發(fā)布時(shí)間：2018-11-26 16:42

【摘要】：背景建模作為目標(biāo)檢測、場景理解等的關(guān)鍵環(huán)節(jié),具有重要的研究意義。本文的主要研究內(nèi)容是基于模型-模型距離的復(fù)雜場景建模,主要研究工作如下:針對傳統(tǒng)的背景建模算法沒有充分利用像素點(diǎn)的時(shí)空信息,本文提出了一種基于深度神經(jīng)網(wǎng)絡(luò)的背景建模方法。為了更充分的利用像素點(diǎn)的空間信息,同時(shí)改變提取空間信息的空間范圍,本文設(shè)計(jì)利用了包含不同膨脹系數(shù)的atrous卷積多分支結(jié)構(gòu),用以提取像素不同鄰域范圍的空間信息。另外,為了更充分的利用像素點(diǎn)的時(shí)間域信息,本文提出了對連續(xù)視頻幀圖像序列進(jìn)行變間隔采樣得到網(wǎng)絡(luò)輸入的方法。通過在數(shù)據(jù)庫ChangeDetection Benchmark Dataset的四個(gè)場景中的主觀和客觀實(shí)驗(yàn)對比,本文提出的算法在不同場景中具有較好的適應(yīng)性,特別是在Office場景中的F-Measure達(dá)到92.36%,較經(jīng)典背景建模算法有提升。針對在前景目標(biāo)有長時(shí)間靜止時(shí),前景和背景不能很好的被區(qū)分,本文提出了基于模型-模型距離的背景建模方法。本文提出了一種基于深度神經(jīng)網(wǎng)絡(luò)的特征提取,并建立特征模型和初始化背景模型。根據(jù)深度神經(jīng)網(wǎng)絡(luò)能夠通過學(xué)習(xí)不斷優(yōu)化特征的提取方式,使得特征能夠更好的表達(dá)關(guān)鍵信息,本文通過深度神經(jīng)網(wǎng)絡(luò)提取特征。進(jìn)一步地,本文提出的特征模型中包含了深層網(wǎng)絡(luò)中的特征和淺層網(wǎng)絡(luò)中的特征,使得特征模型從不同層面對像素點(diǎn)進(jìn)行描述。同時(shí)利用特征模型對像素點(diǎn)的背景模型進(jìn)行初始化。為了衡量像素點(diǎn)和其背景模型的相似度,提出了特征模型到背景模型(Feature Model to Background Model,M2M)的距離。針對前景目標(biāo)突然離開造成的“空洞”,本文利用最小、最大M2M距離對像素點(diǎn)和其鄰域像素點(diǎn)的背景模型進(jìn)行更新。另外,本文介紹了模型更新控制器的自適應(yīng)更新過程。通過在數(shù)據(jù)庫ChangeDetection Benchmark Dataset的四個(gè)場景中的主觀和客觀實(shí)驗(yàn)對比,本文提出的M2M算法較好于主流的五種背景建模算法。特別是在場景Office中的F-Measure達(dá)到95.94%,較基于深度神經(jīng)網(wǎng)絡(luò)的背景建模算法有提升。
[Abstract]:Background modeling, as a key link in target detection and scene understanding, is of great significance. The main content of this paper is modeling of complex scene based on model-model distance. The main research work is as follows: the traditional background modeling algorithm does not make full use of space-time information of pixel points. In this paper, a background modeling method based on deep neural network is proposed. In order to make full use of the spatial information of pixels and change the spatial range of extracting spatial information, this paper designs and uses the multi-branch structure of atrous convolution with different expansion coefficients to extract spatial information from different neighborhood areas of pixels. In addition, in order to make full use of the time domain information of pixels, this paper proposes a method to obtain the network input by sampling the sequence of continuous video frames at variable intervals. Through the comparison of subjective and objective experiments in four scenarios of database ChangeDetection Benchmark Dataset, the algorithm proposed in this paper has better adaptability in different scenarios, especially in the Office scene, the F-Measure reaches 92.36. Compared with the classical background modeling algorithm, it is better than the classical background modeling algorithm. The background modeling method based on model-model distance is proposed to solve the problem that the foreground and background can not be distinguished well when the foreground target is stationary for a long time. In this paper, a feature extraction method based on depth neural network is proposed, and the feature model and initialization background model are established. According to the depth neural network can learn to optimize the feature extraction way, so that the feature can better express the key information, this paper extracts the feature through the depth neural network. Furthermore, the feature model proposed in this paper includes the features in the deep network and the features in the shallow network, which makes the feature model describe pixels from different levels. At the same time, the feature model is used to initialize the background model of pixels. In order to measure the similarity between pixel and its background model, the distance between feature model and background model (Feature Model to Background Model,M2M) is proposed. Aiming at the "void" caused by the sudden departure of the foreground target, the background model of the pixel and its neighboring pixel is updated by using the minimum and maximum M2m distance. In addition, this paper introduces the adaptive updating process of model update controller. By comparing the subjective and objective experiments in the four scenarios of database ChangeDetection Benchmark Dataset, the M2m algorithm proposed in this paper is better than the five mainstream background modeling algorithms. Especially, the F-Measure in scene Office reaches 95.94, which is better than the background modeling algorithm based on depth neural network.
【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】：2017
【分類號】：TP391.41;TP183

【參考文獻(xiàn)】

相關(guān)期刊論文 前1條

1 Bi Song;Han Cunwu;Sun Dehui;;Neural network based method for background modeling and detecting moving objects[J];The Journal of China Universities of Posts and Telecommunications;2015年03期

相關(guān)碩士學(xué)位論文 前2條

1 蘇建安;面向智能視頻監(jiān)控的高動(dòng)態(tài)場景建模和修復(fù)[D];電子科技大學(xué);2014年

2 陳景東;智能視頻監(jiān)控中的目標(biāo)檢測技術(shù)研究[D];華中科技大學(xué);2011年

，

本文編號：2359084