Video indexing and summarization service for mobile users.

Description
Title: Video indexing and summarization service for mobile users.
Authors: Ahmed, Mohamed Ali.
Date: 2002
Abstract: Image processing, video analysis and computer vision techniques are presently developing rapidly because of the availability of acquisition, processing and editing tools which use current hardware and software systems. However, problems still remain in conveying this video data to the end users. Limiting factors are the resource capabilities in distributed architectures, and the features of the users' terminals. The efficient use of image processing, video indexing, and analysis techniques can provide solutions or alternatives. This thesis presents a new algorithm for video segmentation, indexing and key framing tasks. The algorithm is based on color histograms, and uses a binary penetration technique. Although a lot of work has been done in this area, most does not adequately consider the optimization of timing performance and processing storage. This is especially the case when the techniques are designed for use within run-time distributed environments. A main contribution of this thesis is to blend high performance and storage criteria with the need for effective results. The algorithm uses the temporal heuristic characteristics of the visual information in a video stream. It considers the issues of detecting false cuts and missing true cuts due to the movement of the camera, the optical flow of large objects, or both. We discuss the merits of the new algorithm compared to the existing one, supporting the discussion both with results from experiments and from the implementation of our application. We also propose a video event modeling mechanism to intelligently parse, analyze and extract the significant content information from digital video libraries or video mails. This also requires an adaptation stage in order to react to the status, policies and configuration of the end user environment. In order to build robust and extendable systems capable of dealing with future new devices that may have new specifications, we consider devices by their characteristics rather than their type (PDA, PC, cellular phone, etc). We designed and developed a video key framing and summarization service within an overall agent-based architecture that negotiates the different factors autonomously and dynamically at run-time in order to provide the service to the user in an efficient and secure manner.
URL: http://hdl.handle.net/10393/6358
http://dx.doi.org/10.20381/ruor-11229
CollectionTh├Ęses, 1910 - 2010 // Theses, 1910 - 2010
Files
NQ76423.PDF5.29 MBAdobe PDFOpen