Content based video indexing and retrieval

  title={Content based video indexing and retrieval},
  author={Stephen W. Smoliar and HongJiang Zhang},
  journal={IEEE MultiMedia},
Video management tools and techniques are based on pixels rather than perceived content. Thus, state-of-the-art video editing systems can easily manipulate such things as time codes and image frames, but they cannot "know," for example, what a basketball is. Our research addresses four areas of content-based video management.<<ETX>> 

Figures from this paper

Review of Image and Video Indexing Techniques
A critical survey of existing literature on content-based indexing techniques is provided to point out the relative advantages and disadvantages of each approach.
Content-based structuring of video information
  • M. Shibata, Yeun-Bae Kim
  • Computer Science
    Proceedings of the Third IEEE International Conference on Multimedia Computing and Systems
  • 1996
A component-based scene description model for computerizing linguistic descriptions written by the directors and a method for extracting a content-based hierarchical structure for video sequences based on this model are proposed.
A content based retrieval video system for educational environments
The main focus in any video information system is to develop a database management system with a friendly content-based retrieval of the digital video information.
An Overview of Video Abstraction Techniques
This paper focuses on video abstraction, one of the most important topics, which helps to enable a quick browsing of a large collection of video data and to achieve efficient content access and representation.
Digital Video Revisited
A description of a system which can extract video object based representation of video sequences and builds up a video objectbased description of the content of the video collection is presented.
Automatic video segmentation and indexing
Experimental results using a variety of videos selected in the corpus of the French Audiovisual National Institute are presented to demonstrate the effectiveness of performing shot detection, the content characterization of shots and the scene constitution.
Non-sequential video content representation using temporal variation of feature vectors
  • A. Doulamis, N. Doulamis, S. Kollias
  • Computer Science
    2000 Digest of Technical Papers. International Conference on Consumer Electronics. Nineteenth in the Series (Cat. No.00CH37102)
  • 2000
An efficient non-sequential representation of the video content is presented based on the temporal variation of the extracted feature trajectory that is very fast and accurate and can be applied to any generic video stream.
This paper has tried to present a novel method which will be very efficient to work on large video database and the multiple contents of video will lead to accurate result.
Content based video retrieval
This work conjectured that a technique which employs multiple features for indexing and retrieval would be more effective in the discrimination and search tasks of videos.
Content-based indexing of images and video.
  • A. Pentland
  • Computer Science
    Philosophical transactions of the Royal Society of London. Series B, Biological sciences
  • 1997
By representing image content using probabilistic models of an object's appearance the authors can obtain semantics-preserving compression of the image data and allow rapid computer searches of even large image databases.


Video indexing using motion vectors
A video indexing method that uses motion vectors to 'identify' video sequences and corresponding icons is presented, based on the identification of discrete cut points and camera operations made possible by analyzing motion vectors.
Developing power tools for video indexing and retrieval
The Video Classification Project is presented, an effort toward automating content-based video indexing and retrieval, at the Institute of Systems Science of the National University of Singapore.
Knowledge-guided parsing in video databases
The steps in the insertion process, and some of the tools the authors have developed to semi-automatically segment the data into domain objects which are meaningful to the user are discussed.
Automatic parsing of news video
Approaches to locating and identifying frame structure models based on temporal and spatial structure of news video data, along with algorithms to apply these models in parsing news video, have been developed and are presented in detail in this paper.
Salient video stills: content and context preserved
A new class of images called salient stills is demonstrated and a software development platform for their creation is discussed and a by-product of the salient still process is a structured representation of moving image data.
VideoMAP and VideoSpaceIcon: tools for anatomizing video content
The basic concept of VideoMAP and VideoSpaceIcon, which allow the user's creativity to directly interact with the essential features of each video by offering spatial and temporal clues, are introduced.
A magnifier tool for video data
We describe an interface prototype, the Hierarchical Video Magnifier, which allows users to work with a video source at fine-levels of detail while maintaining an awareness of temporal context. The
QBIC project: querying images by content, using color, texture, and shape
The main algorithms for color texture, shape and sketch query that are presented, show example query results, and discuss future directions are presented.
Introduction to Modern Information Retrieval
Reading is a need and a hobby at once and this condition is the on that will make you feel that you must read.
Structure out of sound
Sound is the predominant communication modality in the natural world, yet most current computers have no sense of sound whatsoever. They only occasionally "bleep," and are, in effect, stone-deaf.