本文關(guān)鍵詞： 彩色交通柵格地圖 數(shù)字地圖 道路自動(dòng)獲取 顏色自動(dòng)獲取 顏色聚類 噪聲消除 特征匹配　出處：《中國(guó)科學(xué)技術(shù)大學(xué)》2013年博士論文　論文類型：學(xué)位論文

【摘要】：隨著交通地理信息系統(tǒng)的發(fā)展,快速建立交通數(shù)字地圖日趨重要。道路矢量數(shù)據(jù)是交通矢量地圖的基礎(chǔ)數(shù)據(jù),彩色交通柵格地圖是道路矢量數(shù)據(jù)的一個(gè)重要信息源。從彩色柵格地圖中自動(dòng)獲取道路是快速、高效、低成本地自動(dòng)生成道路矢量數(shù)據(jù)的重要途徑。人工識(shí)別彩色交通柵格地圖中道路較容易,利用計(jì)算機(jī)自動(dòng)獲取道路則是一個(gè)挑戰(zhàn)性的課題。 本論文以彩色城市交通柵格地圖和彩色公路交通柵格地圖為研究對(duì)象,綜合利用兩類彩色交通柵格地圖的特征,重點(diǎn)對(duì)地圖要素的顏色自動(dòng)獲取、噪聲消除方法、點(diǎn)狀符號(hào)自動(dòng)獲取幾個(gè)方面進(jìn)行研究。利用本論文提出的方法,實(shí)現(xiàn)了一個(gè)彩色交通柵格地圖道路自動(dòng)獲取系統(tǒng)。 本論文的主要研究成果與創(chuàng)新點(diǎn)： (1)綜合利用彩色交通柵格地圖中背景、道路與噪聲的特征,提出背景顏色自動(dòng)獲取的同色塊檢測(cè)法、城市道路顏色自動(dòng)獲取的游程長(zhǎng)度分析法、公路顏色自動(dòng)獲取的噪聲消除法和公路干道顏色自動(dòng)獲取的鄰域法,應(yīng)用這些方法準(zhǔn)確地獲取了彩色交通柵格地圖中背景與道路的顏色,解決背景與道路的顏色獲取需人工干預(yù)的問題。 (2)提出并綜合線狀噪聲、塊狀噪聲、梯度特征法等多種噪聲消除方法,解決彩色柵格交通地圖中道路顏色已知和未知兩種情況下的噪聲消除問題,獲得了比現(xiàn)有噪聲消除方法更好的噪聲消除效果,克服了現(xiàn)有的噪聲消除方法在背景與道路的顏色聚類中消除大量噪聲的不足。 (3)利用彩色公路交通柵格地圖中縣城符號(hào)的形狀和顏色分布特征,提出與實(shí)現(xiàn)一種縣城符號(hào)自動(dòng)獲取的特征匹配法,應(yīng)用該方法從不同顏色的彩色公路交通柵格地圖中準(zhǔn)確地提取出縣城符號(hào),克服模板匹配法對(duì)彩色公路柵格地圖的顏色變化敏感、閾值難以選取和計(jì)算量大的不足,為實(shí)現(xiàn)公路干道顏色自動(dòng)獲取的鄰域法奠定基礎(chǔ)。本論文先結(jié)合縣城符號(hào)的圖例及其Laplace邊緣圖像選取兩組特征點(diǎn),再依據(jù)兩組特征點(diǎn)的統(tǒng)計(jì)特征識(shí)別縣城符號(hào),最后通過實(shí)驗(yàn)驗(yàn)證特征匹配法的有效性和優(yōu)越性。 (4)綜合上述方法,實(shí)現(xiàn)彩色交通柵格地圖中城市道路與公路的自動(dòng)獲取,設(shè)計(jì)與實(shí)現(xiàn)彩色交通柵格地圖城市道路與公路自動(dòng)獲取系統(tǒng)。先實(shí)現(xiàn)數(shù)字圖像處理系統(tǒng)的基本功能,再實(shí)現(xiàn)彩色交通柵格地圖中城市道路與公路的自動(dòng)獲取,最后通過實(shí)驗(yàn)驗(yàn)證城市道路與公路自動(dòng)獲取方法的有效性與優(yōu)越性。
[Abstract]:With the development of traffic geographic information system, it is more and more important to set up traffic digital map quickly. Road vector data is the basic data of traffic vector map. Color traffic grid map is an important information source of road vector data. It is fast and efficient to automatically obtain the road from color grid map. It is an important way to generate road vector data automatically at low cost. It is easy to manually identify the road in the color traffic grid map, and it is a challenging task to obtain the road automatically by computer. This paper takes the color urban traffic grid map and the color highway traffic grid map as the research object, synthetically uses the two kinds of color traffic grid map's characteristic, emphatically obtains the map essential factor color automatically. In this paper, a color traffic grid map road automatic acquisition system is implemented by using the method proposed in this paper. The main research results and innovations of this thesis are as follows: 1) based on the features of background, road and noise in color traffic grid map, this paper puts forward a method of automatic background color acquisition by the same color block detection method, and a run length analysis method of city road color automatic acquisition method. The noise elimination method of automatic acquisition of road color and the neighborhood method of automatic acquisition of road color are used to accurately obtain the background and the color of the road in the color traffic grid map. To solve the background and road color acquisition needs manual intervention. In order to solve the problem of road noise elimination in color grid traffic map, several noise elimination methods, such as linear noise, block noise and gradient feature method, are proposed and synthesized. A better noise elimination effect is obtained than the existing noise elimination methods, and the shortcomings of the existing noise elimination methods in background and road color clustering are overcome. Based on the shape and color distribution features of county town symbols in the color highway traffic grid map, a feature matching method for automatic acquisition of county town symbols is proposed and implemented. The method is used to extract the county town symbols accurately from the color road traffic grid map of different colors, and to overcome the sensitivity of the template matching method to the color change of the color highway grid map. It is difficult to select the threshold value and the shortage of large amount of calculation. In order to achieve the road color automatic acquisition of the neighborhood method to lay the foundation. Firstly, this paper combines the legend of county town symbol and Laplace edge image to select two groups of feature points. Based on the statistical features of the two groups of feature points, the county seat symbols are identified. Finally, the effectiveness and superiority of the feature matching method are verified by experiments. The above method is integrated to realize the automatic acquisition of urban roads and highways in the color traffic grid map. Design and implementation of color traffic grid map urban road and highway automatic acquisition system. First, realize the basic function of digital image processing system, and then realize the automatic acquisition of urban road and highway in color traffic grid map. Finally, the effectiveness and superiority of the automatic acquisition method of urban roads and highways are verified by experiments.
【學(xué)位授予單位】：中國(guó)科學(xué)技術(shù)大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2013
【分類號(hào)】：U495;P208

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 何孝瑩;宋偉東;韓顏順;;點(diǎn)狀地圖符號(hào)的神經(jīng)網(wǎng)絡(luò)識(shí)別[J];測(cè)繪科學(xué);2006年01期

2 楊云;朱長(zhǎng)青;孫群;;掃描地形圖中居民地街區(qū)提取和矢量化方法[J];測(cè)繪科學(xué);2007年05期

3 李巖影,過靜s，

本文編號(hào)：1456336