面向智能視頻監(jiān)控的高動態(tài)場景建模和修復(fù)
發(fā)布時間：2018-12-07 21:12
【摘要】：在智能視頻監(jiān)控中,場景建模和修復(fù)是目標檢測和場景理解的核心內(nèi)容。計算機視覺科技的進步使得背景建模的算法日臻成熟,對于普通場景中的前景物體變化都能做到較為準確的識別。但在視頻監(jiān)控中常常存在著一些復(fù)雜高動態(tài)的場景,其中前景在時域和空域中的比例都要大于背景,目前流行的背景建模算法難以做到實時、準確地建模。針對此問題,本文提出了一種基于“像素-模型”(Pixel to Model,P2M)距離的無參數(shù)背景模型。本論文在學(xué)術(shù)上的主要貢獻如下。1.本文提出了一種全新的像素表達框架:基于壓縮感知的理論,利用圖像中各點上下文信息,通過提取局部特征的方式來對中心像素進行建模。本文分析了之前多種基于色彩值的背景建模方式,針對其局限性提出了引入空域信息對像素點進行建模的方法,并使用壓縮感知的方法解決其面臨的巨大計算量的問題,將廣義的Haar-like特征引入背景建模,完成本文背景建模中像素點的特征表達。通過引入基于紋理和邊緣的圖像上下文信息,本文的背景模型在前景檢測上比單像素色彩模型更為準確,在監(jiān)控行業(yè)常見的高動態(tài)場景中的魯棒性也有所提高。2.針對先前的“像素-像素”背景建模方法的不足,本文提出了“像素-模型”距離的概念,以量化像素點和背景模型之間的相似度。該量化方式是本文前景分割和模型更新的基礎(chǔ)。同時,本文使用了最小和最大“像素-模型”距離來對像素點以及其鄰域像素點的背景模型進行更新,并對其中一些參數(shù)的自適應(yīng)性做了推導(dǎo)和說明。在復(fù)雜高動態(tài)環(huán)境的前景分割實驗中,該模型優(yōu)于主流的四種背景建模方法;在后續(xù)的應(yīng)用開發(fā)上,利用該模型能進行有效的智能視頻監(jiān)控。3.受高斯混合建模求取期望進行背景生成以及通過歷史幀的線性組合進行背景像素點計算方法的啟發(fā),本文提出了基于貝葉斯方法,使用最小“像素-模型”距離進行權(quán)重計算,并通過類似期望求取的辦法對場景圖像進行修復(fù)的方法,提高了視頻監(jiān)控中場景修復(fù)的準確性。
[Abstract]:In intelligent video surveillance, scene modeling and restoration are the core contents of target detection and scene understanding. With the development of computer vision technology, the background modeling algorithm is becoming more and more mature, which can recognize the change of foreground objects in common scene accurately. However, there are some complex and highly dynamic scenes in video surveillance, in which the foreground is larger than the background in the time domain and the spatial domain. The current popular background modeling algorithms are difficult to achieve real-time and accurate modeling. To solve this problem, a nonparametric background model based on "Pixel-Model" (Pixel to Model,P2M distance is proposed in this paper. The main contributions of this thesis are as follows. 1. In this paper, a new framework of pixel representation is proposed: based on the theory of compression perception, the central pixel is modeled by extracting local features by using the context information of each point in the image. In this paper, several methods of background modeling based on color value are analyzed, aiming at its limitation, a method of introducing spatial information to model pixels is put forward, and the problem of huge computation is solved by using compressed sensing method. The generalized Haar-like feature is introduced into the background modeling, and the feature representation of pixels in the background modeling is completed. By introducing context information based on texture and edge, the background model in this paper is more accurate than the single pixel color model in foreground detection, and the robustness in high dynamic scene is improved. 2. In this paper, the concept of "Pixel-Model" distance is proposed to quantify the similarity between pixel points and background models in view of the shortcomings of previous "Pixel-Pixel" background modeling methods. This quantization method is the basis of foreground segmentation and model updating in this paper. At the same time, the minimum and maximum "Pixel-Model" distance is used to update the background model of pixels and their neighboring pixels, and the self-adaptability of some of the parameters is deduced and explained. In the foreground segmentation experiment of complex high dynamic environment, the model is superior to the four main background modeling methods, and in the following application development, the model can be used to carry out effective intelligent video surveillance. 3. Inspired by Gao Si's mixed modeling and expected background generation, and by linear combination of historical frames, this paper proposes a method based on Bayesian method, which uses the minimum "Pixel-Model" distance to calculate the weight. The accuracy of scene restoration in video surveillance is improved by the method of scene image restoration.
