發(fā)布時(shí)間：2018-01-08 17:12

  本文關(guān)鍵詞：基于無人機(jī)視頻的運(yùn)動(dòng)車輛檢測(cè)研究　出處：《北京交通大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 無人機(jī)視頻 運(yùn)動(dòng)車輛檢測(cè) 改進(jìn)的ViBe算法 懸停 巡航狀態(tài)

【摘要】：隨著無人機(jī)研發(fā)技術(shù)日益成熟,無人機(jī)在民用領(lǐng)域各行業(yè)的應(yīng)用開發(fā)逐漸成為熱門的研究課題。無人機(jī)具有低成本、易部署、高機(jī)動(dòng)性、大視角范圍和統(tǒng)一尺度等優(yōu)勢(shì),可廣泛應(yīng)用于交通監(jiān)控和交通信息采集。本文綜合考慮無人機(jī)在交通視頻采集過程中具有懸停、巡航不同的飛行狀態(tài),針對(duì)無人機(jī)視頻圖像的特性,設(shè)計(jì)開發(fā)了基于無人機(jī)視頻的運(yùn)動(dòng)車輛檢測(cè)算法,并與幀差法、混合高斯算法、光流法等多種運(yùn)動(dòng)目標(biāo)檢測(cè)算法進(jìn)行對(duì)比研究,最后通過實(shí)驗(yàn)證明了本文算法檢測(cè)精度較高,并能滿足實(shí)時(shí)應(yīng)用的需要。本文的主要研究?jī)?nèi)容如下:(1)本文分析了無人機(jī)的發(fā)展前景和行業(yè)應(yīng)用的開發(fā)優(yōu)勢(shì),總結(jié)了無人機(jī)在交通領(lǐng)域的應(yīng)用研究現(xiàn)狀,詳細(xì)歸納了相關(guān)運(yùn)動(dòng)平臺(tái)視頻目標(biāo)檢測(cè)技術(shù)和圖像處理技術(shù),并對(duì)基于視頻的運(yùn)動(dòng)目標(biāo)檢測(cè)的主流算法進(jìn)行了詳細(xì)分析。(2)在考慮了無人機(jī)懸停和巡航不同飛行狀態(tài)下視頻處理需求的基礎(chǔ)上,開發(fā)了基于無人機(jī)視頻的運(yùn)動(dòng)車輛檢測(cè)算法,實(shí)現(xiàn)過程分為:①設(shè)置感興趣區(qū)域選擇運(yùn)動(dòng)車輛檢測(cè)的范圍;②引入ViBe背景更新算法進(jìn)行運(yùn)動(dòng)前景區(qū)域提取,改進(jìn)了ViBe算法使用固定閾值和存在鬼影問題的缺陷,提高了算法對(duì)無人機(jī)視頻運(yùn)動(dòng)目標(biāo)檢測(cè)的效果;③通過形態(tài)學(xué)優(yōu)化處理和車輛目標(biāo)識(shí)別完成了運(yùn)動(dòng)車輛的檢測(cè)。(3)通過定性、定量的實(shí)驗(yàn)分析,將幀差法、混合高斯算法和光流法三種主流的運(yùn)動(dòng)目標(biāo)檢測(cè)算法與本文算法進(jìn)行了比較,證明本文算法在無人機(jī)懸停和巡航狀態(tài)下均具有較高檢測(cè)精度(90.25%)和實(shí)時(shí)的計(jì)算速度(42.69fps),能夠有效地進(jìn)行基于無人機(jī)視頻的運(yùn)動(dòng)車輛檢測(cè),實(shí)現(xiàn)實(shí)時(shí)應(yīng)用。本研究對(duì)于豐富基于無人機(jī)視頻的車輛檢測(cè)和交通信息采集方法具有重要的參考意義,有助于無人機(jī)在交通領(lǐng)域應(yīng)用的推廣。
[Abstract]:With the development of UAV technology is increasingly mature, no application development in the field of civil UAV industry has gradually become a hot research topic. The UAV has the advantages of low cost, easy deployment, high mobility, large scope and unified scale and other advantages, can be widely used in traffic monitoring and traffic information collection. Considering the UAV with hovering in the traffic video capture process, different cruise flight, according to the characteristics of UAV video image, design and development of vehicle UAV video detection algorithm based on difference method, and with the frame, the mixed Gauss algorithm, comparative study of multiple moving targets detection algorithm of optical flow method, the experiment proved that the accuracy is higher the detection algorithm, and can meet the needs of real-time applications. The main contents of this paper are as follows: (1) this paper analyzes the development of UAV's development prospects and industry application No advantage, summarizes the application research situation in the field of transportation machine, sums up the relevant motion platform video object detection technology and image processing technology, and the mainstream of the moving target detection algorithm based on video analysis in detail. (2) in the UAV suspension based video processing and cruise stop needs different flight conditions on the development of the UAV video vehicle detection algorithm based on the realization process is divided into: setting ROI selection range of vehicle detection; the introduction of ViBe background updating algorithm of motion foreground domain extraction improved, and the existence of ghost defects using fixed threshold ViBe algorithm, improved algorithm the UAV video moving target detection; through the morphological processing and optimization of vehicle target recognition complete vehicle detection. (3) through qualitative and quantitative experiments Analysis of the frame difference method, the moving target detection algorithm and the algorithm of hybrid Gauss method and optical flow method three kinds were compared to prove that this algorithm has high detection accuracy in UAV hover and cruise state (90.25%) and real time computing speed (42.69fps), can effectively carry out vehicle UAV video detection based on real-time application. This research is to enrich the UAV video vehicle detection and traffic information collection method based on has the important reference significance, contribute to the promotion of human free applications in the transport sector.

