|Real-Time Image and Video Processing: From Research to Reality
Prof. Nasser Kehtarnavaz, Dept. of Electrical Engineering, University of Texas at Dallas, USA
Date: June 26, 2007
Time: 6:00 - 9:30 PM
This tutorial provides a much-needed treatment on the implementation aspects of real-time image and video processing systems. It brings together in one place the guidelines, strategies and methodologies for taking an image or video-processing algorithm from a research environment to a working, real-time implementation on a resource constrained hardware platform. Carefully selected, relevant examples from the literature will be presented to illustrate the concepts. The participants will be introduced to a wide variety of strategies and tools, which they can then employ in designing a real-time image or video processing system of interest.
- Introductory concepts to real-time image and video processing
- Algorithmic approaches (algorithm simplification strategies)
- Hardware platforms (hardware architectures for image and video processing)
- Software tools (software optimization strategies)
The tutorial is based on a new lecture series book, authored by the presenter, entitled Real-Time Image and Video Processing: From Research to Reality. Its content consists of the following five parts:
- Understand the issues involved in the process of transitioning an algorithm from a research development environment to a real-time constrained hardware platform.
- Understand the concept of real-time as it pertains to image or video processing systems.
- Appreciate the diversity of operations in an image/video processing system.
- Identify and apply proven algorithmic simplification strategies to help streamline an image/video-processing algorithm to meet real-time constraints in an application of interest.
- Select a hardware platform for the real-time implementation, which best suits the types of image/video processing operations in a given application.
- Apply proven memory and software optimization strategies to maximize performance of the chosen hardware platform for real-time implementation.
- Engineers and scientists interested in taking an image or video processing algorithm from a development environment to an actual real-time implementation on a resource constrained hardware platform
- Those who wish to pursue a career in image or video processing
- Designers of image/video processing systems and products
- Basic knowledge of image processing
- Background in electrical engineering or computer science
Biography of Instructor
Nasser Kehtarnavaz received the PhD degree in Electrical and Computer Engineering from Rice University in 1987. He is currently a Professor of Electrical Engineering at the University of Texas at Dallas (UTD). His research interests include signal and image processing, real-time image processing, pattern recognition, and biomedical image analysis. He has authored or co-authored 5 books and more than 140 journal and conference papers in these areas. He is currently managing a Texas Instruments sponsored research program at UTD involving the development and implementation of real-time image processing algorithms for digital and cell-phone cameras. Dr. Kehtarnavaz is a Fellow of SPIE, Chair of the Dallas Chapter of the IEEE Signal Processing Society and Editor-in-Chief of Journal of Real-Time Image Processing.