【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2014
【分類號】：TP391.41;TN948.6
本文編號：2367878
[Abstract]:In intelligent video surveillance, scene modeling and restoration are the core contents of target detection and scene understanding. With the development of computer vision technology, the background modeling algorithm is becoming more and more mature, which can recognize the change of foreground objects in common scene accurately. However, there are some complex and highly dynamic scenes in video surveillance, in which the foreground is larger than the background in the time domain and the spatial domain. The current popular background modeling algorithms are difficult to achieve real-time and accurate modeling. To solve this problem, a nonparametric background model based on "Pixel-Model" (Pixel to Model,P2M distance is proposed in this paper. The main contributions of this thesis are as follows. 1. In this paper, a new framework of pixel representation is proposed: based on the theory of compression perception, the central pixel is modeled by extracting local features by using the context information of each point in the image. In this paper, several methods of background modeling based on color value are analyzed, aiming at its limitation, a method of introducing spatial information to model pixels is put forward, and the problem of huge computation is solved by using compressed sensing method. The generalized Haar-like feature is introduced into the background modeling, and the feature representation of pixels in the background modeling is completed. By introducing context information based on texture and edge, the background model in this paper is more accurate than the single pixel color model in foreground detection, and the robustness in high dynamic scene is improved. 2. In this paper, the concept of "Pixel-Model" distance is proposed to quantify the similarity between pixel points and background models in view of the shortcomings of previous "Pixel-Pixel" background modeling methods. This quantization method is the basis of foreground segmentation and model updating in this paper. At the same time, the minimum and maximum "Pixel-Model" distance is used to update the background model of pixels and their neighboring pixels, and the self-adaptability of some of the parameters is deduced and explained. In the foreground segmentation experiment of complex high dynamic environment, the model is superior to the four main background modeling methods, and in the following application development, the model can be used to carry out effective intelligent video surveillance. 3. Inspired by Gao Si's mixed modeling and expected background generation, and by linear combination of historical frames, this paper proposes a method based on Bayesian method, which uses the minimum "Pixel-Model" distance to calculate the weight. The accuracy of scene restoration in video surveillance is improved by the method of scene image restoration.
【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2014
【分類號】：TP391.41;TN948.6
【共引文獻】
相關(guān)期刊論文 前1條
1 徐巧玉;葉東;車仁生;;基于光學(xué)參考棒的立體視覺測量系統(tǒng)現(xiàn)場標定技術(shù)[J];光學(xué)學(xué)報;2008年01期
相關(guān)博士學(xué)位論文 前6條
1 鄒曉亮;車載測量系統(tǒng)數(shù)據(jù)處理若干關(guān)鍵技術(shù)研究[D];解放軍信息工程大學(xué);2011年
2 金翠云;MEMS平面微運動測量的若干關(guān)鍵技術(shù)研究[D];天津大學(xué);2004年
3 方磊;基于特征的圖像序列三維場景重建技術(shù)研究[D];華中科技大學(xué);2007年
4 陳京;新一代人機交互中基于多視點圖像的三維信息獲取研究[D];北京交通大學(xué);2013年
5 周駿;多視圖圖像三維重建若干關(guān)鍵技術(shù)研究[D];電子科技大學(xué);2013年
6 李暢;城市街道立面自動重建關(guān)鍵技術(shù)研究[D];武漢大學(xué);2009年
相關(guān)碩士學(xué)位論文 前2條
1 解江川;2D-3D視頻轉(zhuǎn)換中關(guān)鍵幀選取方法的研究[D];山東大學(xué);2014年
2 張迪;基于本質(zhì)矩陣的攝像機自標定研究[D];中國科學(xué)技術(shù)大學(xué);2014年
，本文編號：2367878
本文鏈接：http://sikaile.net/kejilunwen/wltx/2367878.html
最近更新
教材專著