【學(xué)位授予單位】：北京交通大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41;U495

【參考文獻(xiàn)】

相關(guān)期刊論文 前6條

1 周雨陽;龔藝;姚琳;李小勇;;無人機(jī)廣域視頻的機(jī)動(dòng)車交通參數(shù)計(jì)算及分析[J];交通運(yùn)輸系統(tǒng)工程與信息;2015年06期

2 張立業(yè);彭仲仁;李立;王華;;Road boundary estimation to improve vehicle detection and tracking in UAV video[J];Journal of Central South University;2014年12期

3 董建成;蔣樂天;;小型無人機(jī)交通輔助系統(tǒng)[J];電子產(chǎn)品世界;2014年11期

4 董晶;傅丹;楊夏;;無人機(jī)視頻運(yùn)動(dòng)目標(biāo)實(shí)時(shí)檢測(cè)及跟蹤[J];應(yīng)用光學(xué);2013年02期

5 王文龍;李清泉;唐爐亮;;基于低空機(jī)載視頻的車輛檢測(cè)方法[J];武漢理工大學(xué)學(xué)報(bào);2010年10期

6 左鳳艷;高勝法;韓建宇;;基于加權(quán)累積差分的運(yùn)動(dòng)目標(biāo)檢測(cè)與跟蹤[J];計(jì)算機(jī)工程;2009年22期

相關(guān)博士學(xué)位論文 前5條

1 仝小敏;航拍視頻運(yùn)動(dòng)目標(biāo)檢測(cè)與跟蹤方法研究[D];西北工業(yè)大學(xué);2015年

2 李子龍;智能交通系統(tǒng)中視頻目標(biāo)檢測(cè)與識(shí)別的關(guān)鍵算法研究[D];華南理工大學(xué);2014年

3 劉慧;基于低空視頻的多目標(biāo)檢測(cè)與跟蹤算法研究[D];武漢大學(xué);2013年

4 辛哲奎;基于視覺的小型無人直升機(jī)地面目標(biāo)跟蹤技術(shù)研究[D];南開大學(xué);2010年

5 徐治非;視頻監(jiān)控中運(yùn)動(dòng)目標(biāo)檢測(cè)與跟蹤方法研究[D];上海交通大學(xué);2009年

相關(guān)碩士學(xué)位論文 前2條

1 李聰;基于機(jī)載攝像機(jī)的高速公路車輛檢測(cè)與跟蹤技術(shù)的研究[D];東南大學(xué);2016年

2 吳長(zhǎng)俠;低空對(duì)地運(yùn)動(dòng)車輛檢測(cè)與運(yùn)動(dòng)特性分析[D];中國(guó)科學(xué)技術(shù)大學(xué);2011年

，

本文編號(hào)：1397966