【摘要】：隨著電視技術(shù)的發(fā)展,3D視頻顯示技術(shù)漸漸走入人們的視野,人們可以在屏幕上觀看到立體的影像,并在軍事,醫(yī)療,教育等領(lǐng)域得到快速發(fā)展。一種獲得3D視頻的方法是通過2D轉(zhuǎn)3D視頻技術(shù)直接將2D視頻轉(zhuǎn)為3D視頻,這種方法制作成本低周期短,而且有豐富的2D視頻資源可供轉(zhuǎn)換,因此受到廣泛研究。在2D轉(zhuǎn)3D視頻系統(tǒng)中最為關(guān)鍵的是深度圖提取,本文主要研究基于運(yùn)動(dòng)檢測(cè)的深度圖提取的方法,這是一種將運(yùn)動(dòng)目標(biāo)當(dāng)作前景的深度賦值方式,這種假設(shè)的方式符合觀影的習(xí)慣特點(diǎn)且具有很高的效率,運(yùn)動(dòng)目標(biāo)檢測(cè)結(jié)果就成為這種方法的核心所在。然而大多數(shù)的運(yùn)動(dòng)檢測(cè)結(jié)果受環(huán)境的影響很大,如果場(chǎng)景中存在動(dòng)態(tài)背景就會(huì)產(chǎn)生大量的誤檢點(diǎn),運(yùn)動(dòng)物體運(yùn)動(dòng)速度過快就會(huì)產(chǎn)生鬼影,運(yùn)動(dòng)物體遮擋光線則會(huì)將陰影區(qū)域也檢測(cè)為運(yùn)動(dòng)目標(biāo),針對(duì)以上可能出現(xiàn)的問題,本文提出一種準(zhǔn)確有效的運(yùn)動(dòng)檢測(cè)算法。針對(duì)鬼影和場(chǎng)景中存在動(dòng)態(tài)背景的問題,提出一種基于時(shí)間和空間信息的背景模型,這種背景模型能夠有效去除大部分的誤檢點(diǎn);減少漏檢點(diǎn)的方法則是在前后景分割的過程中結(jié)合一種“或”類型的三幀差法,并將分割結(jié)果和顯著性檢測(cè)結(jié)果相與,可以進(jìn)一步去除誤檢點(diǎn);最后基于HSV顏色空間去除陰影區(qū)域。在Matlab和Opencv平臺(tái)對(duì)算法進(jìn)行軟件層驗(yàn)證,實(shí)驗(yàn)結(jié)果表明算法可以得到正確的運(yùn)動(dòng)檢測(cè)結(jié)果,量化指標(biāo)f-measure可以達(dá)到0.80以上。
[Abstract]:With the development of television technology, 3D video display technology has gradually come into people's view, people can watch stereoscopic images on the screen, and get rapid development in military, medical, education and other fields. One way to get 3D video is to convert 2D video to 3D video directly through 2D to 3D video technology. This method is widely studied because of its low cost, short period and abundant 2D video resources. In 2D to 3D video system, the key is depth map extraction. This paper mainly studies the method of depth map extraction based on motion detection, which is a kind of depth assignment method which regards moving target as foreground. This hypothetical method is consistent with the habit of viewing and has high efficiency. The result of moving target detection is the core of this method. However, most of the results of motion detection are greatly affected by the environment. If there is a dynamic background in the scene, there will be a large number of false detection points, and if the moving object is moving too fast, it will produce a ghost image. The shaded light of moving object will also detect the shadow area as moving target. In view of the above possible problems, this paper proposes an accurate and effective motion detection algorithm. A background model based on temporal and spatial information is proposed to solve the problem of dynamic background in ghosts and scenes. This kind of background model can effectively remove most of the false detection points. The method of reducing missed detection points is to combine a "or" type of three frame difference method in the process of scene segmentation, and to combine the segmentation result with the significant detection result, which can further remove the false detection points. Finally, shadow area is removed based on HSV color space. The software layer of the algorithm is verified on the platform of Matlab and Opencv. The experimental results show that the algorithm can get correct motion detection results, and the quantization index f-measure can reach more than 0.80.
【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)】：TN948.6;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 龐碩;張遠(yuǎn);曲熠;;3D電視系統(tǒng)的構(gòu)成及發(fā)展[J];電視技術(shù);2013年02期

2 馬建設(shè);夏飛鵬;蘇萍;潘龍法;;數(shù)字全息三維顯示關(guān)鍵技術(shù)與系統(tǒng)綜述[J];光學(xué)精密工程;2012年05期

3 洪艷;陳佩怡;;3D電影的現(xiàn)狀與問題研究[J];重慶郵電大學(xué)學(xué)報(bào)(社會(huì)科學(xué)版);2012年02期

4 郝毫剛;陳家琪;;基于五幀差分和背景差分的運(yùn)動(dòng)目標(biāo)檢測(cè)算法[J];計(jì)算機(jī)工程;2012年04期

5 王瓊?cè)A;王愛紅;梁棟;鄧歡;;裸視3D顯示技術(shù)概述[J];真空電子技術(shù);2011年05期

6 李樂;張茂軍;熊志輝;徐瑋;;基于內(nèi)容理解的單幅靜態(tài)街景圖像深度估計(jì)[J];機(jī)器人;2011年02期

7 Abbas KOOCHARI;Mohsen SORYANI;;Exemplar-based video inpainting with large patches[J];Journal of Zhejiang University-Science C(Computer & Electronics);2010年04期

8 張凱舟;劉鵬;姚慶棟;;基于自適應(yīng)搜索模板的快速運(yùn)動(dòng)估計(jì)算法[J];中國(guó)圖象圖形學(xué)報(bào);2009年11期

9 鞠芹;安平;張倩;張兆揚(yáng);;高質(zhì)量的虛擬視點(diǎn)圖像的繪制方法[J];電視技術(shù);2009年09期

10 楊鈾;郁梅;蔣剛毅;;交互式三維視頻系統(tǒng)研究進(jìn)展[J];計(jì)算機(jī)輔助設(shè)計(jì)與圖形學(xué)學(xué)報(bào);2009年05期

相關(guān)博士學(xué)位論文 前1條

1 李樂;面向3DTV應(yīng)用的視頻2D轉(zhuǎn)3D技術(shù)研究[D];國(guó)防科學(xué)技術(shù)大學(xué);2012年

相關(guān)碩士學(xué)位論文 前6條

1 趙興朋;視頻圖像2D轉(zhuǎn)3D算法研究及硬件實(shí)現(xiàn)[D];中國(guó)海洋大學(xué);2012年

2 關(guān)珊珊;基于FPGA的圖像顯示技術(shù)研究[D];南京航空航天大學(xué);2012年

3 徐萍;基于深度圖像繪制的二維轉(zhuǎn)三維視頻關(guān)鍵技術(shù)研究[D];南京郵電大學(xué);2011年

4 辛海濤;基于運(yùn)動(dòng)目標(biāo)檢測(cè)的行人計(jì)數(shù)方法[D];河北工業(yè)大學(xué);2011年

5 程鴻亮;基于FPGA的實(shí)時(shí)圖像邊緣檢測(cè)系統(tǒng)的研究[D];長(zhǎng)安大學(xué);2009年

6 杜晶晶;智能視頻監(jiān)控中運(yùn)動(dòng)目標(biāo)檢測(cè)與跟蹤算法研究[D];西南交通大學(xué);2009年

，

本文編號(hào)：2180425