【摘要】：進(jìn)入二十一世紀(jì)以來(lái)，我國(guó)社會(huì)和經(jīng)濟(jì)得到快速發(fā)展，城市化進(jìn)程不斷加快，城市道路的交通壓力也在不斷增大，城市交通擁堵現(xiàn)象愈發(fā)嚴(yán)重，，且機(jī)動(dòng)車(chē)數(shù)量的日益增加導(dǎo)致城市道路交通事故頻發(fā)。傳統(tǒng)的交通事故檢測(cè)和查閱通常是通過(guò)人工監(jiān)測(cè)的方式進(jìn)行的，但這種方法效率低、實(shí)時(shí)性較差。隨著智能交通的迅速發(fā)展以及計(jì)算機(jī)視覺(jué)技術(shù)的廣泛應(yīng)用，利用視頻圖像處理技術(shù)對(duì)道路監(jiān)控視頻進(jìn)行實(shí)時(shí)分析、智能檢測(cè)交通事故、獲取交通信息成為了研究的熱點(diǎn)。對(duì)交通事故的實(shí)時(shí)檢測(cè)不僅可以減少警力資源的浪費(fèi)，而且對(duì)于提高交通事故處理效率有著重大的意義。 本文主要基于視頻對(duì)交通事故的自動(dòng)判別算法進(jìn)行研究，論文的主要研究?jī)?nèi)容如下：首先介紹了運(yùn)動(dòng)目標(biāo)檢測(cè)的技術(shù)難點(diǎn)，歸納了初始化背景模型的常用方法，并利用均值法背景建模方法提取背景圖像，獲得初始背景之后，通過(guò)背景更新算法使背景及時(shí)更新到當(dāng)前狀態(tài)；然后利用背景差分法提取差分圖像，并對(duì)車(chē)輛陰影進(jìn)行去除后進(jìn)行連通區(qū)域標(biāo)定，實(shí)現(xiàn)運(yùn)動(dòng)目標(biāo)的檢測(cè)。通過(guò)進(jìn)行實(shí)驗(yàn)并進(jìn)行效果分析，驗(yàn)證了算法的有效性。運(yùn)動(dòng)目標(biāo)跟蹤算法部分，首先介紹了卡爾曼濾波器的工作原理，應(yīng)用卡爾曼濾波對(duì)運(yùn)動(dòng)目標(biāo)進(jìn)行跟蹤與匹配，利用運(yùn)動(dòng)前景的質(zhì)心距離和面積大小作為匹配參數(shù)；運(yùn)動(dòng)目標(biāo)特征提取部分，首先對(duì)攝像機(jī)標(biāo)定算法進(jìn)行分析，然后根據(jù)前一章運(yùn)動(dòng)目標(biāo)檢測(cè)和匹配跟蹤的結(jié)果，通過(guò)提取前景目標(biāo)的運(yùn)動(dòng)信息，計(jì)算目標(biāo)的速度、行駛方向和軌跡等特征。通過(guò)卡爾曼濾波預(yù)測(cè)運(yùn)動(dòng)目標(biāo)下一幀質(zhì)心點(diǎn)坐標(biāo)，并與檢測(cè)到的前景質(zhì)心位置進(jìn)行比較，判斷檢測(cè)到的前景是否為重合的前景，如果兩個(gè)前景目標(biāo)發(fā)生重合，則發(fā)生了交通沖突。然后，對(duì)交通沖突作進(jìn)一步判斷，提出了綜合車(chē)輛減速度、行駛方向變化率和時(shí)間參數(shù)的自動(dòng)判別交通事故的算法，對(duì)車(chē)輛造成的遮擋情況和偽碰撞現(xiàn)象進(jìn)行識(shí)別，最終判斷交通事故是否發(fā)生。最后通過(guò)實(shí)驗(yàn)進(jìn)行驗(yàn)證，證明了判別算法的有效性，同時(shí)分析了實(shí)驗(yàn)存在的誤差。
[Abstract]:Since the 21 century, the society and economy of our country have been developed rapidly, the process of urbanization has been quickened, the traffic pressure of urban roads is also increasing, and the phenomenon of urban traffic congestion is becoming more and more serious. And the increasing number of motor vehicles leads to frequent urban road traffic accidents. The traditional method of traffic accident detection and inspection is usually carried out by manual monitoring, but this method is inefficient and poor in real time. With the rapid development of intelligent transportation and the wide application of computer vision technology, real-time analysis of road surveillance video using video image processing technology, intelligent detection of traffic accidents, access to traffic information has become a research hotspot. The real-time detection of traffic accidents can not only reduce the waste of police resources, but also improve the efficiency of traffic accidents. The main contents of this paper are as follows: firstly, the technical difficulties of moving target detection are introduced, and the common methods of initializing background model are summarized. The background image is extracted by the mean method, and the background is updated to the current state by the background updating algorithm. Then the background difference method is used to extract the differential image, and then the connected region is calibrated after removing the shadow of the vehicle, and the moving object detection is realized. The effectiveness of the algorithm is verified by experiment and effect analysis. In the part of moving target tracking algorithm, firstly, the working principle of Kalman filter is introduced. Kalman filter is used to track and match moving target, and the centroid distance and area of moving foreground are used as matching parameters. In the part of feature extraction of moving targets, the camera calibration algorithm is analyzed first, and then according to the results of moving target detection and matching and tracking in the previous chapter, the velocity of the target is calculated by extracting the moving information of the foreground target. Driving direction and trajectory and other characteristics. The coordinates of the next frame centroid of moving target are predicted by Kalman filter, and compared with the detected centroid position of foreground, to judge whether the detected foreground is the same prospect, if the two foreground targets overlap, Traffic conflicts occur. Then, the traffic conflict is judged further, and an algorithm is proposed to automatically distinguish traffic accidents by synthesizing vehicle deceleration, direction change rate and time parameters, and to identify the occlusion and pseudo-collision caused by vehicles. Finally determine whether the traffic accident occurred. Finally, the validity of the discriminant algorithm is verified by experiments, and the error of the experiment is analyzed.
【學(xué)位授予單位】：吉林大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類(lèi)號(hào)】：U491.31;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前9條

