本文關(guān)鍵詞：細(xì)微運(yùn)動(dòng)的視覺增強(qiáng)及硬件加速技術(shù)研究　出處：《中國科學(xué)技術(shù)大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 細(xì)微運(yùn)動(dòng) 視覺增強(qiáng) 硬件加速 視頻監(jiān)控

【摘要】：智能化的視頻監(jiān)控作為計(jì)算機(jī)視覺研究的一個(gè)重要方向,它主要是利用計(jì)算機(jī)技術(shù),對(duì)監(jiān)控視野內(nèi)的目標(biāo)進(jìn)行識(shí)別、追蹤、行為描述等處理,其關(guān)注的目標(biāo)通常是我們裸眼所能分辨的物體或者運(yùn)動(dòng);然而我們的眼睛在觀察目標(biāo)時(shí),對(duì)物體的空間尺度大小、運(yùn)動(dòng)幅度和頻率都有一定的要求;所以在監(jiān)控視頻中還存在著一些我們裸眼難以分辨的細(xì)微運(yùn)動(dòng),比如臉部顏色隨血液的流動(dòng)會(huì)發(fā)生微弱變化,腹部在呼吸時(shí)會(huì)有微小起伏。在醫(yī)療看護(hù)中,上述兩種細(xì)微運(yùn)動(dòng)可以輔助護(hù)理人員檢測病人的身體狀況及其睡眠質(zhì)量。因此我們需要對(duì)視頻監(jiān)控中的細(xì)微運(yùn)動(dòng)進(jìn)行增強(qiáng),使其可視化。在增強(qiáng)視頻監(jiān)控中細(xì)微運(yùn)動(dòng)時(shí),我們首先需要對(duì)目標(biāo)進(jìn)行識(shí)別,然后提取目標(biāo)所在區(qū)域,對(duì)提取區(qū)域中的細(xì)微運(yùn)動(dòng)進(jìn)行放大,最后重新渲染視頻。由于目標(biāo)識(shí)別和區(qū)域提取已經(jīng)是視頻監(jiān)控中非常成熟的算法,所以本文結(jié)合視頻監(jiān)控在醫(yī)療看護(hù)中的應(yīng)用,重點(diǎn)研究了細(xì)微運(yùn)動(dòng)增強(qiáng)算法。首先,本文闡述了細(xì)微運(yùn)動(dòng)增強(qiáng)算法的相關(guān)原理。隨后,本文結(jié)合視頻監(jiān)控的特點(diǎn),對(duì)細(xì)微運(yùn)動(dòng)增強(qiáng)算法進(jìn)行了優(yōu)化,獲得了良好的可視化效果。最后,本文實(shí)現(xiàn)了細(xì)微運(yùn)動(dòng)的實(shí)時(shí)增強(qiáng)。本文的具體工作如下。(1)線性歐拉運(yùn)動(dòng)放大算法雖然能同時(shí)放大目標(biāo)的顏色和運(yùn)動(dòng)變化,但是輸出視頻中會(huì)存在著嚴(yán)重的噪聲污染和偽影。相位歐拉運(yùn)動(dòng)放大算法雖然能解決噪聲和偽影問題,但是計(jì)算復(fù)雜度高并且會(huì)產(chǎn)生大量的中間數(shù)據(jù)。為了解決計(jì)算量、噪聲和偽影難題,本文首先將輸入的視頻序列進(jìn)行完全金字塔分解;然后根據(jù)不同的運(yùn)動(dòng)類型,選取不同的帶通濾波器來提取我們感興趣的細(xì)微運(yùn)動(dòng)。由于提取后的圖像中會(huì)摻雜相同頻率的噪聲,因此本文對(duì)圖像進(jìn)行一次平滑去噪。最后本文將去噪后的圖像進(jìn)行放大并重新渲染視頻。(2)由于上述算法屬于計(jì)算密集型運(yùn)算,同時(shí)還要滿足視頻監(jiān)控中實(shí)時(shí)性的要求。所以本文提出了一種基于FPGA的硬件加速方案。在硬件實(shí)現(xiàn)過程中,本文首先對(duì)細(xì)微運(yùn)動(dòng)增強(qiáng)算法中的色彩空間轉(zhuǎn)換模塊、金字塔分解模塊、去噪模塊和濾波模塊進(jìn)行了硬件設(shè)計(jì)。然后根據(jù)各個(gè)模塊的處理流程,設(shè)計(jì)了流水線架構(gòu)。為了實(shí)現(xiàn)FPGA對(duì)DDR的連續(xù)快速訪問,本文在DDR和FPGA間設(shè)計(jì)了ping-pong數(shù)據(jù)緩沖結(jié)構(gòu)。(3)本文首先在CPU上對(duì)細(xì)微運(yùn)動(dòng)增強(qiáng)算法進(jìn)行了驗(yàn)證,然后結(jié)合Xilinx KC705板卡實(shí)現(xiàn)了視頻監(jiān)控中細(xì)微運(yùn)動(dòng)的可視化。我們對(duì)輸出視頻的時(shí)間切片、亮度變化、PSNR等參數(shù)進(jìn)行了分析,本文算法在具有良好可視化效果的同時(shí),對(duì)噪聲具有良好的抑制能力。最后我們設(shè)計(jì)了細(xì)微運(yùn)動(dòng)的監(jiān)控系統(tǒng),并且完成了細(xì)微運(yùn)動(dòng)的實(shí)時(shí)監(jiān)控。
[Abstract]:As an important direction of computer vision research, intelligent video surveillance mainly uses computer technology to identify, track and describe the target in the field of surveillance. The object of attention is usually the object or motion that we can distinguish with the naked eye. However, when our eyes observe the target, there are certain requirements for the spatial scale, motion amplitude and frequency of the object. So there are some subtle movements that we can't tell from the naked eye in the surveillance video, such as the slight change in color of the face with the flow of blood, the slight fluctuation of the abdomen as it breathes. In medical care. Both of these subtle exercises can assist nursing staff in monitoring the patient's physical condition and sleep quality, so we need to enhance the fine movement in video surveillance. In order to enhance the fine motion in video surveillance, we first need to identify the target, then extract the region where the target is located, and enlarge the fine motion in the extracted region. Because target recognition and region extraction are very mature algorithms in video surveillance, this paper combines video surveillance in medical care applications. Focus on the fine motion enhancement algorithm. Firstly, this paper describes the principle of the fine motion enhancement algorithm. Then, combining the characteristics of video surveillance, this paper optimizes the fine motion enhancement algorithm. A good visualization effect is obtained. Finally. In this paper, the real-time enhancement of fine motion is realized. The specific work of this paper is as follows: 1) Linear Euler motion amplification algorithm can amplify both color and motion changes of target at the same time. However, there will be serious noise pollution and artifacts in the output video. Although the phase Euler motion amplification algorithm can solve the noise and artifact problems. In order to solve the problem of computational complexity, noise and artifact, the input video sequences are decomposed into complete pyramids. Then according to different motion types, different bandpass filters are selected to extract the fine motion we are interested in. Because the extracted image will be doped with the same frequency of noise. Therefore, the image is de-noised once. Finally, the de-noised image is amplified and the video is rerendered. (2) because the above algorithm is computationally intensive. At the same time to meet the real-time requirements of video surveillance. So this paper proposes a hardware acceleration scheme based on FPGA. In the process of hardware implementation. In this paper, the color space conversion module, pyramid decomposition module, denoising module and filtering module are designed firstly. Then according to the processing flow of each module. In order to realize the continuous and fast access to DDR by FPGA, the pipeline architecture is designed. In this paper, we design a ping-pong data buffer structure between DDR and FPGA.) in this paper, we first verify the fine motion enhancement algorithm on CPU. Then we realize the visualization of fine motion in video surveillance with Xilinx KC705 card. We analyze the time slice, brightness change and other parameters of video output. At the same time, the algorithm has a good ability to suppress noise. Finally, we design a monitoring system for fine motion, and complete the real-time monitoring of fine motion.
【學(xué)位授予單位】：中國科學(xué)技術(shù)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前7條

