發(fā)布時(shí)間：2018-03-23 03:34

  本文選題：行人檢測(cè)　切入點(diǎn)：LBP-HOG聯(lián)合特征　出處：《內(nèi)蒙古大學(xué)》2017年碩士論文　論文類(lèi)型：學(xué)位論文

【摘要】：近年來(lái),隨著社會(huì)的進(jìn)步,計(jì)算機(jī)行業(yè)也持續(xù)繁榮發(fā)展。計(jì)算機(jī)智能視覺(jué)技術(shù)儼然成為一個(gè)熱門(mén)的研究方向,其中行人檢測(cè)技術(shù)廣受研究者們青睞。實(shí)際生活中,行人檢測(cè)技術(shù)具有非常廣泛的用途,如致力于改善交通安全問(wèn)題的車(chē)輛輔助系統(tǒng),當(dāng)今社會(huì)無(wú)處不在的視頻監(jiān)控系統(tǒng),備受重視的人群數(shù)目預(yù)測(cè)與管理等,在機(jī)器人與高級(jí)人機(jī)交互等領(lǐng)域也有著很好的應(yīng)用價(jià)值。隨著Android系統(tǒng)在移動(dòng)端的廣泛應(yīng)用,它的發(fā)展前景廣受各界人士看好。另外,多種移動(dòng)端電子產(chǎn)品的體積小、便于攜帶、性能良好等優(yōu)點(diǎn)吸引了大量的用戶,所以,Android系統(tǒng)在移動(dòng)端的應(yīng)用市場(chǎng)十分廣闊,因此將行人檢測(cè)技術(shù)移植到Android平臺(tái)上有很大的必要性并且意義深遠(yuǎn)。將基于OpenCV的行人檢測(cè)移植到Android平臺(tái),這不僅使用戶能夠方便快捷的處理視頻圖像,還拓寬了 Android平臺(tái)的應(yīng)用范圍。本文主要考慮到行人檢測(cè)與安卓平臺(tái)具有良好的發(fā)展前景和廣闊的應(yīng)用領(lǐng)域,所以在安卓平臺(tái)上實(shí)現(xiàn)行人檢測(cè)。論文的主要工作內(nèi)容羅列如下:1.對(duì)Android系統(tǒng)進(jìn)行概述,包括Android系統(tǒng)的誕生發(fā)展與繁榮。詳細(xì)描述了 Android系統(tǒng)的組成框架與結(jié)構(gòu)、生命周期、四大組件和應(yīng)用進(jìn)程的工作過(guò)程等。2.詳細(xì)介紹了行人檢測(cè)技術(shù)中的基本行人特征,如SIFT特征、HOG特征與LBP特征。學(xué)習(xí)了傳統(tǒng)的訓(xùn)練行人檢測(cè)分類(lèi)器的算法,如SVM算法。另外,研究了利用Adaboost框架訓(xùn)練級(jí)聯(lián)分類(lèi)器的整個(gè)過(guò)程,并將此運(yùn)用于本次實(shí)驗(yàn)中。此后將因掃描多尺度圖片產(chǎn)生的多個(gè)矩形框利用并查集技術(shù)進(jìn)行融合。3.選擇INRIA數(shù)據(jù)集作為本項(xiàng)目實(shí)驗(yàn)的訓(xùn)練集與測(cè)試集,另外測(cè)試集還包括現(xiàn)場(chǎng)拍照與加載本地圖片�？紤]到HOG單一特征的不足和LBP特征對(duì)它的性能的一些補(bǔ)充作用,本項(xiàng)目結(jié)合LBP和HOG兩個(gè)特征來(lái)表征行人。由于聯(lián)合特征的維數(shù)增加,利用SVM分類(lèi)器進(jìn)行行人檢測(cè)時(shí)間消耗較大,所以使用Adaboost算法訓(xùn)練級(jí)聯(lián)分類(lèi)器,降低了算法的復(fù)雜性增加了行人檢測(cè)的正確率。4.搭建實(shí)驗(yàn)編碼的環(huán)境,首先搭建Android系統(tǒng)環(huán)境,在Android平臺(tái)上引入OpenCV庫(kù),將PC端的基于OpenCV開(kāi)發(fā)的行人檢測(cè)移植到Android平臺(tái)上。
[Abstract]:In recent years, with the progress of society, the computer industry has continued to flourish and develop. Computer intelligent vision technology has become a hot research direction, among which pedestrian detection technology is widely favored by researchers. In real life, Pedestrian detection technology has a wide range of applications, such as the vehicle assistant system which is dedicated to improving traffic safety, the ubiquitous video surveillance system in today's society, and the number prediction and management of the population that has received much attention, and so on. With the wide application of Android system in mobile terminal, its development prospect is widely appreciated by people from all walks of life. In addition, many kinds of mobile end electronic products are small in size and easy to carry. Good performance and other advantages have attracted a large number of users, so Android system in the mobile application market is very broad, Therefore, it is necessary and meaningful to transplant pedestrian detection technology to Android platform. Transplanting pedestrian detection based on OpenCV to Android platform not only enables users to process video images conveniently and quickly. It also broadens the application scope of Android platform. This paper mainly considers that pedestrian detection and Android platform have good development prospects and wide application fields. The main work of this paper is listed as follows: 1. This paper summarizes the Android system, including the birth, development and prosperity of the Android system. It describes in detail the framework and structure of the Android system, its life cycle. The basic pedestrian features in pedestrian detection technology, such as SIFT feature hog feature and LBP feature, are introduced in detail. The traditional algorithms of training pedestrian detection classifier, such as SVM algorithm, are studied. The whole process of training cascade classifier with Adaboost framework is studied. After that, the multiple rectangular frames generated by scanning multi-scale images are fused by the technique of parallel search. 3. The INRIA data set is selected as the training set and test set of the project experiment. In addition, the test set also includes taking pictures in situ and loading local images. Considering the shortcomings of the single feature of HOG and the supplement of LBP features to its performance, This project combines LBP and HOG features to represent pedestrians. Because the dimension of joint features increases and the time of pedestrian detection using SVM classifier is large, Adaboost algorithm is used to train cascade classifier. The complexity of the algorithm is reduced and the accuracy rate of pedestrian detection is increased. Finally, the environment of experimental coding is built. Firstly, the Android system environment is built, and the OpenCV library is introduced into the Android platform, and the pedestrian detection based on OpenCV is transplanted to the Android platform.
【學(xué)位授予單位】：內(nèi)蒙古大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 白云;王亞飛;朱偉;馬英楠;;城市密集人群安全管理大數(shù)據(jù)應(yīng)用大有可為[J];城市管理與科技;2016年06期

