發(fā)布時間：2018-07-21 20:02

【摘要】：隨著顯示技術(shù)的飛速發(fā)展,人們對高分辨率的圖像、視頻資源的需求也日益增長。然而由于圖像采集設(shè)備的硬件限制,高分辨率的資源比較稀缺,并且高質(zhì)量的圖像在存儲與傳輸上也有比較高的要求,而解決這種矛盾的一個非常好的方法就是圖像超分辨率。目前在圖像超分辨率領(lǐng)域,目前超分辨率重建效果較好的算法是基于學(xué)習(xí)的算法。這些算法都有著優(yōu)秀的超分辨率效果,然而這些算法大都將注意力集中于超分辨率的重建效果上,在算法的效率上則不盡如人意。最近由于深度學(xué)習(xí)熱潮的興起,卷積神經(jīng)網(wǎng)絡(luò)被應(yīng)用于圖像超分辨率領(lǐng)域,這種使用卷積神經(jīng)網(wǎng)絡(luò)進(jìn)行超分辨率的方法稱為超分辨率卷積神經(jīng)網(wǎng)絡(luò),也是一種基于學(xué)習(xí)的方法。超分辨率卷積神經(jīng)網(wǎng)絡(luò)由于其簡單的前饋網(wǎng)絡(luò)結(jié)構(gòu),算法無需求解復(fù)雜的優(yōu)化問題,因此算法在效率上相比其它算法了有很大的提升。雖然超分辨率卷積神經(jīng)網(wǎng)絡(luò)在效率上已經(jīng)超越了其它基于學(xué)習(xí)的算法,然而對于實(shí)時性要求較高的應(yīng)用來說,超分辨率卷積神經(jīng)網(wǎng)絡(luò)的時效性還是不足以滿足實(shí)時超分辨率的要求。針對超分辨率卷積神經(jīng)網(wǎng)絡(luò)的時效性問題,本文首先對小規(guī)模的超分辨率卷積神經(jīng)網(wǎng)絡(luò)進(jìn)行優(yōu)化,使得小規(guī)模的超分辨率卷積神經(jīng)網(wǎng)絡(luò)也能夠取得良好的超分辨率效果。其次借助CUDNN庫,將超分辨率卷積神經(jīng)網(wǎng)絡(luò)在GPU上實(shí)現(xiàn),用以提高卷積神經(jīng)網(wǎng)絡(luò)在PC上的計算效率。最后,本文將GPU上的卷積神經(jīng)網(wǎng)絡(luò)進(jìn)行封裝,并應(yīng)用在視頻壓縮仿真及增強(qiáng)處理系統(tǒng)中,使得系統(tǒng)能夠?qū)崿F(xiàn)實(shí)時的視頻超分辨率功能。
[Abstract]:With the rapid development of display technology, the demand for high resolution images and video resources is also increasing. However, due to the hardware limitation of image acquisition equipment, high resolution resources are scarce, and high quality images are also required in storage and transmission. A very good method to solve this contradiction is image super-resolution. At present, in the field of image super-resolution, the algorithm of super-resolution reconstruction is based on learning. These algorithms have excellent super-resolution effects, but most of them focus on the super-resolution reconstruction effect, but the efficiency of these algorithms is not satisfactory. Recently, due to the rise of deep learning craze, convolutional neural network is applied to image super-resolution field. This method using convolution neural network for super-resolution is called super-resolution convolution neural network, and it is also a learning-based method. Due to the simple feedforward network structure of super-resolution convolution neural network, the algorithm does not need to solve complex optimization problems, so the efficiency of the algorithm is greatly improved compared with other algorithms. Although super-resolution convolution neural network has outperformed other learning-based algorithms in efficiency, however, for applications with high real-time requirements, The timeliness of super-resolution convolution neural network is not enough to meet the requirement of real-time super-resolution. Aiming at the time-efficiency of super-resolution convolution neural network, this paper first optimizes the small-scale super-resolution convolution neural network, so that the small-scale super-resolution convolution neural network can also obtain good super-resolution effect. Secondly, the super-resolution convolution neural network is realized on GPU with the help of CUDNN library, so as to improve the computing efficiency of convolution neural network on PC. Finally, this paper encapsulates the convolutional neural network on GPU and applies it to video compression simulation and enhancement processing system, which enables the system to realize real-time video super-resolution function.
【學(xué)位授予單位】：北京郵電大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2016
【分類號】：TP391.41;TP183

【參考文獻(xiàn)】

相關(guān)期刊論文 前2條

1 浦劍;張軍平;黃華;;超分辨率算法研究綜述[J];山東大學(xué)學(xué)報(工學(xué)版);2009年01期

2 蘇秉華,金偉其,牛麗紅,劉廣榮;超分辨率圖像復(fù)原及其進(jìn)展[J];光學(xué)技術(shù);2001年01期

，

本文編號：2136704