跳到主要內容

臺灣博碩士論文加值系統

(18.204.48.64) 您好!臺灣時間:2021/08/04 18:00
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:洪善群
研究生(外文):Simon Hung
論文名稱:人體偵測與追蹤演算法的分類與評估
論文名稱(外文):A Taxonomy and Evaluation of Human Detection and Tracking Algorithms
指導教授:劉震昌
指導教授(外文):Jen-Chang Liu
學位類別:碩士
校院名稱:國立暨南國際大學
系所名稱:資訊工程學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2007
畢業學年度:95
語文別:中文
論文頁數:101
中文關鍵詞:前景偵測人體偵測人體追蹤
外文關鍵詞:Foreground DetectionHuman DetectionHuman Tracking
相關次數:
  • 被引用被引用:0
  • 點閱點閱:308
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:2
人體偵測與追蹤為電腦視覺中一項重要的研究主題,已被廣泛利用到監視系統、人機介面、行為分析等應用上面。現今有許多的人體偵測與追蹤系統,當面對偵測環境改變時,都會導致偵測效果不佳,並且沒有一套整合的平台來評估不同的人體偵測與追蹤系統。本論文將人體偵測與追蹤演算法區分成以下主要步驟:
(1)影像擷取,以影像擷取裝置得到影像序列;
(2)前景偵測,使用快速且正確的方式將物體從背景中分離;
(3)人體偵測,在前景偵測結果中以人體特徵來找出人體位置;
(4)人體追蹤,在影像序列中找出人體移動的軌跡。
利用上述分類,我們可以探討這些步驟的設計需求,完成這些步驟的各種演算法的優、缺點,並實驗如何整合出一個最佳的人體偵測與追蹤系統。
為了達到整合各種不同演算法的目的,本篇論文在MATLAB環境下設計一套人體偵測與追蹤的整合測試平台,將人體偵測與追蹤系統的三個主要部份:前景偵測、人體偵測、與人體追蹤,每個主要部分的程式都模組化,使得系統可以在各個模組彈性的測試不同的演算法。我們亦提出了幾組公開測試資料及效能評估計算方法,便於比較不同人體偵測與追蹤演算法整合後的效能。
利用本論文所提出的整合測試平台,我們實驗出一組最有效率且準確的人體偵測與追蹤系統,另外我們也提出了一些新技術,修改了現有的演算法使得整合後的系統更為快速及準確。
關鍵詞:前景偵測、人體偵測、人體追蹤、多重假設追蹤
Human detection and tracking is an important research in computer vision, and it has been extensively applied to the surveillance systems, the human-machine interfaces, behavior analysis, and so on.
Nowadays, there are many human detection and tracking systems. They will produce false detection while they are confronted with the changing environment, such as lighting changes. There is no any integrated platform to evaluate the performance of these different human detection and tracking systems.
We have proposed a framework that divides the human detection and tracking algorithms into four major components as follows:
(1) Image acquisition: get the image sequences with the image acquisition device;
(2) Foreground detection: use fast and correct methods to separate the object from the background;
(3) Human detection: find out the human position using the human characteristics from the result of foreground detection;
(4) Human tracking: find out the tracks of humans in the image sequences.
According to the foregoing taxonomy, we can define the requirements of these components and then analyze the advantages and drawbacks of various algorithms. Through experiments, it is possible to integrate an optimum system for human detection and tracking.
In order to allow flexible integration of different algorithms for these components, we use MATLAB to design a test platform of human detection and tracking system, which is divided into three major components: foreground detection, human detection and human tracking. Each component has a specific program module. These program modules can be replaced to test different algorithms. We have also proposed several public test data and measurement that allow fair comparison of different human detection and tracking systems after integrating different algorithms.
By using the proposed integrated test platform, we have designed an efficient and accurate human detection and tracking system. Moreover, some new methods are proposed to modify existing algorithms to further improve the performance.