1 高聰;王福龍;;基于模板匹配和局部HOG特征的車牌識(shí)別算法[J];計(jì)算機(jī)系統(tǒng)應(yīng)用;2017年01期

2 王霞;付曉靜;王楠;王蒙軍;;預(yù)決策金字塔層數(shù)的歐拉視頻微弱運(yùn)動(dòng)放大算法[J];科學(xué)技術(shù)與工程;2016年01期

3 李樂鵬;雷林;孫水發(fā);尹輝;董方敏;;視頻微小運(yùn)動(dòng)放大的加速方法[J];計(jì)算機(jī)工程與應(yīng)用;2015年24期

4 賀承浩;金西;鄭琳琳;劉子恒;王浩原;;時(shí)變數(shù)據(jù)的實(shí)時(shí)體繪制加速算法優(yōu)化[J];計(jì)算機(jī)輔助設(shè)計(jì)與圖形學(xué)學(xué)報(bào);2014年02期

5 陳寧寧;尹乾;周媛;高麗娜;;數(shù)字圖像處理技術(shù)在智能交通中的應(yīng)用[J];電子設(shè)計(jì)工程;2013年03期

6 焦繼超;趙保軍;陶芬芳;婁娟;;一種基于局部圖像復(fù)原的天文圖像增強(qiáng)算法[J];儀器儀表學(xué)報(bào);2011年07期

7 楊海鋼;孫嘉斌;王慰;;FPGA器件設(shè)計(jì)技術(shù)發(fā)展綜述[J];電子與信息學(xué)報(bào);2010年03期

相關(guān)博士學(xué)位論文 前1條

1 賀承浩;實(shí)時(shí)超聲可視化關(guān)鍵技術(shù)研究[D];中國科學(xué)技術(shù)大學(xué);2013年

相關(guān)碩士學(xué)位論文 前5條

1 雷林;微小運(yùn)動(dòng)放大及其在水電工程監(jiān)測中的應(yīng)用[D];三峽大學(xué);2016年

2 李樂鵬;基于微小運(yùn)動(dòng)放大的視覺增強(qiáng)及其應(yīng)用研究[D];三峽大學(xué);2015年

3 陳澤茂;基于全景視覺的汽車安全駕駛輔助系統(tǒng)的平臺(tái)設(shè)計(jì)與實(shí)現(xiàn)[D];華南理工大學(xué);2014年

4 胡聘聘;基于歐拉視頻放大技術(shù)的視頻圖像微變化分析與研究[D];武漢理工大學(xué);2014年

5 王慶帥;智能監(jiān)控系統(tǒng)中人體行為識(shí)別技術(shù)研究與實(shí)現(xiàn)[D];西安電子科技大學(xué);2010年

，

本文編號(hào)：1359984