【摘要】：隨著無(wú)線(xiàn)網(wǎng)絡(luò)技術(shù)的發(fā)展,監(jiān)控視頻出現(xiàn)在了越來(lái)越多的行業(yè)領(lǐng)域,傳統(tǒng)的信號(hào)處理中,信號(hào)采樣要求滿(mǎn)足大于信號(hào)最高頻率的兩倍,這樣才能夠精準(zhǔn)地重構(gòu)原始信號(hào),這直接導(dǎo)致了數(shù)據(jù)存儲(chǔ)量大,傳輸信號(hào)慢等問(wèn)題。而壓縮感知理論的提出給視頻處理技術(shù)帶來(lái)了新的進(jìn)展,基于壓縮感知方法的視頻處理技術(shù),逐步成為了海內(nèi)外的研究熱門(mén)。本文以洗車(chē)行監(jiān)控視頻作為研究背景和樣本,首先通過(guò)圖像處理基本手段將監(jiān)控視頻內(nèi)容進(jìn)行了有效篩選,將有車(chē)圖像保存,對(duì)保存圖像采用壓縮感知的方法處理。字典構(gòu)造方法是壓縮感知十分重要的技術(shù)手段之一,對(duì)重構(gòu)信號(hào)的質(zhì)量有著重要的影響。本文一開(kāi)始先介紹了壓縮感知基本理論的框架,對(duì)重建算法予以重點(diǎn)介紹,總結(jié)各種重建算法的優(yōu)缺點(diǎn)。對(duì)KSVD字典訓(xùn)練算法進(jìn)行深入分析,并給出了一種結(jié)合KSVD初始字典訓(xùn)練法和OMP算法的壓縮感知視頻處理方法,該方法與能夠讓原子不斷迭代,不斷更新字典,達(dá)到減小誤差,獲得更好的重建質(zhì)量;考慮到視頻前后幀間關(guān)聯(lián)性,接下來(lái)給出一種基于幀差法的KSVD字典訓(xùn)練構(gòu)造方法,并利用設(shè)置幀組,不斷調(diào)整關(guān)鍵幀以及非關(guān)鍵幀的采樣率,不僅利用了幀內(nèi)信息,還高效的利用到幀間信息,大大減小了存儲(chǔ)空間,并獲得了更為顯著的主觀(guān)視覺(jué)重建效果和客觀(guān)數(shù)值對(duì)比的重建效果。實(shí)驗(yàn)結(jié)果表明,采用壓縮感知方法處理洗車(chē)行監(jiān)控視頻圖像能夠使得存儲(chǔ)空間大大減小。并且與未利用幀差法的KSVD字典法相比,在關(guān)鍵幀采樣率為0.9時(shí),非關(guān)鍵幀幀差采樣率為0.1時(shí),基于幀差法的KSVD字典構(gòu)造方法使得視頻單幀圖像的平均PSNR (峰值信噪比)提高了 1.86～3.95dB,提高了重建圖像的主觀(guān)和客觀(guān)質(zhì)量。
[Abstract]:With the development of wireless network technology, surveillance video has appeared in more and more industries. In traditional signal processing, the requirement of signal sampling is twice as high as the highest frequency of the signal, so that the original signal can be reconstructed accurately. This directly leads to the problems of large data storage and slow transmission signal. The video processing technology based on compressed sensing has gradually become a hot research topic at home and abroad. This paper takes the monitoring video of the car washer as the research background and sample. Firstly, the content of the monitoring video is effectively screened by the basic means of image processing, and the vehicle image is saved. Preserved images are processed by compressive sensing. Dictionary construction is one of the most important technical means of compressive sensing, which has an important impact on the quality of reconstructed signals. Dictionary training algorithm is analyzed in depth, and a compression sensing video processing method combining KSVD initial dictionary training method and OMP algorithm is proposed. This method can make the atoms iterate and update the dictionary continuously, so as to reduce the error and obtain better reconstruction quality. The KSVD dictionary is trained and constructed by frame difference method, and the sampling rate of key frame and non-key frame is adjusted continuously by setting frame groups. Not only the intra-frame information is utilized, but also the inter-frame information is used efficiently, which greatly reduces the memory space and obtains more significant subjective visual reconstruction effect and the reconstruction effect of objective numerical comparison. The experimental results show that the compression sensing method can greatly reduce the storage space of the video image of the car wash line. Compared with the KSVD dictionary method without frame difference method, when the key frame sampling rate is 0.9 and the non-key frame difference sampling rate is 0.1, the KSVD dictionary construction method based on frame difference method can make the video single frame image level. Average PSNR (peak signal-to-noise ratio) increased by 1.86 to 3.95dB, which improved subjective and objective quality of reconstructed images.
【學(xué)位授予單位】：哈爾濱工程大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類(lèi)號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前6條

1 蔣業(yè)文;于昕梅;;壓縮感知的自適應(yīng)冗余字典及其圖像恢復(fù)方法研究[J];中山大學(xué)學(xué)報(bào)(自然科學(xué)版);2012年06期

2 戴瓊海;付長(zhǎng)軍;季向陽(yáng);;壓縮感知研究[J];計(jì)算機(jī)學(xué)報(bào);2011年03期

3 王艷;練秋生;李凱;;基于聯(lián)合正則化及壓縮傳感的MRI圖像重構(gòu)[J];光學(xué)技術(shù);2010年03期

4 余慧敏;方廣有;;壓縮感知理論在探地雷達(dá)三維成像中的應(yīng)用[J];電子與信息學(xué)報(bào);2010年01期

5 石光明;劉丹華;高大化;劉哲;林杰;王良君;;壓縮感知理論及其研究進(jìn)展[J];電子學(xué)報(bào);2009年05期

6 鄒福輝;李忠科;;圖像邊緣檢測(cè)算法的對(duì)比分析[J];計(jì)算機(jī)應(yīng)用;2008年S1期

相關(guān)博士學(xué)位論文 前2條

1 孫玉寶;圖像稀疏表示模型及其在圖像處理反問(wèn)題中的應(yīng)用[D];南京理工大學(xué);2010年

2 鄧承志;圖像稀疏表示理論及其應(yīng)用研究[D];華中科技大學(xué);2008年

相關(guān)碩士學(xué)位論文 前4條

1 姜平;基于壓縮視頻感知字典構(gòu)造方法研究[D];西安電子科技大學(xué);2013年

2 黨銀強(qiáng);復(fù)雜場(chǎng)景下的車(chē)輛識(shí)別研究[D];哈爾濱工程大學(xué);2013年

3 見(jiàn)春雨;壓縮感知算法及其在超寬帶信道估計(jì)中的應(yīng)用研究[D];南京郵電大學(xué);2012年

4 劉智威;基于壓縮感知的重構(gòu)算法與語(yǔ)音壓縮研究[D];南京郵電大學(xué);2013年

，

本文編號(hào)：2228250