1 王國(guó)鋒;宋鵬飛;張?zhí)N靈;;智能交通系統(tǒng)發(fā)展與展望[J];公路;2012年05期

2 張勇;余建平;孫軍偉;金鐵;;基于Harris的角點(diǎn)匹配算法研究[J];計(jì)算機(jī)與現(xiàn)代化;2011年11期

3 孫秋云;;改進(jìn)的卡爾曼濾波算法在行駛汽車(chē)狀態(tài)估計(jì)中的應(yīng)用現(xiàn)狀[J];價(jià)值工程;2011年19期

4 ;Traficon視頻檢測(cè)的世界級(jí)參考標(biāo)準(zhǔn)——TrafiCam一體化路口視頻車(chē)輛檢測(cè)器[J];中國(guó)交通信息產(chǎn)業(yè);2007年02期

5 施毅;路小波;黃衛(wèi);劉濤;;基于時(shí)空馬爾可夫隨機(jī)場(chǎng)模型的車(chē)輛跟蹤算法研究[J];土木工程學(xué)報(bào);2007年01期

6 李勃;陳啟美;;基于監(jiān)控視頻的運(yùn)動(dòng)車(chē)輛行為分析算法[J];儀器儀表學(xué)報(bào);2006年S3期

7 湯淑明;王坤峰;李元濤;;基于視頻的交通事件自動(dòng)檢測(cè)技術(shù)綜述[J];公路交通科技;2006年08期

8 王兆華,劉志強(qiáng);視頻檢測(cè)技術(shù)在交通安全中的應(yīng)用[J];交通運(yùn)輸工程與信息學(xué)報(bào);2005年03期

9 劉相濱,向堅(jiān)持,陽(yáng)波;基于八鄰域邊界跟蹤的標(biāo)號(hào)算法[J];計(jì)算機(jī)工程與應(yīng)用;2001年23期

本文編號(hào)：2305604