基于特征學(xué)習(xí)的視頻行人檢測
發(fā)布時間:2021-04-11 10:18
在論文中實驗結(jié)果表明了我們的貢獻,我們的方法是基于提高訓(xùn)練集候選框的對齊質(zhì)量和完美多幀檢測器,這兩種方法通過手動剔除Caltech數(shù)據(jù)集的訓(xùn)練標(biāo)簽,并對剩余的訓(xùn)練樣本進行測試。同時我們研究了用于行人檢測的卷積神經(jīng)網(wǎng)絡(luò),并描述了影響它們性能的因素。為了說明背景/前景的區(qū)別,我們研究了用于行人檢測的卷積神經(jīng)網(wǎng)絡(luò),并描述了影響它們性能的因素。我們詳細(xì)研究并報告了在Caltech數(shù)據(jù)集的最好的表現(xiàn)性能,并提出了一套新的經(jīng)過篩選的訓(xùn)練和測試樣本。行人檢測是一個眾所周知的計算機視覺研究領(lǐng)域的子課題,它的應(yīng)用十分廣泛,雖然已經(jīng)被提出很多年,仍然是一個研究的重點問題。我們對比了現(xiàn)在的最先進的方法和“完美的多幀檢測器和候選框的對齊”的不同。受行人檢測最新發(fā)展的啟發(fā),我們創(chuàng)建了一個行人的檢測的基準(zhǔn)(在Caltech數(shù)據(jù)集上)。不僅可以實現(xiàn)定位,也可以得到前景和背景的誤差。同時為了說明定位誤差,我們研究了訓(xùn)練標(biāo)注噪聲對檢測器性能的影響,并表明我們可以在少部分經(jīng)過篩選的訓(xùn)練數(shù)據(jù)的基礎(chǔ)上進行改進。盡管針對行人檢測的研究已經(jīng)有了很深入的研究,但是關(guān)于行人檢測的研究還有很大的發(fā)展空間,還有很多可以繼續(xù)深入研究的方面...
【文章來源】:北京交通大學(xué)北京市 211工程院校 教育部直屬院校
【文章頁數(shù)】:63 頁
【學(xué)位級別】:碩士
【文章目錄】:
Acknowledgement
摘要
ABSTRACT
序言 Preface
Abbreviations
1 Introduction
1.1 Problem
1.2 Objectives and Problem Statement
1.3 Machine Learning and Convolutional Neural Network
1.4 Structure of Thesis
2 Related Work
2.1 Classical Features
2.2 HOG & LUV Features
2.3 Convolutional Neural Networks (CNN)
2.4 Fast Feature Pyramids
3 Methodology
3.1 Convolutional Neural Network
3.1.1 layer Typess
3.2 Training CNN
3.2.1 Dropout
3.2.2 Random Dropout
3.2.3 Rectified Linear unit Layer
3.2.4 Positive and Negative Data Ratio
3.3 Proposed Network
3.3.1 Version One
3.3.2 Version Two
3.3.3 Version Three
3.3.4 Version Four
3.3.5 Depth
3.4 Data
3.4.1 Data Collection
3.4.2 Dataset Augmentation
3.4.3 Data Usage
3.5 The First Network Proposal
3.5.1 12-Network Structures
3.5.2 16-Network Structures
4 Results
4.1 12-Network Results
4.1.1 12-Network Performance
4.1.2 12-Network Complexity
4.2 16-Network Results
4.2.1 16-Network Performance
4.2.2 16-Network Complexity
4.2.3 16-network Discussion
4.3 First Network Comparison
4.4 Comparing Against State-of-the-Art
4.5 State-of-the-Art Discussion
5 Conclusion
5.1 Conclusion
5.2 Future Work
參考文獻 References
附錄A Appendix A
索引 INDEX
作者簡歷及攻讀碩士/博士學(xué)位期間取得的研究成果 AUTHOR PROFILE AND RESEARCH ACHIEVEMENTS OBTAINEDDURING THE STUDY FOR A MASTER'S/DOCTORAL DEGREE
學(xué)位論文數(shù)據(jù)集 DATASET FOR THE MASTER'S THESIS
本文編號:3131075
【文章來源】:北京交通大學(xué)北京市 211工程院校 教育部直屬院校
【文章頁數(shù)】:63 頁
【學(xué)位級別】:碩士
【文章目錄】:
Acknowledgement
摘要
ABSTRACT
序言 Preface
Abbreviations
1 Introduction
1.1 Problem
1.2 Objectives and Problem Statement
1.3 Machine Learning and Convolutional Neural Network
1.4 Structure of Thesis
2 Related Work
2.1 Classical Features
2.2 HOG & LUV Features
2.3 Convolutional Neural Networks (CNN)
2.4 Fast Feature Pyramids
3 Methodology
3.1 Convolutional Neural Network
3.1.1 layer Typess
3.2 Training CNN
3.2.1 Dropout
3.2.2 Random Dropout
3.2.3 Rectified Linear unit Layer
3.2.4 Positive and Negative Data Ratio
3.3 Proposed Network
3.3.1 Version One
3.3.2 Version Two
3.3.3 Version Three
3.3.4 Version Four
3.3.5 Depth
3.4 Data
3.4.1 Data Collection
3.4.2 Dataset Augmentation
3.4.3 Data Usage
3.5 The First Network Proposal
3.5.1 12-Network Structures
3.5.2 16-Network Structures
4 Results
4.1 12-Network Results
4.1.1 12-Network Performance
4.1.2 12-Network Complexity
4.2 16-Network Results
4.2.1 16-Network Performance
4.2.2 16-Network Complexity
4.2.3 16-network Discussion
4.3 First Network Comparison
4.4 Comparing Against State-of-the-Art
4.5 State-of-the-Art Discussion
5 Conclusion
5.1 Conclusion
5.2 Future Work
參考文獻 References
附錄A Appendix A
索引 INDEX
作者簡歷及攻讀碩士/博士學(xué)位期間取得的研究成果 AUTHOR PROFILE AND RESEARCH ACHIEVEMENTS OBTAINEDDURING THE STUDY FOR A MASTER'S/DOCTORAL DEGREE
學(xué)位論文數(shù)據(jù)集 DATASET FOR THE MASTER'S THESIS
本文編號:3131075
本文鏈接:http://sikaile.net/kejilunwen/zidonghuakongzhilunwen/3131075.html
最近更新
教材專著