本文關(guān)鍵詞：復(fù)雜場景下的交通標(biāo)志識(shí)別技術(shù)研究　出處：《合肥工業(yè)大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 交通安全 灰度形態(tài)學(xué) Hough變換 交通標(biāo)志定位 支持向量機(jī)分類

【摘要】：隨著城市建設(shè)規(guī)模的不斷擴(kuò)大,市民生活水平正逐步提高,極大程度地加快了人們的生活節(jié)奏,私家車儼然成為眾多市民出行的重要交通工具。然而,隨著路面機(jī)動(dòng)車輛的不斷增加,在給人們帶來便利的同時(shí),也造成一些不容忽視的交通問題——道路交通擁堵和交通安全。而這些問題一方面與駕駛員的駕駛行為有著緊密的聯(lián)系,如酒駕、路怒、駕駛經(jīng)驗(yàn)和不規(guī)范的駕駛行為等;另一方面與我國尚未健全的交通管理措施有關(guān),如何建立規(guī)范有效的解決方案已成為世界各國共同克服的難題。目前,有眾多學(xué)者認(rèn)為:大規(guī)模地普及應(yīng)用智能交通技術(shù),提高道路交通管理水平和智能駕駛系統(tǒng)運(yùn)行質(zhì)量是實(shí)現(xiàn)道路交通系統(tǒng)良性發(fā)展的一條有效途徑。交通標(biāo)志作為道路中一種重要的基礎(chǔ)輔助設(shè)施,通過提供指示和禁令等駕駛信息對(duì)交通流量的疏導(dǎo),并且規(guī)范駕駛員的交通行為,確保交通秩序井然有序的進(jìn)行。道路交通標(biāo)志識(shí)別(Road traffic sign recognition.RTSR)作為其智能駕駛輔助系統(tǒng)的關(guān)鍵技術(shù)之一,引起眾多學(xué)者和相關(guān)科研機(jī)構(gòu)的重視和研究。對(duì)于應(yīng)用在實(shí)際場景下的交通標(biāo)志識(shí)別系統(tǒng),其所面臨的道路背景日趨復(fù)雜,而且所設(shè)計(jì)的識(shí)別系統(tǒng)對(duì)實(shí)時(shí)性和高效性的要求較高,這無疑是一個(gè)巨大的挑戰(zhàn)。本文主要針對(duì)復(fù)雜環(huán)境下的道路交通標(biāo)志的定位和識(shí)別相關(guān)算法展開了討論:首先依據(jù)交通標(biāo)志的形狀特征,提出了基于小波低頻分量的邊緣檢測方法,檢測出交通標(biāo)志圖像的邊緣信息,接著,對(duì)其進(jìn)行灰度形態(tài)學(xué)和紋理降噪處理,削弱灰度邊緣圖像中的噪聲干擾區(qū)域,然后,對(duì)降噪后的灰度圖像進(jìn)行二值化處理,隨后,采用改良的Hough變換方法分割出路標(biāo)區(qū)域,進(jìn)而定位出交通標(biāo)志圖像。對(duì)自然場景下拍攝的交通標(biāo)志圖像進(jìn)行算法測試,試驗(yàn)表明:該算法的定位準(zhǔn)確率為91.8%,平均定位時(shí)間為0.46s;最后,采用Hu不變矩提取樣本和定位到的標(biāo)志圖像的特征向量,并使用支持向量機(jī)進(jìn)行分類識(shí)別出其含義,同時(shí)采用了最小距離分類方法進(jìn)行了比較。
[Abstract]:With the continuous expansion of the scale of urban construction, the standard of living of citizens is gradually improving, greatly accelerating the pace of people's lives, private cars have become an important means of transportation for many citizens to travel. With the increasing number of road motor vehicles, it brings convenience to people at the same time. It also causes some traffic problems that can't be ignored-road traffic congestion and traffic safety. On the one hand, these problems are closely related to driver's driving behavior, such as drunk driving, road rage. Driving experience and irregular driving behavior; On the other hand, with the unsound traffic management measures in China, how to establish a standardized and effective solution has become a common problem that all countries in the world overcome. Many scholars believe that the application of intelligent transportation technology is widely used in a large scale. Improving the level of road traffic management and the quality of intelligent driving system is an effective way to realize the benign development of road traffic system. Traffic signs as an important basic auxiliary facilities in the road. Through the provision of guidance and ban on driving information to the traffic flow, and regulate the traffic behavior of drivers. Ensure that traffic order is in order. Road traffic sign recognition. RTSR). As one of the key technologies of its intelligent driving assistance system. It has attracted the attention and research of many scholars and related research institutions. For the traffic sign recognition system which is applied in the actual scene, the road background is becoming more and more complex. And the design of the recognition system for real-time and high efficiency requirements. This is undoubtedly a huge challenge. This paper mainly discusses the location and recognition algorithms of road traffic signs in complex environment: firstly, according to the shape characteristics of traffic signs. An edge detection method based on wavelet low frequency component is proposed to detect the edge information of traffic sign image. Then the gray level morphology and texture denoising are processed. The noise interference area in the gray edge image is weakened, then the gray image is binary processed, and then the improved Hough transform method is used to segment the signpost area. Then the traffic sign image is located. The algorithm test of the traffic sign image taken under the natural scene shows that the localization accuracy of the algorithm is 91.8 and the average positioning time is 0.46s; Finally, Hu moment invariant moment is used to extract the feature vector of the image and the support vector machine (SVM) is used to classify and recognize its meaning. At the same time, the minimum distance classification method is compared.
【學(xué)位授予單位】：合肥工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 吳巍;楊帆;許東;徐穎鑫;;基于灰度形態(tài)學(xué)重構(gòu)的目標(biāo)檢測[J];科技資訊;2011年04期

