本文選題：電子穩(wěn)像 + 特征點(diǎn)匹配　； 參考：《西安科技大學(xué)》2017年碩士論文

【摘要】：由于煤層氣排采設(shè)備的工作環(huán)境比較惡劣,監(jiān)控設(shè)備在這種環(huán)境中工作容易發(fā)生隨機(jī)的抖動(dòng),經(jīng)常會(huì)造成誤報(bào)警現(xiàn)象。而電子穩(wěn)像技術(shù)可以很好的解決這個(gè)問(wèn)題。該技術(shù)是一種穩(wěn)定視頻圖像序列的技術(shù),它具有穩(wěn)像精度高、體積小、重量輕、功耗低等優(yōu)勢(shì)。該技術(shù)在軍事和民用技術(shù)都受到了廣泛的關(guān)注。首先,本文系統(tǒng)的研究了電子穩(wěn)像基本原理及其處理過(guò)程,并對(duì)電子穩(wěn)像算法中四種常用的經(jīng)典算法進(jìn)行了分析,其中有塊匹配法、位平面匹配法、灰度投影算法、特征向量跟蹤法。通過(guò)穩(wěn)像精度、算法的運(yùn)行速度、算法的適用環(huán)境等指標(biāo)給出了算法各自的優(yōu)缺點(diǎn)。根據(jù)本課題的要求,最終選定用基于Harris角點(diǎn)檢測(cè)的特征點(diǎn)匹配算法實(shí)現(xiàn)電子穩(wěn)像的目的。在圖像預(yù)處理的過(guò)程中,針對(duì)原始的開關(guān)中值濾波在保留細(xì)線和細(xì)節(jié)方面的不足,應(yīng)用了一種改進(jìn)的開關(guān)中值濾波方法。通過(guò)仿真實(shí)驗(yàn),對(duì)噪聲信號(hào)從5%增加到30%的圖像進(jìn)行濾波,改進(jìn)后的方法比原始方法峰值信噪比提高的平均值是3.64ldB,圖像的毀壞程度縮小了 1.2%,說(shuō)明改進(jìn)的方法可以更好的保留圖像中的細(xì)線和細(xì)節(jié)。通過(guò)Harris算法對(duì)特征點(diǎn)進(jìn)行提取,并對(duì)其進(jìn)行匹配,從匹配的特征點(diǎn)運(yùn)動(dòng)矢量中求得運(yùn)動(dòng)參數(shù),根據(jù)運(yùn)動(dòng)參數(shù)對(duì)圖像進(jìn)行補(bǔ)償并輸出穩(wěn)定的圖像序列。其次,將電子穩(wěn)像算法移植到TI公司所生產(chǎn)的硬件平臺(tái)DM6467上,并對(duì)算法進(jìn)行優(yōu)化。通過(guò)對(duì)TMS320DM6467的結(jié)構(gòu)和框架的分析,完成DAVINCI開發(fā)環(huán)境的配置,并且對(duì)算法移植的過(guò)程做了詳細(xì)的說(shuō)明。通過(guò)程序優(yōu)化和內(nèi)存的優(yōu)化兩種優(yōu)化方法對(duì)算法進(jìn)行了優(yōu)化,提高了算法的運(yùn)行速度。其中,程序優(yōu)化中又用了 C語(yǔ)言優(yōu)化和匯編語(yǔ)言優(yōu)化。最后,通過(guò)主觀評(píng)價(jià)和客觀評(píng)價(jià)兩種方式對(duì)穩(wěn)像前后的圖像進(jìn)行質(zhì)量評(píng)價(jià),主觀評(píng)價(jià)給出了圖像質(zhì)量評(píng)價(jià)的打分方法,它是以多名實(shí)驗(yàn)室的同學(xué)作為評(píng)判員對(duì)同一張圖像的穩(wěn)像前后的圖像進(jìn)行打分,然后取平均值,穩(wěn)像后圖像要比穩(wěn)像前的平均高1.3分左右。應(yīng)用的客觀評(píng)價(jià)方法包括峰值信噪比,加權(quán)峰值信噪比和差影比較法。實(shí)驗(yàn)結(jié)果顯示穩(wěn)像后的峰值信噪比的值相對(duì)于穩(wěn)像前平均提高了 7.542dB,加權(quán)峰值信噪比平均提高了 6.614dB,對(duì)比穩(wěn)像前后相鄰兩幀圖像的差影圖可以明顯看出穩(wěn)像后所留下的灰度值小,說(shuō)明穩(wěn)定的程度更高。綜合兩種評(píng)價(jià)方法得出該算法在硬件平臺(tái)DM6467上很好的實(shí)現(xiàn)了穩(wěn)像的目的,對(duì)穩(wěn)像的效果比較滿意。
[Abstract]:Because of the poor working environment of coal bed methane extraction equipment, random jitter is easy to occur in the monitoring equipment working in this environment, which often results in false alarm phenomenon. And electronic image stabilization technology can solve this problem very well. This technology is a stable video image sequence technology, it has the advantages of high image stabilization accuracy, small volume, light weight, low power consumption and so on. This technology has received extensive attention in both military and civil technology. Firstly, this paper systematically studies the basic principle of electronic image stabilization and its processing process, and analyzes four common classical algorithms of electronic image stabilization, including block matching, bit plane matching and gray projection algorithm. Eigenvector tracking method. The advantages and disadvantages of the algorithm are given by the image stabilization accuracy, the speed of the algorithm and the applicable environment of the algorithm. According to the requirement of this paper, the aim of electronic image stabilization is to use the feature point matching algorithm based on Harris corner detection. In the process of image preprocessing, an improved switching median filtering method is applied to solve the deficiency of the original switching median filter in preserving fine lines and details. Through the simulation experiment, the image whose noise signal is increased from 5% to 30% is filtered. Compared with the original method, the average value of the improved method is 3.64ldB, and the damage degree of the image is reduced by 1.2, which shows that the improved method can better retain the fine lines and details in the image. The feature points are extracted and matched by Harris algorithm. The motion parameters are obtained from the motion vectors of the matching feature points. The image is compensated according to the motion parameters and a stable image sequence is output. Secondly, the electronic image stabilization algorithm is transplanted to the hardware platform DM6467 produced by TI, and the algorithm is optimized. By analyzing the structure and framework of TMS320DM6467, the configuration of DAVINCI development environment is completed, and the process of algorithm porting is explained in detail. Two optimization methods, program optimization and memory optimization, are used to optimize the algorithm and improve the speed of the algorithm. Among them, C language optimization and assembly language optimization are used in program optimization. Finally, the image quality before and after stabilization is evaluated by subjective evaluation and objective evaluation, and the evaluation method of image quality is given. It uses several laboratory students as judges to rate the image before and after the same image stabilization, and then takes the average value. The image after image stabilization is about 1.3 points higher than that before the image stabilization. The objective evaluation methods used include peak signal-to-noise ratio, weighted peak signal-to-noise ratio and contrast comparison. The experimental results show that the peak signal-to-noise ratio (PSNR) after image stabilization is 7.542 dB higher than that before stabilization, and the weighted peak signal-to-noise ratio (PSNR) is increased by 6.614 dB on average. The gray value left behind is small, The degree of stability is higher. By synthesizing two evaluation methods, it is concluded that the algorithm achieves the purpose of image stabilization on the hardware platform DM6467, and is satisfied with the effect of image stabilization.
【學(xué)位授予單位】：西安科技大學(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 張見(jiàn)雙;張紅民;羅永濤;陳柏元;;一種改進(jìn)的Harris角點(diǎn)檢測(cè)的圖像配準(zhǔn)方法[J];激光與紅外;2017年02期

