当前位置:首页 > 工业技术
时空视频检索  英文
时空视频检索  英文

时空视频检索 英文PDF电子书下载

工业技术

  • 电子书积分:10 积分如何计算积分?
  • 作 者:任伟著
  • 出 版 社:哈尔滨:哈尔滨工程大学出版社
  • 出版年份:2010
  • ISBN:9787811336115
  • 页数:212 页
图书介绍:本书重点探索了利用时空关系和机器学习的方法进行视频语义分类,首先阐明图象的各种特性,接着论述视频的特性,系统介绍了视频的时空逻辑关系、视频的统计特性的分析,研究了如何捕捉视频的特性、如何利用神经网络进行视频切割、如何训练计算机“学会”人类的思维进行视频语义分类。本书可以作为高等学校信号与图像处理、计算机科学、机器学习、人工智能等领域的研究生教材和参考书,也可以作为在这些领域从事相关工作的高级科学技术人员的参考书。
《时空视频检索 英文》目录

Chapter Ⅰ Introduction 1

1.1 Motivation 1

1.2 Proposed Solution 5

1.3 Structure of Book 8

Chapter Ⅱ Approaches to Video Retrieval 10

2.1 Introduction 10

2.2 Video Structure and Properties 11

2.3 Query 34

2.4 Similarity Metrics 38

2.5 Performance Evaluation Metrics 41

2.6 Systems 43

Chapter Ⅲ Spatio-temporal Image and Video Analysis 47

3.1 Spatio-temporal Information for Video Retrieval 48

3.2 Spatial Information Modelling in Multimedia Retrieval 50

3.3 Temporal Model 67

3.4 Spatio-temporal Information Fusion 76

Chapter Ⅳ Video Spatio-temporal Analysis and Retrieval(VSTAR):A New Model 89

4.1 VSTAR Model Components 92

4.2 Spatial Image Analysis 94

4.3 A Model for the Temporal Analysis of Image Sequences 100

4.4 Video Representation,Indexing,and Retrieval Using VSTAR 109

4.5 Conclusions 129

Chapter Ⅴ Two Comparison Baseline Models for Video Retrieval 131

5.1 Baseline Models 131

5.2 Adjeroh et al.(1999)Sequences Matching—Video Retrieval Model 133

5.3 Kim and Park(2002a)data set matching—Video Retrieval Model 135

Chapter Ⅵ Spatio-temporal Video Retrieval—Experiments and Results 137

6.1 Purpose of Experiments 137

6.2 Data Description 138

6.3 Spatial and Temporal Feature Extraction 142

6.4 Video Retrieval Models:Procedure for Parameter Optimisation 146

6.5 Video Retrieval Models:Results on Parameter Optimisation 147

6.6 Comparison of Four Models 149

6.7 Model Robustness(Noise) 154

6.8 Computational Complexity 156

6.9 Conclusions 159

Chapter Ⅶ Conclusions 160

7.1 Reflections on the book as a whole 160

7.2 Support for book statement 161

7.3 Limitations of the spatio-temporal knowledge-based model 161

7.4 Directions for further work 162

Appendix A Compressed vs.Uncompressed Video 163

Appendix B Video Annotation 168

B.1 Semi-automatic Video Annotation System 168

B.2 Automatic Annotation by Object Tracking 169

Appendix C Object-pair Correlation Matrix 173

Appendix D Key-frames Extraction 175

D.1 Feature-based Representation and Similarity Measures 175

D.2 Threshold Selection 176

Appendix E Audio Features 177

Reference 180

返回顶部