本文選題：實(shí)時(shí) + 增強(qiáng)現(xiàn)實(shí)��； 參考：《浙江大學(xué)》2010年博士論文

【摘要】：隨著計(jì)算機(jī)運(yùn)算能力的不斷增強(qiáng),計(jì)算機(jī)視覺(jué)研究得到了持續(xù)的發(fā)展,在監(jiān)控、檢索、識(shí)別、導(dǎo)航、醫(yī)療、教育等領(lǐng)域的應(yīng)用為人的視覺(jué)提供有效的補(bǔ)充,甚至在某些方面很好地替代了人的視覺(jué)。虛實(shí)混合作為計(jì)算機(jī)視覺(jué)的重要應(yīng)用之一,是通過(guò)特殊的設(shè)備,將計(jì)算機(jī)產(chǎn)生的虛擬信息與現(xiàn)實(shí)環(huán)境無(wú)縫融合,給人們提供額外的信息,如說(shuō)明文字、視頻教程、三維動(dòng)畫等。 本文涉及的增強(qiáng)現(xiàn)實(shí)是虛實(shí)混合技術(shù)的一種,利用相關(guān)計(jì)算機(jī)視覺(jué)技術(shù)分析現(xiàn)實(shí)場(chǎng)景中的物體和環(huán)境特征,并在指定的位置繪制計(jì)算機(jī)生成的附屬信息,幫助人們更好地理解場(chǎng)景。一般的增強(qiáng)現(xiàn)實(shí)系統(tǒng),包括視頻輸入、特征分析、攝像機(jī)定位、虛實(shí)融合等模塊,其中特征分析和攝像機(jī)定位是最核心的模塊。離線增強(qiáng)現(xiàn)實(shí)已經(jīng)在電影工業(yè),視頻廣告中得到廣泛應(yīng)用,然而實(shí)時(shí)增強(qiáng)現(xiàn)實(shí)更多地處在實(shí)驗(yàn)階段。本文主要研究實(shí)時(shí)增強(qiáng)現(xiàn)實(shí)的三維跟蹤技術(shù),即實(shí)時(shí)地恢復(fù)攝像機(jī)與場(chǎng)景之間的相對(duì)空間方位,內(nèi)容包括多線程技術(shù)框架設(shè)計(jì)、圖像特征分析、大規(guī)模場(chǎng)景的關(guān)鍵幀表達(dá)、和純旋轉(zhuǎn)相機(jī)下的雙層分割方法�？傮w來(lái)說(shuō),本文希望能促進(jìn)實(shí)時(shí)三維跟蹤技術(shù)在增強(qiáng)現(xiàn)實(shí)中的應(yīng)用,主要貢獻(xiàn)在以下幾個(gè)方面。 ·提出統(tǒng)一的實(shí)時(shí)增強(qiáng)現(xiàn)實(shí)系統(tǒng)框架。在關(guān)鍵技術(shù)充分模塊化,模塊接口標(biāo)準(zhǔn)化的基礎(chǔ)上,將各種現(xiàn)實(shí)環(huán)境下的增強(qiáng)現(xiàn)實(shí)統(tǒng)一在一個(gè)多線程并行框架里,用戶可以便捷地在此基礎(chǔ)上開發(fā)新的增強(qiáng)現(xiàn)實(shí)應(yīng)用,而且這個(gè)框架充分利用了多核機(jī)器的計(jì)算能力,使系統(tǒng)在適應(yīng)各種復(fù)雜環(huán)境的情況下保證高效可靠的性能。 ·提出改進(jìn)的基準(zhǔn)標(biāo)志系統(tǒng)。在一些桌面增強(qiáng)現(xiàn)實(shí)應(yīng)用中,系統(tǒng)不能從自然場(chǎng)景中提取足夠的特征定位攝像機(jī),必須輔以基準(zhǔn)標(biāo)志。本文提出的基準(zhǔn)標(biāo)志是包圍在黑色方框中的漢字圖像。為了在復(fù)雜的光影下也能穩(wěn)定地檢測(cè)出標(biāo)志,系統(tǒng)利用邊緣信息檢測(cè)標(biāo)志的包圍框。同時(shí),本文將漢字的結(jié)構(gòu)表達(dá)為漢字輪廓到邊框的距離場(chǎng),增加了漢字標(biāo)志的可識(shí)別度。另一方面,傳統(tǒng)的基準(zhǔn)標(biāo)志一般是黑白圖案,從視覺(jué)上看很不美觀,本文于是利用自然圖像作為基準(zhǔn)標(biāo)志的補(bǔ)充。 提出基于關(guān)鍵幀的場(chǎng)景表達(dá)和快速選擇候選關(guān)鍵幀方法。在大規(guī)模自然場(chǎng)景中,系統(tǒng)利用Structure-from-Motion技術(shù)從預(yù)處理視頻序列中恢復(fù)場(chǎng)景的稀疏三維點(diǎn)云。由于大規(guī)模場(chǎng)景的特征過(guò)于豐富,特征匹配在時(shí)間和數(shù)量上的性能都會(huì)明顯下降。本文通過(guò)貪婪優(yōu)化方法,從輸入預(yù)處理視頻序列中自動(dòng)選擇一些關(guān)鍵幀,這些關(guān)鍵幀將包含比較穩(wěn)定的,特征明顯的三維特征點(diǎn)。三維跟蹤通過(guò)圖像識(shí)別算法,為輸入圖像選擇相似的候選關(guān)鍵幀,然后只跟候選關(guān)鍵幀進(jìn)行特征匹配。為了獲得更穩(wěn)定的跟蹤結(jié)果,本文還利用極線約束,連續(xù)幀跟蹤等方法匹配更多特征點(diǎn)。 提出攝像機(jī)純旋轉(zhuǎn)運(yùn)動(dòng)下,快速穩(wěn)定地分離前景背景物體的方法。由于場(chǎng)景和攝像機(jī)運(yùn)動(dòng)的雙重復(fù)雜性,場(chǎng)景層次分割是處理增強(qiáng)現(xiàn)實(shí)中的虛實(shí)遮擋的重要方法,同時(shí)也是非常難解決的問(wèn)題。本文嘗試解決在攝像機(jī)只有旋轉(zhuǎn)運(yùn)動(dòng)情況下前背景之間的遮擋,這事實(shí)上是一個(gè)前背景分割問(wèn)題。系統(tǒng)首先建立背景的全景圖,然后將實(shí)時(shí)輸入圖像與背景全景圖配準(zhǔn),估計(jì)背景信息,并利用圖割算法進(jìn)行分割。針對(duì)復(fù)雜背景和背景配準(zhǔn)誤差,本文結(jié)合過(guò)分割方法對(duì)背景全景圖建立局部顏色模型,同時(shí)壓制背景的顏色反差信息。系統(tǒng)得到精確的分割結(jié)果,并實(shí)現(xiàn)了一系列特殊的增強(qiáng)現(xiàn)實(shí)效果。
[Abstract]:With the continuous enhancement of computer computing power, computer vision research has been developed continuously. Applications in monitoring, retrieval, identification, navigation, medical, education and other fields provide an effective complement to human vision, and even in some ways, it is a good substitute for human vision. The mixture of virtual and real is one of the important applications of computer vision. Through the special equipment, the virtual information produced by the computer is fused seamlessly with the real environment to provide people with additional information, such as the description of the text, the video course, the 3D animation, etc.
The augmented reality in this paper is a kind of virtual and real mixing technology, using the related computer vision technology to analyze the object and environment features in the real scene, and draw computer generated auxiliary information in the specified position to help people to better understand the scene. General enhancement of the real system, including video input, feature analysis, camera Location, virtual fusion and other modules, feature analysis and camera positioning are the core modules. Off-line augmented reality has been widely used in film industry and video advertising. However, real time augmented reality is more in the experimental stage. This paper mainly studies real-time enhancement of real 3D tracking technology, that is, real-time recovery of cameras. The relative spatial orientation between the scene and the scene includes the multi thread technology framework design, the image feature analysis, the key frame expression of the large-scale scene, and the double decker segmentation method under the pure rotation camera. In general, this paper hopes to promote the real-time 3D tracking technology to enhance the application in the present. The main contributions are in the following aspects.