2 汪波;;基于特征匹配的電子穩(wěn)像算法研究[J];數(shù)字技術(shù)與應(yīng)用;2016年11期

3 翟博;鄭錦;劉養(yǎng)科;;一種多子塊協(xié)同的自適應(yīng)快速數(shù)字穩(wěn)像方法[J];電子與信息學(xué)報(bào);2016年05期

4 鮮勇;董力文;;基于角點(diǎn)特征的機(jī)載攝像系統(tǒng)電子穩(wěn)像算法[J];光學(xué)與光電技術(shù);2016年02期

5 葉建平;陸小霞;;我國(guó)煤層氣產(chǎn)業(yè)發(fā)展現(xiàn)狀和技術(shù)進(jìn)展[J];煤炭科學(xué)技術(shù);2016年01期

6 張?jiān)?張巍;伍小潔;楊鶴猛;趙恩偉;;一種適用于電子穩(wěn)像的圖像補(bǔ)償方法[J];光學(xué)與光電技術(shù);2015年06期

7 鄧娜;田增山;袁正午;;基于達(dá)芬奇技術(shù)的視頻監(jiān)控系統(tǒng)設(shè)計(jì)[J];電子技術(shù)應(yīng)用;2015年01期

8 王金洋;余紅英;樊永生;;基于C6000系列DSP的算法優(yōu)化研究[J];中國(guó)科技信息;2015年01期

9 王建平;曾祥鴻;;基于DM6467的H.264高清視頻壓縮平臺(tái)的設(shè)計(jì)[J];光學(xué)與光電技術(shù);2014年06期

10 王初陽(yáng);李力;劉伯棟;任志斌;;基于DM642的電子穩(wěn)像算法研究[J];火力與指揮控制;2014年S1期

相關(guān)碩士學(xué)位論文 前10條

1 靳萬(wàn)鑫;手持成像設(shè)備復(fù)合運(yùn)動(dòng)下的快速電子穩(wěn)像技術(shù)研究[D];哈爾濱工業(yè)大學(xué);2016年

2 李寶同;運(yùn)動(dòng)估計(jì)算法的改進(jìn)及電子穩(wěn)像技術(shù)應(yīng)用[D];北京工業(yè)大學(xué);2016年

3 郭政;基于多分辨率灰度投影的電子穩(wěn)像算法研究[D];中國(guó)礦業(yè)大學(xué);2016年

4 黃文娟;運(yùn)動(dòng)狀態(tài)下的視頻穩(wěn)像技術(shù)研究[D];南京航空航天大學(xué);2016年

5 王曉東;實(shí)時(shí)電子穩(wěn)像技術(shù)研究[D];北京理工大學(xué);2015年

6 李棱銥;基于塊匹配和局部子空間的視頻穩(wěn)像方法研究[D];大連理工大學(xué);2015年

7 張玉英;基于特征匹配的電子穩(wěn)像算法研究[D];西安電子科技大學(xué);2014年

8 李昕;基于FPGA的Harris角點(diǎn)圖像配準(zhǔn)系統(tǒng)設(shè)計(jì)與實(shí)現(xiàn)[D];東北大學(xué);2014年

9 倪越;基于DSP的快速目標(biāo)檢測(cè)系統(tǒng)的研究與實(shí)現(xiàn)[D];西安電子科技大學(xué);2014年

10 顧學(xué)海;基于DSP642的電子穩(wěn)像技術(shù)[D];南京理工大學(xué);2014年

，

本文編號(hào)：1787781