图书介绍
时空视频检索 英文PDF|Epub|txt|kindle电子书版本网盘下载
![时空视频检索 英文](https://www.shukui.net/cover/15/30257883.jpg)
- 任伟著 著
- 出版社: 哈尔滨:哈尔滨工程大学出版社
- ISBN:9787811336115
- 出版时间:2010
- 标注页数:212页
- 文件大小:14MB
- 文件页数:221页
- 主题词:数字图象处理-英文
PDF下载
下载说明
时空视频检索 英文PDF格式电子书版下载
下载的文件为RAR压缩包。需要使用解压软件进行解压得到PDF格式图书。建议使用BT下载工具Free Download Manager进行下载,简称FDM(免费,没有广告,支持多平台)。本站资源全部打包为BT种子。所以需要使用专业的BT下载软件进行下载。如BitComet qBittorrent uTorrent等BT下载工具。迅雷目前由于本站不是热门资源。不推荐使用!后期资源热门了。安装了迅雷也可以迅雷进行下载!
(文件页数 要大于 标注页数,上中下等多册电子书除外)
注意:本站所有压缩包均有解压码: 点击下载压缩包解压工具
图书目录
Chapter Ⅰ Introduction1
1.1 Motivation1
1.2 Proposed Solution5
1.3 Structure of Book8
Chapter Ⅱ Approaches to Video Retrieval10
2.1 Introduction10
2.2 Video Structure and Properties11
2.3 Query34
2.4 Similarity Metrics38
2.5 Performance Evaluation Metrics41
2.6 Systems43
Chapter Ⅲ Spatio-temporal Image and Video Analysis47
3.1 Spatio-temporal Information for Video Retrieval48
3.2 Spatial Information Modelling in Multimedia Retrieval50
3.3 Temporal Model67
3.4 Spatio-temporal Information Fusion76
Chapter Ⅳ Video Spatio-temporal Analysis and Retrieval(VSTAR):A New Model89
4.1 VSTAR Model Components92
4.2 Spatial Image Analysis94
4.3 A Model for the Temporal Analysis of Image Sequences100
4.4 Video Representation,Indexing,and Retrieval Using VSTAR109
4.5 Conclusions129
Chapter Ⅴ Two Comparison Baseline Models for Video Retrieval131
5.1 Baseline Models131
5.2 Adjeroh et al.(1999)Sequences Matching—Video Retrieval Model133
5.3 Kim and Park(2002a)data set matching—Video Retrieval Model135
Chapter Ⅵ Spatio-temporal Video Retrieval—Experiments and Results137
6.1 Purpose of Experiments137
6.2 Data Description138
6.3 Spatial and Temporal Feature Extraction142
6.4 Video Retrieval Models:Procedure for Parameter Optimisation146
6.5 Video Retrieval Models:Results on Parameter Optimisation147
6.6 Comparison of Four Models149
6.7 Model Robustness(Noise)154
6.8 Computational Complexity156
6.9 Conclusions159
Chapter Ⅶ Conclusions160
7.1 Reflections on the book as a whole160
7.2 Support for book statement161
7.3 Limitations of the spatio-temporal knowledge-based model161
7.4 Directions for further work162
Appendix A Compressed vs.Uncompressed Video163
Appendix B Video Annotation168
B.1 Semi-automatic Video Annotation System168
B.2 Automatic Annotation by Object Tracking169
Appendix C Object-pair Correlation Matrix173
Appendix D Key-frames Extraction175
D.1 Feature-based Representation and Similarity Measures175
D.2 Threshold Selection176
Appendix E Audio Features177
Reference180