For the research in the book the key question is how to encode the spatial and temporal information in video for its efficient retrieval. Novel algorithms areproposed for matching videos and are compared them with state-of-the-art.These algorithms take into account image objects and their spatial relationships, and temporal information with in a video which correlates withits semantic class. Also, the algorithms perform hierarchical matching starting with frame, and shot level before overall video level similarity can becomputed. The approach, then, is exhaustively tested on the basis ofprecision and recall measures on a large number of queries and use the areaunder the average precision recall curve to compare the methods with those inthe literature. As a part of this book an international video benchmark Minerva was proposed on which the results have been discussed.
任伟的《时空视频检索(英文版)》重点挖掘了视频的时空关系,探索了利用机器学习的方法进行视频切割、语义分类。本书分七章,阐明了图像的各种特性,论述了视频的特征,系统介绍了视频的时空逻辑关系、视频的统计分析方法,研究了如何捕捉视频的时空特性,如何利用人工智能神经网络进行视频切割,如何训练计算机“学会”用人类的思维进行视频语义分类、检索。各章节撰写排列体现了从简到繁、由浅入深、从理论到实际、从技术到系统的特点。
《时空视频检索(英文版)》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、机器视觉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。
Chapter Ⅰ Introduction
1.1 Motivation
1.2 Proposed Solution
1.3 Structure of Book
Chapter Ⅱ Approaches to Video Retrieval
2.1 Introduction
2.2 Video Structure and Properties
2.3 Query
2.4 Similarity Metrics
2.5 Performance Evaluation Metrics
2.6 Systems
Chapter Ⅲ Spatio-temporal Image and Video Analysis
3.1 Spatio-temporal Information for Video Retrieval
3.2 Spatial Information Modelling in Multimedia Retrieval .
3.3 Temporal Model
3.4 Spatio-temporal Information Fusion
Chapter Ⅳ Video Spatio-temporal Analysis and Retrieval (VSTAR) :A New Model
4.1 VSTAR Model Components
4.2 Spatial Image Analysis
4.3 A Model for the Temporal Analysis of Image Sequences
4.4 Video Representation.Indexing.and Retrieval Usinz VSTAR
4.5 Conclusions
Chapter Ⅴ Two Comparison Baseline Models for Video Retrieval
5.1 Baseline Models
5.2 Adjeroh et al.(1999) Sequences Matching——Video Retrieval Model
5.3 Kim and Park (2002a) data set matching——Video Retrieval Model
Chapter Ⅵ Spatio-temporal Video Retrieval——Experiments and Results
6.1 Purpose of Experiments
6.2 Data Description
6.3 Spatial and Temporal Feature Extraction
6.4 Video Retrieval Models: Procedure for Parameter Optimisation
6.5 Video Retrieval Models:Resuhs on Parameter Optimisation
6.6 Comparison of Four Models
6.7 Model Robustness (Noise)
6.8 Computational Complexity
6.9 Conclusions
Chapter Ⅶ Conclusions
7.1 Reflections on the book as a whole
7.2 Support for book statement
7.3 Limitations of the spatio-temporal knowledge-based model
7.4 Directions for further work
Appendix A Compressed vs.Uncompressed Video
Appendix B Video Annotation
B.1 Semi-automatic Video Annotation System
B.2 Automatic Annotation by Object Tracking
Appendix C Object-pair Correlation Matrix
Appendix D Key-frames Extraction
D.1 Feature-based Representation and Similarity Measures .
D.2 Threshold Selection
Appendix E Audio Features
Reference