本文選題：運(yùn)動(dòng)目標(biāo)檢測(cè)　切入點(diǎn)：mean　出處：《南京理工大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：近年來,隨著機(jī)器視覺、智能視頻監(jiān)控等領(lǐng)域的快速發(fā)展,運(yùn)動(dòng)目標(biāo)的識(shí)別與跟蹤技術(shù)日漸發(fā)展與成熟。針對(duì)基于視覺的運(yùn)動(dòng)目標(biāo)跟蹤技術(shù),論文提出了一種基于ARM嵌入式平臺(tái)的運(yùn)動(dòng)目標(biāo)跟蹤方案,將嵌入式平臺(tái)和運(yùn)動(dòng)目標(biāo)跟蹤技術(shù)結(jié)合起來。本論文主要工作和成果如下:(1)研究了三種典型的的運(yùn)動(dòng)目標(biāo)檢測(cè)算:光流法、幀間差分法和基于混合高斯模型的背景減除法。在各種現(xiàn)有算法的基礎(chǔ)上,提出了一種基于Surendra背景更新算法的運(yùn)動(dòng)目標(biāo)檢測(cè)算法,從二值差分方法、自適應(yīng)閾值分割和背景更新策略三個(gè)方面進(jìn)行了改進(jìn)。(2)對(duì)目標(biāo)跟蹤算法進(jìn)行了研究。在兩種主流目標(biāo)跟蹤算法:mean shift和粒子濾波算法基礎(chǔ)上,提出了一種以粒子濾波算法為框架的改進(jìn)算法。改進(jìn)的粒子濾波算法融合了顏色和運(yùn)動(dòng)兩種特征,采用一種改進(jìn)的重要性重采樣方法,并且把mean shift嵌入到粒子濾波算法中。(3)完成了運(yùn)動(dòng)目標(biāo)跟蹤算法的嵌入式設(shè)計(jì)。構(gòu)建了一個(gè)以MINI5728為核心、搭載USB攝像頭的嵌入式平臺(tái),完成了軟件開發(fā)環(huán)境的搭建并對(duì)嵌入式Linux系統(tǒng)進(jìn)行移植。在此基礎(chǔ)上完成了運(yùn)動(dòng)目標(biāo)跟蹤系統(tǒng)的軟件設(shè)計(jì),包括基于VideoLinux2的圖像采集模塊設(shè)計(jì)、基于計(jì)算機(jī)視覺庫OpenCV的運(yùn)動(dòng)目標(biāo)跟蹤模塊設(shè)計(jì)以及Qt可視化界面的開發(fā)。
[Abstract]:In recent years, with the rapid development of machine vision, intelligent video surveillance and other fields, moving target recognition and tracking technology has been developed and matured. In this paper, a moving target tracking scheme based on ARM embedded platform is proposed. The main work and results of this paper are as follows: 1) three typical algorithms of moving target detection are studied: optical flow method, optical flow method, Based on the existing algorithms, a moving target detection algorithm based on Surendra background updating algorithm is proposed. The adaptive threshold segmentation and background updating strategy are improved. (2) the target tracking algorithm is studied. On the basis of two main target tracking algorithms:: mean shift and particle filter, An improved particle filter algorithm is proposed, which combines color and motion features, and uses an improved importance resampling method. The embedded design of moving target tracking algorithm is completed by embedding mean shift into particle filter algorithm. An embedded platform based on MINI5728 and USB camera is constructed. The software development environment is built and the embedded Linux system is transplanted. On this basis, the software design of the moving target tracking system is completed, including the design of the image acquisition module based on VideoLinux2. The design of moving target tracking module based on computer vision library OpenCV and the development of QT visual interface.
【學(xué)位授予單位】：南京理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前5條

1 翟衛(wèi)欣;程承旗;;基于Kalman濾波的Camshift運(yùn)動(dòng)跟蹤算法[J];北京大學(xué)學(xué)報(bào)(自然科學(xué)版);2015年05期

2 張娟;毛曉波;陳鐵軍;;運(yùn)動(dòng)目標(biāo)跟蹤算法研究綜述[J];計(jì)算機(jī)應(yīng)用研究;2009年12期

3 曹占中;周余;王自強(qiáng);都思丹;;基于s3c2440的Linux攝像頭驅(qū)動(dòng)開發(fā)[J];電子測(cè)量技術(shù);2009年02期

4 王素玉;沈蘭蓀;;智能視覺監(jiān)控技術(shù)研究進(jìn)展[J];中國(guó)圖象圖形學(xué)報(bào);2007年09期

5 ;TI推出嵌入式最強(qiáng)處理器AM57x[J];儀表技術(shù);2015年11期

，

本文編號(hào)：1570236