Keyword:Foreground Detection、Human Detection、Human Tracking
致謝....................................................................................................................................... i
摘要...................................................................................................................................... ii
Abstract ............................................................................................................................... iii
圖目錄................................................................................................................................ vii
表目錄.................................................................................................................................. x
第一章:導論....................................................................................................................... 1
1.1 研究動機與目的......................................................................................................... 1
1.2 過去的研究................................................................................................................. 2
1.2.1 偵測出移動中物體的研究.................................................................................. 2
1.2.2 判斷是否為人體的研究...................................................................................... 2
1.2.3 人體追蹤的研究.................................................................................................. 3
1.3 系統簡介..................................................................................................................... 4
1.3.1 器材簡介.............................................................................................................. 4
1.3.2 實驗環境.............................................................................................................. 6
1.3.3 元件在系統中的功能.......................................................................................... 8
1.4 研究方法概述............................................................................................................. 8
1.5 論文大綱................................................................................................................... 10
第二章:前景偵測..............................................................................................................11
2.1 基本概念....................................................................................................................11
2.2 目前的前景偵測演算法的介紹............................................................................... 13
2.2.1 Background Subtraction..................................................................................... 13
2.2.2 Gaussian Model.................................................................................................. 13
2.2.3 Gaussian Mixture Model.................................................................................... 14
2.3 前景偵測演算法的實作........................................................................................... 17
2.3.1 Background Subtraction的實作......................................................................... 17
2.3.2 Gaussian Model的實作...................................................................................... 17
2.3.3 Gaussian Mixture Model的實作........................................................................ 19
2.4 結果討論................................................................................................................... 21
第三章:人體偵測............................................................................................................. 23
3.1 基本概念................................................................................................................... 23
3.2 目前的Human detection演算法的介紹................................................................... 24
3.2.1 Human by Head Top Candidates........................................................................ 24
3.2.2 Human Shape Classification .............................................................................. 25
3.2.3 Human by Implicit Shape Model ....................................................................... 28
3.3 人體偵測演算法的實作........................................................................................... 33
3.3.1 Human by Head Top Candidates的實作............................................................ 33
3.3.2 Human Shape Classification的實作.................................................................. 34
3.3.3 Human by Implicit Shape Model的實作........................................................... 37
3.4 結果討論................................................................................................................... 40
第四章:人體追蹤............................................................................................................. 41
4.1 基本概念................................................................................................................... 41
4.2 目前的Human Tracking演算法的介紹.................................................................... 41
4.2.1 Multiple Hypothesis Tracking............................................................................ 41
4.2.2 Dynamic Objects Tracking................................................................................. 48
4.3 人體追蹤演算法的實作........................................................................................... 50
4.3.1 Multiple Hypothesis Trackings的實作.............................................................. 50
4.3.2 Dynamic Objects Tracking的實作..................................................................... 52
4.4 結果討論................................................................................................................... 53
第五章:實驗結果討論..................................................................................................... 54
5.1 測試平台................................................................................................................... 54
5.2 前景偵測分析........................................................................................................... 57
5.3 Human Detection分析............................................................................................... 61
5.4 Human Tracking分析................................................................................................ 69
5.3.1 以人數分析....................................................................................................... 69
5.4.2 以訊框分析....................................................................................................... 71
5.4.3 以物體分析....................................................................................................... 73
第六章:結論與未來方向................................................................................................. 77
6.1 結論........................................................................................................................... 77
6.2 未來方向................................................................................................................... 77
參考文獻............................................................................................................................. 78
附錄1: 使用說明............................................................................................................... 80
附錄2 程式架構................................................................................................................. 88
[1] A. M. McIvor, “Background Subtraction Techniques,” Proc. of Image and Vision
Computing, 2000.
[2] S. Birchfield, “Elliptical Head Tracking using Intensity Gradients and Color
Histograms,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp.232-237,
1998.
[3] S. J. McKenna, S. Jabri, Z. Duric, H. Wechsler, and A. Rosenfeld, “Tracking
Groups of People,” Proc. of the Computer Vision and Image Understanding: CVIU.
[4] C. Stauffer and W. Grimson, “Adaptive Background Mixture Models for
Real-Time Tracking,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, 1999.
[5] J. Zhou and J. Hoang, “Real Time Robust Human Detection and Tracking
System,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2005.
[6] B. Leibe, A. Leonardis, and B. Schiele, “Combined Object Categorization and
Segmentation with an Implicit Shape Model,” ECCV’04 Workshop on Statistical
Learning in Computer Vision, May 2004.
[7] T. Zhao and R. Nevatia, “Tracking Multiple Humans in Complex Situations,”
IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 9, Sep. 2004.
[8] I. O. Sebe, S. You, and U. Neumann, “Globally Optimum Multiple Object
Tracking,” Acquisition, Tracking, and Pointing XIX. Edited by Masten, Michael K.;
Stockum, Larry A. Proceedings of the SPIE, vol. 5810, pp. 82-93, 2005.
[9] I. J. Cox and S.L. Hingorani, “An Efficient Implementation of Reid’s Multiple
Hypothesis Tracking Algorithm and Its Evaluation for The Purpose of Visual
Tracking,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, no.2, Feb.
1996.
[10] X. Zhou, R. Collins, T. Kanade, and P. Metes, “A Master-Slave System to Acquire
Biometric Imagery of Humans at Distance,” ACM International Workshop on Video
Surveillance, Nov. 2003.
[11] C. Ridder, O. Munkelt, and H. Kirchner, “Adaptive Background Estimation and
Foreground Detection using Kalman-Filter,” Proc. Int’l Conf. on Recent Advances in
Mechatronics, pp. 193−199, 1995.
[12] F. Bashir and F. Porikli, “Performance Evaluation of Object Detection and
Tracking Systems,” Proc. 9th IEEE International Workshop on PETS, June 2006.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top