本文選題：移動(dòng)增強(qiáng)現(xiàn)實(shí)　切入點(diǎn)：大范圍場(chǎng)景　出處：《華中科技大學(xué)》2013年博士論文　論文類型：學(xué)位論文

【摘要】：隨著智能手機(jī)的廣泛使用，移動(dòng)AR技術(shù)更加受到國內(nèi)外研究人員的關(guān)注。由于諸如智能手機(jī)之類的移動(dòng)終端設(shè)備相對(duì)于PC機(jī)具有資源受限的特點(diǎn)，比如，計(jì)算速度慢、內(nèi)存空間有限、手機(jī)功耗問題等，同時(shí)，智能手機(jī)輕便、體積小、可隨身攜帶等特點(diǎn)，又?jǐn)U大了使用者的活動(dòng)范圍，因此，需要在智能手機(jī)上提供能夠完成大范圍場(chǎng)景定位識(shí)別和三維注冊(cè)的移動(dòng)AR技術(shù)，但是，又不能簡(jiǎn)單的把應(yīng)用于PC機(jī)上的增強(qiáng)現(xiàn)實(shí)技術(shù)移植到智能手機(jī)上�；谝陨蟽�(nèi)容，本文提出了可以直接在移動(dòng)設(shè)備上實(shí)現(xiàn)大范圍場(chǎng)景的定位識(shí)別和三維注冊(cè)的系統(tǒng)構(gòu)架，主要研究工作如下： 第一，通過使用重力來增強(qiáng)局部向量聚集描述符VLAD的鑒別力，設(shè)計(jì)了GAVLAD圖像描述符，并設(shè)計(jì)了一個(gè)有效的向量量化策略，能將高維圖像描述符壓縮成幾個(gè)字節(jié)的壓縮編碼，將圖像描述符編碼成幾個(gè)字節(jié)，這樣可以存儲(chǔ)在移動(dòng)設(shè)備中，有助于完成高效搜索，并以此設(shè)計(jì)了一個(gè)適合移動(dòng)設(shè)備RAM的圖像搜索引擎，使其能夠高效完成移動(dòng)設(shè)備上的定位識(shí)別。本文還建構(gòu)了一個(gè)基于圖像和傳感器的相結(jié)合的壓縮的索引結(jié)構(gòu)，能在移動(dòng)設(shè)備上直接處理大范圍圖像數(shù)據(jù)。 第二，設(shè)計(jì)了一個(gè)簡(jiǎn)單有效的向量二值化方法以減少多特征融合內(nèi)存占用量，并提出了一個(gè)位置敏感的融合算法將多特征融合起來。該算法可以將多個(gè)圖像特征壓縮成一個(gè)占用空間小的、高區(qū)分度的圖像描述符，可以直接在移動(dòng)設(shè)備上高效的進(jìn)行存儲(chǔ)和搜索。并提出將特征融合與索引結(jié)構(gòu)聯(lián)合優(yōu)化，以提高定位識(shí)別的準(zhǔn)確性，同時(shí)減少內(nèi)存占用。 第三，設(shè)計(jì)了一個(gè)靈活的攝像機(jī)初始化和追蹤方法，可以以高達(dá)10Hz每幀的幀率在現(xiàn)階段主流配置的手機(jī)上追蹤非平面場(chǎng)景，一定程度上解決了大范圍場(chǎng)景移動(dòng)增強(qiáng)現(xiàn)實(shí)應(yīng)用中的虛實(shí)注冊(cè)問題。 第四，發(fā)布了一套新的數(shù)據(jù)庫，包含1,295,000個(gè)地理標(biāo)記街景圖像以及849個(gè)測(cè)試查詢圖像，這些資源可以被用作新的參照基準(zhǔn)，可以在今后的相關(guān)研究中作為參照基準(zhǔn)供其他研究人員繼續(xù)使用。 本文通過多組實(shí)驗(yàn)證明，，本研究提出的基于移動(dòng)設(shè)備的大范圍場(chǎng)景定位識(shí)別和三維注冊(cè)移動(dòng)AR系統(tǒng)提高了定位識(shí)別的精確性，并在節(jié)省內(nèi)存、提高速度等方面取得了滿意的效果，為提高移動(dòng)增強(qiáng)現(xiàn)實(shí)系統(tǒng)的真實(shí)感和促進(jìn)其走出實(shí)驗(yàn)室、面向廣泛應(yīng)用提供必要的技術(shù)支撐。
[Abstract]:With the wide use of smart phones, mobile AR technology has attracted more attention from researchers at home and abroad. Because mobile terminal devices such as smart phones have the characteristics of limited resources compared with PCs, for example, the computing speed is slow. Limited memory space, mobile phone power problems, and so on, at the same time, smart phones are light, small, portable and other characteristics, but also expand the range of activities of users, so, We need to provide mobile AR technology on the smartphone that can complete the large-scale scene location recognition and 3D registration, but we can't simply transplant the augmented reality technology applied to the PC to the smart phone. This paper presents a system framework that can directly realize the location recognition and 3D registration of large-scale scene on mobile devices. The main research work is as follows:. First, by using gravity to enhance the discriminant