gòu)建換道決策模型。確定視覺特性指標(biāo)體系,利用主成分分析法降維,并提出基于支持向量機(jī)的非線性駕駛行為分類,以視覺特性參數(shù)獲取換道概率,判別駕駛行為類型。同時(shí)對(duì)比四種核函數(shù),結(jié)果表明,高斯徑向基函數(shù)核函數(shù)準(zhǔn)確率91.67%,靈敏度90.21%,適用于小樣本量、低維度情況。(4)提出基于預(yù)測(cè)軌跡的沖突嚴(yán)重程度判別方法。采用視頻檢測(cè)技術(shù),對(duì)固定背景下運(yùn)動(dòng)目標(biāo)進(jìn)行軌跡提取,利用神經(jīng)網(wǎng)絡(luò)實(shí)時(shí)預(yù)測(cè)軌跡,并引入量化指標(biāo)J以碰撞概率分析分流區(qū)兩車沖突嚴(yán)重程度。同時(shí)探討融合換道決策的碰撞概率算法,構(gòu)建融合視覺特性的分流區(qū)風(fēng)險(xiǎn)評(píng)估模型。結(jié)果顯示,指標(biāo)J考慮避險(xiǎn)行為對(duì)潛在沖突點(diǎn)出現(xiàn)時(shí)間的影響,準(zhǔn)確性更高;融合視覺特性的碰撞概率模型,準(zhǔn)確度85.71%、靈敏度92.75%,更接近于實(shí)際。
[Abstract]:In order to evaluate the security service level of the diversion area effectively, this paper collects and analyzes the eye movement data of the diversion area by means of the D-Lab Human cause data acquisition and Analysis system. Traffic conflict technology is used to extract vehicle trajectory, and a risk assessment model of diverging area with visual characteristics is constructed. The main contents are as follows: (1) the experimental scheme of obtaining visual characteristics is proposed. A total of 25 drivers were selected to carry out a parallel single-lane diverging area test with optional lanes to obtain eye movement data. The pixel coordinate of the fixation point is transformed into a unique two-dimensional coordinate by using the reference object. (2) the eye movement data analysis under the region of interest is realized. From the basic eye movement, target gaze, line of sight transfer three characteristic analysis test data, using the binary variable analysis to divide the fixation point distribution into two categories, select the senior driver fixed point distribution and use the nearest neighbor propagation clustering algorithm. The number of clusters is established by adjusting damping coefficient 位 and bias parameter p, according to the clustering results, the region of interest is divided into 7 parts, in which the front window is divided by radiation, so as to analyze the visual differences between different driving behaviors. A total of 11 types of significant difference data were selected. (3) the decision model of changing channels was constructed. The visual characteristic index system is determined, the dimension is reduced by principal component analysis, and the nonlinear driving behavior classification based on support vector machine is proposed. The change probability is obtained by the visual characteristic parameter, and the driving behavior type is distinguished. At the same time, the results show that the accuracy of Gao Si radial basis function kernel function is 91.67, the sensitivity is 90.21, and it is suitable for small sample size and low dimension. (4) A method for judging the severity of conflict based on prediction trajectory is proposed. Based on the video detection technique, the trajectory of moving target in fixed background is extracted, and the trajectory is predicted by neural network in real time. The impact probability is introduced to analyze the severity of collision between two vehicles in the split area. At the same time, the collision probability algorithm of fusion path changing decision is discussed, and the risk assessment model of shunt region is constructed based on fusion vision characteristics. The results show that the impact of risk avoidance behavior on the time of occurrence of potential conflict points is more accurate, and the collision probability model with visual characteristics is more accurate, with a sensitivity of 92.755.75, which is closer to reality.
【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】：2017
【分類號(hào)】：U491

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 丁世飛;齊丙娟;譚紅艷;;支持向量機(jī)理論與算法研究綜述[J];電子科技大學(xué)學(xué)報(bào);2011年01期

2 郭唐儀;鄧衛(wèi);侯建生;Lu John;;高速公路前置指路標(biāo)志設(shè)置距離及其安全影響(英文)[J];Journal of Southeast University(English Edition);2010年04期

3 徐慧智;程國(guó)柱;裴玉龍;;車道變換行為對(duì)道路通行能力影響的研究[J];中國(guó)科技論文在線;2010年10期

4 徐慧智;程國(guó)柱;裴玉龍;;車道變換行為對(duì)交通流運(yùn)行速度影響的研究[J];中國(guó)科技論文在線;2010年10期

5 王曉原;邢麗;吳芳;;車道變換決策仿真模型[J];計(jì)算機(jī)工程與應(yīng)用;2010年16期

6 裴玉龍;張銀;;車道變換期望運(yùn)行軌跡仿真[J];交通與計(jì)算機(jī);2008年04期

7 袁偉;付銳;郭應(yīng)時(shí);張建峰;;汽車駕駛?cè)烁兄獩Q策校正行為模式[J];長(zhǎng)安大學(xué)學(xué)報(bào)(自然科學(xué)版);2007年03期

8 郭應(yīng)時(shí);付銳;袁偉;張建峰;;通道寬度對(duì)駕駛員動(dòng)態(tài)視覺和操作行為的影響[J];中國(guó)公路學(xué)報(bào);2006年05期

9 楊京帥;預(yù)防道路交通事故的駕駛行為干預(yù)技術(shù)分析[J];人類工效學(xué);2005年03期

10 吳立新,王永君;交通事故中駕駛行為與道路線形的關(guān)系[J];吉林建筑工程學(xué)院學(xué)報(bào);2005年01期

，

本文編號(hào)：2168815