【摘要】：運動目標的檢測和跟蹤作為數(shù)字圖像處理和計算機視覺領(lǐng)域的熱點,在自動導(dǎo)航、交通監(jiān)控、國防軍工等領(lǐng)域都具有十分高的應(yīng)用價值。過去幾十年,眾多研究者在目標檢測和跟蹤領(lǐng)域進行了深入的研究,但是由于應(yīng)用場景復(fù)雜多變、目標運動規(guī)律復(fù)雜等因素,導(dǎo)致目標的檢測與跟蹤技術(shù)無法得到大量廣泛的使用。因此,設(shè)計一種適用性強的目標檢測與跟蹤算法有著重大的意義。針對目標跟蹤檢測的有效性與準確性,本文在融合幀差法的混合高斯模型目標區(qū)域提取基礎(chǔ)上,研究基于多特征的粒子濾波目標跟蹤算法,并且利用BP神經(jīng)網(wǎng)絡(luò)調(diào)整與改進粒子濾波跟蹤算法。論文主要的算法改進和成果如下:一、提出一種融合幀差法的混合高斯模型獲取運動目標區(qū)域。混合高斯模型不能完整的檢測運動前景區(qū)域,容易將背景錯誤混淆成前景。本文通過融合幀差法和混合高斯模型,通過區(qū)分背景凸顯區(qū)域與前景區(qū)域,利用不同的學(xué)習(xí)速率來完整的提取目標運動區(qū)域。二、提出了基于多種特征融合的粒子濾波跟蹤方法。針對單個特征的跟蹤模型算法精度低,適用性差等問題。本文提取目標的顏色特征和HOG特征,構(gòu)建多特征觀測模型,通過該特征模型進行粒子濾波目標檢測與跟蹤。實驗表明該算法準確性更高。三、提出了一種通過BP神經(jīng)網(wǎng)絡(luò)改進多特征融合的粒子濾波跟蹤算法。傳統(tǒng)的粒子濾波算法具有粒子退化問題,粒子數(shù)越來越匱乏。本文利用BP神經(jīng)網(wǎng)絡(luò)反向傳播來調(diào)整更新粒子權(quán)值,增加粒子的多樣性,通過結(jié)合多特征模型,改善算法的濾波性能,并且提高了目標跟蹤的精度。本文通過以上三個方面對粒子濾波的目標檢測跟蹤算法做了優(yōu)化改進,實驗結(jié)果表明,在復(fù)雜的場景如發(fā)生遮擋、背景相似、運動規(guī)律多樣復(fù)雜等情況下,目標跟蹤的誤差得到縮減,精度獲得了相應(yīng)的提升。
[Abstract]:As a hot spot in the field of digital image processing and computer vision, the detection and tracking of moving targets has high application value in the fields of automatic navigation, traffic monitoring, national defense industry and so on. In the past few decades, many researchers have carried out in-depth research in the field of target detection and tracking. As a result, target detection and tracking technology can not be widely used. Therefore, it is of great significance to design a target detection and tracking algorithm with strong applicability. Aiming at the validity and accuracy of target tracking detection, this paper studies the particle filter target tracking algorithm based on multi-feature based on the target region extraction of hybrid Gao Si model based on fusion frame difference method. And the BP neural network is used to adjust and improve the particle filter tracking algorithm. The main improvements and results of this paper are as follows: firstly, a hybrid Gao Si model based on frame difference method is proposed to obtain the moving target region. The mixed Gao Si model can not detect the moving foreground region completely, so it is easy to confuse the background error with the foreground. By combining frame difference method and hybrid Gao Si model, this paper distinguishes the background salient region from the foreground region, and uses different learning rates to extract the moving region of the target completely. Secondly, a particle filter tracking method based on multi-feature fusion is proposed. The tracking model based on single feature has low accuracy and poor applicability. In this paper, the color features and HOG features of the target are extracted, and a multi-feature observation model is constructed, which is used for particle filter target detection and tracking. Experiments show that the algorithm is more accurate. Thirdly, an improved particle filter tracking algorithm based on BP neural network is proposed. The traditional particle filter algorithm has the problem of particle degradation, and the number of particles is becoming more and more scarce. In this paper, BP neural network is used to adjust the weight of the updated particle, to increase the diversity of particles, to improve the filtering performance of the algorithm and to improve the precision of target tracking by combining the multi-feature model. In this paper, the target detection and tracking algorithm of particle filter is optimized and improved through the above three aspects. The experimental results show that, in the case of complex scenes such as occlusion, similar background, complex motion rules and so on, The target tracking error is reduced and the accuracy is improved accordingly.
【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】：TP391.41;TP183

【參考文獻】

相關(guān)期刊論文 前10條

1 孫挺;齊迎春;耿國華;;基于幀間差分和背景差分的運動目標檢測算法[J];吉林大學(xué)學(xué)報(工學(xué)版);2016年04期

2 高仕博;程詠梅;肖利平;韋海萍;;面向目標檢測的稀疏表示方法研究進展[J];電子學(xué)報;2015年02期

3 閆河;劉婕;楊德紅;王樸;金煒;;基于特征融合的粒子濾波目標跟蹤新方法[J];光電子.激光;2014年10期

4 周建英;吳小培;張超;呂釗;;基于滑動窗的混合高斯模型運動目標檢測方法[J];電子與信息學(xué)報;2013年07期

5 夏楠;邱天爽;李景春;李書芳;;一種卡爾曼濾波與粒子濾波相結(jié)合的非線性濾波算法[J];電子學(xué)報;2013年01期

6 楊寧;錢峰;朱瑞;;基于遺傳算法的改進粒子濾波算法[J];上海交通大學(xué)學(xué)報;2011年10期

7 曹潔;李偉;;基于多特征融合的目標跟蹤算法[J];蘭州理工大學(xué)學(xué)報;2011年02期

8 程洪炳;黃國榮;倪世宏;劉華偉;;基于粒子濾波的自組織模糊神經(jīng)網(wǎng)絡(luò)算法研究[J];儀器儀表學(xué)報;2011年03期

9 羅寰;于雷;廖俊;穆中林;;復(fù)雜背景下紅外弱小多目標跟蹤系統(tǒng)[J];光學(xué)學(xué)報;2009年06期

10 齊美彬;王倩;蔣建國;安寶磊;;基于背景像素值頻次最高假設(shè)的背景重構(gòu)算法[J];中國圖象圖形學(xué)報;2008年04期

相關(guān)博士學(xué)位論文 前1條

1 丁建浩;基于單目視覺的人體檢測和運動恢復(fù)[D];浙江大學(xué);2013年

，

本文編號：2146137