The framework of a unified real time augmented reality system is proposed. On the basis of full modularization of key technologies and standardization of module interfaces, the augmented reality under various realistic environments is unified in a multi thread parallel framework, and users can easily develop new enhanced applications on this basis, and this framework makes full use of multi-core frameworks. The computing power of the machine enables the system to ensure efficient and reliable performance in a variety of complex environments.
In some desktop augmented reality applications, the system can not extract sufficient feature location cameras from natural scenes and must be supplemented with reference marks. The reference mark presented in this paper is a Chinese character image enclosed in a black box. In order to detect the signs steadily in a complex light and shadow, the system can also be detected. At the same time, the structure of the Chinese character is expressed as the distance field of the Chinese character outline to the border, and the recognition of the Chinese character marks is increased. On the other hand, the traditional benchmark is generally black and white, and it is not beautiful from the vision. So the natural image is used as the supplement of the reference mark.
The method of scene expression based on key frame and fast selection of candidate key frame is proposed. In large-scale natural scene, the system uses Structure-from-Motion technology to recover the sparse 3D point cloud from the preprocessed video sequence. Because the feature of large-scale scene is too rich, the performance of feature matching in time and quantity will be obvious. In this paper, through greedy optimization, some key frames are automatically selected from the input preprocessed video sequence. These key frames will contain more stable and characteristic 3D feature points. Three dimensional tracking is used to select similar candidate key frames for the input image by image recognition algorithm, and then only match the feature of candidate key frames. In order to get more stable tracking results, we also use polar line constraint and continuous frame tracking to match more feature points.
The method of fast and stable separation of foreground objects is proposed under the pure rotation of the camera. Because of the dual complexity of the scene and camera motion, the scene hierarchy segmentation is an important method to deal with the virtual reality in the augmented reality. It is also a very difficult problem to solve. This paper tries to solve the problem that the camera has only rotation motion. In fact, the occlusion between the front background is a front background segmentation problem. The system first sets up the panorama of the background, then registers the real time input image with the background panorama, estimates the background information, and uses the graph cutting algorithm to divide it. The paper combines the error of the complex background and background registration. This paper combines the over segmentation method to build the background panorama. A local color model is established to suppress background color contrast information. The system achieves accurate segmentation results and achieves a series of special augmented reality effects.
【學(xué)位授予單位】：浙江大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2010
【分類號(hào)】：TP391.41

【引證文獻(xiàn)】

相關(guān)碩士學(xué)位論文 前1條

1 陳爍;增強(qiáng)現(xiàn)實(shí)中實(shí)時(shí)跟蹤技術(shù)的研究[D];沈陽(yáng)工業(yè)大學(xué);2014年

，

本文編號(hào)：2084215