ability of the local vector aggregation descriptor (VLAD), the GAVLAD image descriptor is designed, and an effective vector quantization strategy is designed, which can compress the high-dimensional image descriptor into several bytes of compression coding. The image descriptor is encoded into several bytes, which can be stored on a mobile device, which is helpful for efficient search, and an image search engine suitable for the mobile device RAM is designed. This paper also constructs a compressed index structure based on image and sensor, which can directly process large range image data on mobile devices. Secondly, a simple and effective vector binarization method is designed to reduce the memory footprint of multi-feature fusion. A position sensitive fusion algorithm is proposed, which can compress multiple image features into a small space and high partition image descriptor. It can be stored and searched directly on mobile devices, and it is proposed to optimize the feature fusion and index structure to improve the accuracy of location identification and reduce the memory footprint. Thirdly, a flexible camera initialization and tracking method is designed, which can track non-planar scenes at a frame rate of up to 10 Hz per frame on the current mainstream mobile phone. To some extent, the problem of virtual reality registration in large scale mobile augmented reality applications is solved. In 4th, a new database containing 1, 295,000 geo-marked streetscape images and 849 test query images was released, which can be used as a new reference frame. It can be used as a reference for other researchers in future studies. In this paper, it is proved by many experiments that the large scale scene location recognition based on mobile device and 3D registered mobile AR system can improve the accuracy of location recognition and save memory. In order to improve the reality of mobile augmented reality system and promote it out of the laboratory, it provides the necessary technical support for the wide application of mobile augmented reality system.
【學(xué)位授予單位】：華中科技大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2013
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前6條

1 林福華;軟件無線電技術(shù)[J];電子工程師;1999年02期

2 陳靖;王涌天;林亻京;;增強(qiáng)現(xiàn)實(shí)技術(shù)在PDA上的應(yīng)用[J];光學(xué)技術(shù);2007年01期

3 管濤;李利軍;王乘;;增強(qiáng)現(xiàn)實(shí)開發(fā)工具ARDK的研究與應(yīng)用[J];計(jì)算機(jī)工程與應(yīng)用;2006年19期

4 李玉;王涌天;劉越;;基于彩色標(biāo)志點(diǎn)的增強(qiáng)現(xiàn)實(shí)注冊(cè)算法研究[J];系統(tǒng)仿真學(xué)報(bào);2008年03期

5 朱淼良,姚遠(yuǎn),蔣云良;增強(qiáng)現(xiàn)實(shí)綜述[J];中國圖象圖形學(xué)報(bào);2004年07期

6 林P;楊珂;王涌天;劉越;;移動(dòng)增強(qiáng)現(xiàn)實(shí)系統(tǒng)的關(guān)鍵技術(shù)研究[J];中國圖象圖形學(xué)報(bào);2009年03期

本文編號(hào)：1587591