本文關(guān)鍵詞： 視頻監(jiān)控 背景減除法 運(yùn)動(dòng)檢測(cè) 靜態(tài)相機(jī) 后處理　出處：《浙江大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：背景減除法在許多計(jì)算機(jī)視覺系統(tǒng)中是一個(gè)非常關(guān)鍵的步驟,它可以檢測(cè)視頻流中有意義的運(yùn)動(dòng)物體或區(qū)域,背景減除法主要應(yīng)用于視頻監(jiān)控、遙感和人機(jī)交互等。本文主要研究在靜態(tài)攝像機(jī)條件下針對(duì)靜態(tài)背景的背景減除法。首先討論了一般背景減除法所面臨的主要挑戰(zhàn)包括逐漸光照條件變化、光照條件突變、動(dòng)態(tài)背景、相機(jī)抖動(dòng)、前景偽裝、前景陰影、Ghost區(qū)域等;其次介紹了目前主流背景減除法的基本原理和特點(diǎn),分析不同類型背景減除法的優(yōu)缺點(diǎn)。在簡(jiǎn)單幀間差法中通常采用線性平滑平均更新方法來更新背景模型,本文提出了一種基于非線性更新方法來更新背景模型。在一像素點(diǎn)被判定為背景的情況下,根據(jù)該像素點(diǎn)當(dāng)前輸入和該像素點(diǎn)前一時(shí)刻背景之間的差異來自適應(yīng)調(diào)整更新率,從而使得背景模型隨時(shí)間推移更加穩(wěn)定,不會(huì)輕易將一些前景內(nèi)容包含進(jìn)來。我們同時(shí)還把該非線性更新策略推廣到ViBe算法中,使得ViBe中原先離散隨機(jī)背景更新策略拓展成連續(xù)隨機(jī)背景更新策略,而原先背景更新策略是新的背景更新策略的一種特殊情況。為了客觀分析比較不同背景減除法在不同場(chǎng)景下的檢測(cè)結(jié)果,本文采用Change Detection 2012和2014的數(shù)據(jù)集對(duì)算法的檢測(cè)結(jié)果進(jìn)行量化分析和比較,發(fā)現(xiàn)采用非線性背景更新策略的兩種具有代表性算法在一些視頻類別上檢測(cè)精度比原算法有大幅度的提高。但是由于背景減除法所面臨的挑戰(zhàn),設(shè)計(jì)一種背景減除算法能適用于所有的場(chǎng)景和光照條件仍是一個(gè)非常困難的問題。
[Abstract]:Background subtraction is a key step in many computer vision systems. It can detect significant moving objects or regions in video streams. Background subtraction is mainly used in video surveillance. Remote sensing and human-computer interaction, etc. In this paper, the background subtraction method for static background under the condition of static camera is studied. Firstly, the main challenges of the general background subtraction method are discussed, including the gradual change of illumination condition, the abrupt change of illumination condition, and so on. Dynamic background, camera shake, foreground camouflage, foreground shadow Ghost region, etc. Secondly, the basic principle and characteristics of current mainstream background subtraction and division are introduced. The advantages and disadvantages of subtraction and division of different types of background are analyzed. The linear smooth average updating method is usually used to update the background model in the simple inter-frame difference method. In this paper, a nonlinear updating method is proposed to update the background model. In the case of a pixel being judged as background, the difference between the current input of the pixel and the background at the previous moment of the pixel is derived from the adaptive updating rate. So that the background model is more stable over time, and some foreground content will not be included easily. We also extend the nonlinear updating strategy to ViBe algorithm. The original discrete random background updating strategy in ViBe is extended to continuous random background updating strategy. The original background updating strategy is a special case of the new background updating strategy. In order to objectively analyze and compare the detection results of different background subtraction methods in different scenarios, In this paper, the data sets of Change Detection 2012 and 2014 are used to quantitatively analyze and compare the detection results of the algorithm. It is found that the two representative algorithms with nonlinear background updating strategy have much higher detection accuracy than the original algorithm in some video categories. However, because of the challenges faced by the background subtraction method, It is still a very difficult problem to design a background subtraction algorithm that can be applied to all scenes and lighting conditions.
【學(xué)位授予單位】：浙江大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前7條

1 趙光磊;許向陽;;對(duì)運(yùn)動(dòng)車輛檢測(cè)之背景減除法的一點(diǎn)改進(jìn)[J];無線互聯(lián)科技;2013年06期

2 陳華;胡春海;;基于積分圖像的人體肢體檢測(cè)算法[J];應(yīng)用光學(xué);2011年05期

3 楊磊;;背景減除法在機(jī)場(chǎng)場(chǎng)面監(jiān)視系統(tǒng)視頻信號(hào)處理中的應(yīng)用[J];電子技術(shù)與軟件工程;2014年02期

4 韓新宇;朱齊丹;章慧君;;基于人體頭肩部形狀的身份識(shí)別[J];應(yīng)用科技;2006年12期

5 宋濤;李林濤;宋振宇;;一種抗遮擋的全自動(dòng)Mean-shift跟蹤算法[J];信息安全與通信保密;2010年09期

6 黃文麗;范勇;李繪卓;薛琴;唐遵烈;李立;;改進(jìn)的混合高斯算法[J];計(jì)算機(jī)工程與設(shè)計(jì);2011年02期

7 李世鋒;文志強(qiáng);吳岳忠;;基于改進(jìn)的GMM參數(shù)估計(jì)的目標(biāo)檢測(cè)方法[J];重慶工商大學(xué)學(xué)報(bào)(自然科學(xué)版);2013年05期

相關(guān)碩士學(xué)位論文 前4條

1 楊志翔;面向靜態(tài)相機(jī)的背景減除法分析比較[D];浙江大學(xué);2017年

2 李金奎;視頻中運(yùn)動(dòng)目標(biāo)的檢測(cè)和提取方法研究[D];北京郵電大學(xué);2011年

3 楊帆;智能化考場(chǎng)中考生考勤的關(guān)鍵技術(shù)研究[D];昆明理工大學(xué);2014年

4 趙海鵬;視頻中運(yùn)動(dòng)目標(biāo)檢測(cè)與跟蹤算法的研究和實(shí)現(xiàn)[D];電子科技大學(xué);2013年

，

本文編號(hào)：1510896