2 韓田甜;李航;張濤;;基于改進(jìn)HOG-LBP特征的行人檢測(cè)[J];信息工程大學(xué)學(xué)報(bào);2016年03期

3 段月媛;鄭登輝;;基于Android的個(gè)性化手機(jī)通訊錄設(shè)計(jì)[J];軟件導(dǎo)刊;2014年07期

4 張春鳳;宋加濤;王萬(wàn)良;;行人檢測(cè)技術(shù)研究綜述[J];電視技術(shù);2014年03期

5 王亦然;王瑞堯;;基于Android的二維碼掃描系統(tǒng)設(shè)計(jì)與實(shí)現(xiàn)[J];數(shù)字技術(shù)與應(yīng)用;2013年12期

6 關(guān)晶鑫;李永全;;Android中的Activity生命周期[J];電腦知識(shí)與技術(shù);2013年11期

7 蘇松志;李紹滋;陳淑媛;蔡國(guó)榕;吳云東;;行人檢測(cè)技術(shù)綜述[J];電子學(xué)報(bào);2012年04期

8 陳衛(wèi)伍;王建民;陳榕;;Dalvik在CAR構(gòu)件運(yùn)行時(shí)中的應(yīng)用研究[J];電腦知識(shí)與技術(shù);2010年31期

9 黃秀麗;王蔚;;SVM在非平衡數(shù)據(jù)集中的應(yīng)用[J];計(jì)算機(jī)技術(shù)與發(fā)展;2009年06期

10 任俊偉,林東岱;JNI技術(shù)實(shí)現(xiàn)跨平臺(tái)開(kāi)發(fā)的研究[J];計(jì)算機(jī)應(yīng)用研究;2005年07期

相關(guān)博士學(xué)位論文 前2條

1 張志杰;智能手機(jī)操作系統(tǒng)的競(jìng)爭(zhēng)與發(fā)展研究[D];北京郵電大學(xué);2012年

2 夏東;智能視頻監(jiān)控中目標(biāo)檢測(cè)、跟蹤和識(shí)別方法研究[D];國(guó)防科學(xué)技術(shù)大學(xué);2012年

相關(guān)碩士學(xué)位論文 前7條

1 周全良;基于多特征和Adaboost的行人檢測(cè)研究[D];南京郵電大學(xué);2014年

2 張義龍;基于加速度傳感器的人體運(yùn)動(dòng)狀態(tài)監(jiān)測(cè)的研究[D];南京郵電大學(xué);2014年

3 高原;基于移動(dòng)平臺(tái)的SNS系統(tǒng)的設(shè)計(jì)與實(shí)現(xiàn)[D];電子科技大學(xué);2013年

4 王寧波;基于RGB-D的行人檢測(cè)[D];浙江大學(xué);2013年

5 陳彩蓮;基于Android移動(dòng)平臺(tái)的智能視頻監(jiān)控系統(tǒng)設(shè)計(jì)[D];天津大學(xué);2012年

6 葉炳發(fā);Android操作系統(tǒng)移植及關(guān)鍵技術(shù)研究[D];暨南大學(xué);2010年

7 朱文佳;基于機(jī)器學(xué)習(xí)的行人檢測(cè)關(guān)鍵技術(shù)研究[D];上海交通大學(xué);2008年

，

本文編號(hào)：1651734