本文選題：自動聚焦 + 清晰度評價��； 參考：《浙江大學(xué)》2017年碩士論文

【摘要】：近年來,隨著數(shù)字和網(wǎng)絡(luò)的發(fā)展,網(wǎng)絡(luò)攝像機(jī)已成為安防監(jiān)控系統(tǒng)中重要的終端組成部分。高清網(wǎng)絡(luò)攝像機(jī)(HD_IPC)相對于傳統(tǒng)的模擬攝像機(jī)具有高清晰度、高交互性、智能化的特點(diǎn)。因此,高清網(wǎng)絡(luò)攝像機(jī)被廣泛地應(yīng)用于各種監(jiān)控場合,如銀行、安檢、公路等,已成為安防行業(yè)重要的終端產(chǎn)品。在網(wǎng)絡(luò)攝像機(jī)中,一體化的網(wǎng)絡(luò)攝像機(jī)占據(jù)了很重要的一個部分,能夠滿足不同場景下的高監(jiān)控需求。自動聚焦技術(shù)是一體機(jī)中的一項(xiàng)核心技術(shù),對于最終的成像質(zhì)量有直接的影響。本文研究了高清自動聚焦及其在網(wǎng)絡(luò)一體機(jī)中的應(yīng)用,主要包括三個核心子算法:圖像清晰度評價函數(shù)、峰值搜索算法和變焦跟蹤算法。本文總結(jié)了清晰度評價函數(shù)的定性評判標(biāo)準(zhǔn)和定量評判標(biāo)準(zhǔn),對現(xiàn)有、常用的清晰度評價函數(shù)進(jìn)行總結(jié)、分類。本文重點(diǎn)講述了基于小波分析的圖像清晰度評價函數(shù),然后對其進(jìn)行改進(jìn)和優(yōu)化,提出了基于小波變換和梯度函數(shù)融合的圖像清晰度評價函數(shù),并使用提升小波的方式來減少計(jì)算復(fù)雜度。本文提出的評價函數(shù)相對于其他的評價函數(shù)具有更好的'靈敏度和抗干擾性,在噪聲環(huán)境下也能保持良好的評價性能。本文根據(jù)聚焦曲線的理想特性,在現(xiàn)有峰值搜索算法的基礎(chǔ)上提出基于新判據(jù)的變步長峰值搜索算法。該方法將聚焦曲線的不同部分劃分為初始化(Initial)、粗調(diào)(Coarse)、中調(diào)(Mid)、細(xì)調(diào)(Fine)4個狀態(tài),不同狀態(tài)有不同的電機(jī)步長,在保持準(zhǔn)確性的前提下提升了峰值搜索算法的運(yùn)行速度。本文研究了現(xiàn)有的變焦跟蹤算法,對反饋?zhàn)兘垢櫵惴?FZT)進(jìn)行改進(jìn),提出了IFZT算法。IFZT相對于FZT算法,修改了反饋修正點(diǎn)的修正判據(jù),針對大幅離焦?fàn)顟B(tài)做了特殊處理,去除了相對復(fù)雜的PID算法,相對于FZT方法更加簡單、可靠,相比于GZT、AZT方法有更高的跟蹤精度。最后本文搭建了以海思Hi3516A為核心的IPC實(shí)驗(yàn)平臺,并且編寫了后端服務(wù)程序,進(jìn)行相應(yīng)的運(yùn)行和測試實(shí)驗(yàn)。實(shí)驗(yàn)結(jié)果表明,該實(shí)驗(yàn)平臺能準(zhǔn)確、穩(wěn)定地實(shí)現(xiàn)自動聚焦,滿足設(shè)計(jì)要求。
[Abstract]:In recent years, with the development of digital and network, network camera has become an important terminal component of security monitoring system. HDI PC has the characteristics of high definition, high interactivity and intelligence compared with the traditional analog camera. Therefore, high-definition network cameras are widely used in various monitoring occasions, such as banks, security inspection, highways and so on, which has become an important end product of security industry. In the network camera, the integrated network camera occupies a very important part, which can meet the needs of high monitoring in different scenes. Automatic focusing is one of the core technologies in an integrated computer, which has a direct impact on the final imaging quality. In this paper, the high-definition auto-focus and its application in the integrated network are studied, which includes three core sub-algorithms: image definition evaluation function, peak search algorithm and zoom tracking algorithm. This paper summarizes the qualitative evaluation criteria and quantitative evaluation criteria of definition evaluation function, summarizes and classifies the existing and commonly used definition evaluation functions. This paper focuses on the image definition evaluation function based on wavelet analysis, then improves and optimizes it, and puts forward the image definition evaluation function based on the fusion of wavelet transform and gradient function. The lifting wavelet is used to reduce the computational complexity. Compared with other evaluation functions, the evaluation function presented in this paper has better sensitivity and anti-interference, and can also maintain good evaluation performance in noisy environment. Based on the ideal characteristics of the focusing curve and the existing peak search algorithms, a new criterion based variable step size peak search algorithm is proposed in this paper. In this method, the different parts of the focusing curve are divided into four states: initialized initialer, coarseau, midway, fine Fine.There are different motor step sizes in different states, and the running speed of the peak search algorithm is improved on the premise of maintaining accuracy. In this paper, the existing zoom tracking algorithm is studied, the feedback zoom tracking algorithm is improved, and the IFZT algorithm is proposed relative to the FZT algorithm, the correction criterion of the feedback correction point is modified, and the special treatment for the large defocus state is made. Compared with the FZT method, the PID algorithm is simpler and more reliable, and has a higher tracking accuracy than the FZT algorithm. At last, the IPC experiment platform based on Hayes Hi3516A is built, and the back-end service program is written to run and test the experiment. The experimental results show that the platform can realize auto-focusing accurately and stably and meet the design requirements.
【學(xué)位授予單位】：浙江大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TN948.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 聶凱;劉文耀;王晉疆;;基于圖像矩函數(shù)的圖像清晰度評價方法[J];傳感技術(shù)學(xué)報;2013年10期

2 張桂慶;;高清網(wǎng)絡(luò)攝像機(jī)在公共領(lǐng)域的應(yīng)用與分析[J];中國安防;2012年09期

3 王健;陳洪斌;周國忠;安濤;;改進(jìn)的Brenner圖像清晰度評價算法[J];光子學(xué)報;2012年07期

4 李祚林;李曉輝;馬靈玲;胡s，

本文編號：1812304