2 ;基于灰度形態(tài)學(xué)的�？毡尘跋碌募t外點(diǎn)目標(biāo)檢測算法[J];中國計(jì)量學(xué)院學(xué)報(bào);2001年02期

3 孫忠貴;王玲;;一個(gè)關(guān)于脈沖噪聲去除的灰度形態(tài)學(xué)模型[J];計(jì)算機(jī)應(yīng)用與軟件;2006年06期

4 海濤,鮑遠(yuǎn)律;消除彩色城市地圖中道路上的文字噪聲[J];微型機(jī)與應(yīng)用;2004年04期

5 李秀忠;高向東;;灰度形態(tài)學(xué)在焊縫圖像處理中的應(yīng)用[J];焊接;2007年10期

6 侯德鵬;劉政清;路遠(yuǎn);;綜合灰度形態(tài)學(xué)與模糊熵的紅外圖像區(qū)域分割[J];光電技術(shù)應(yīng)用;2007年03期

7 郭駿;潘申;胡小建;;基于灰度形態(tài)學(xué)的煙葉圖像邊緣檢測[J];計(jì)算機(jī)工程;2007年21期

8 周云川;何永強(qiáng);李計(jì)添;;基于小波和灰度形態(tài)學(xué)的紅外圖像增強(qiáng)方法[J];激光與紅外;2011年06期

9 宋霞;張紅超;李琳;;基于灰度形態(tài)學(xué)開運(yùn)算的遙感圖像處理[J];中小企業(yè)管理與科技(下旬刊);2011年04期

10 楊歐;胡濤;郭軒;郭寶平;;灰度形態(tài)學(xué)在印刷品缺陷檢測中的應(yīng)用[J];微計(jì)算機(jī)信息;2008年07期

相關(guān)會(huì)議論文 前3條

1 韓建濤;王書宏;陳曾平;;基于灰度形態(tài)學(xué)的可見光弱小目標(biāo)檢測[A];第十二屆全國信號(hào)處理學(xué)術(shù)年會(huì)（CCSP-2005）論文集[C];2005年

2 魯昌華;程現(xiàn)彬;胡林和;;基于灰度形態(tài)學(xué)圖像邊緣檢測方法及其應(yīng)用研究[A];2010振動(dòng)與噪聲測試峰會(huì)論文集[C];2010年

3 董宇星;孫海江;劉偉寧;;基于背景抑制和灰度形態(tài)學(xué)的弱小目標(biāo)檢測[A];圖像圖形技術(shù)研究與應(yīng)用(2010)[C];2010年

相關(guān)碩士學(xué)位論文 前5條

1 鄭亞惠;基于超圖與數(shù)學(xué)形態(tài)學(xué)的灰度形態(tài)學(xué)新算子[D];西安電子科技大學(xué);2016年

2 王昔鵬;復(fù)雜場景下的交通標(biāo)志識(shí)別技術(shù)研究[D];合肥工業(yè)大學(xué);2017年

3 謝巍;格同態(tài)映射下的灰度形態(tài)學(xué)連通性理論研究[D];哈爾濱工程大學(xué);2011年

4 郭艷艷;灰度形態(tài)學(xué)算子[D];蘇州科技學(xué)院;2014年

5 秦學(xué)文;基于圖像處理的現(xiàn)場鋼管計(jì)數(shù)研究[D];華中科技大學(xué);2013年

，

本文編號(hào)：1424677