基于特征学习的视频行人检测
发布时间:2021-04-11 10:18
在论文中实验结果表明了我们的贡献,我们的方法是基于提高训练集候选框的对齐质量和完美多帧检测器,这两种方法通过手动剔除Caltech数据集的训练标签,并对剩余的训练样本进行测试。同时我们研究了用于行人检测的卷积神经网络,并描述了影响它们性能的因素。为了说明背景/前景的区别,我们研究了用于行人检测的卷积神经网络,并描述了影响它们性能的因素。我们详细研究并报告了在Caltech数据集的最好的表现性能,并提出了一套新的经过筛选的训练和测试样本。行人检测是一个众所周知的计算机视觉研究领域的子课题,它的应用十分广泛,虽然已经被提出很多年,仍然是一个研究的重点问题。我们对比了现在的最先进的方法和“完美的多帧检测器和候选框的对齐”的不同。受行人检测最新发展的启发,我们创建了一个行人的检测的基准(在Caltech数据集上)。不仅可以实现定位,也可以得到前景和背景的误差。同时为了说明定位误差,我们研究了训练标注噪声对检测器性能的影响,并表明我们可以在少部分经过筛选的训练数据的基础上进行改进。尽管针对行人检测的研究已经有了很深入的研究,但是关于行人检测的研究还有很大的发展空间,还有很多可以继续深入研究的方面...
【文章来源】:北京交通大学北京市 211工程院校 教育部直属院校
【文章页数】:63 页
【学位级别】:硕士
【文章目录】:
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
参考文献 References
附录A Appendix A
索引 INDEX
作者简历及攻读硕士/博士学位期间取得的研究成果 AUTHOR PROFILE AND RESEARCH ACHIEVEMENTS OBTAINEDDURING THE STUDY FOR A MASTER'S/DOCTORAL DEGREE
学位论文数据集 DATASET FOR THE MASTER'S THESIS
本文编号:3131075
【文章来源】:北京交通大学北京市 211工程院校 教育部直属院校
【文章页数】:63 页
【学位级别】:硕士
【文章目录】:
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
参考文献 References
附录A Appendix A
索引 INDEX
作者简历及攻读硕士/博士学位期间取得的研究成果 AUTHOR PROFILE AND RESEARCH ACHIEVEMENTS OBTAINEDDURING THE STUDY FOR A MASTER'S/DOCTORAL DEGREE
学位论文数据集 DATASET FOR THE MASTER'S THESIS
本文编号:3131075
本文链接:https://www.wllwen.com/kejilunwen/zidonghuakongzhilunwen/3131075.html