Title: Color in Image/Video Processing Applications instructors: Theo Gevers and Joost van de Weijer The increasing capacity of digital video cameras and connectivity of the world provides us with rapidly growing digital image/video archives. As visual information becomes more and more available in colour format, there is an increasing demand for the use and understanding of colour information. This tutorial provides an overview of recent developments of color usage in image and video processing applications. The aim is to provide attendees with basics on color concepts and a practical set of techniques which allows to effectively using color information in a number of applications. We will show that color information is a powerful tool for image and video processing and understanding. The course is divided into two parts. First, the fundamentals of color information will be outlined, such as color representation and reflection models, photometric invariance, color constancy, and color saliency. This will also include a discussion on human color vision and an overview of appropriate color spaces. The second part of the course will focus on the practical usage of color in image and video processing. We will show examples from a number of relevant application areas, such as edge detection, image segmentation, motion detection and object tracking, object recognition, image and video retrieval, and scene classification. Among others, the overview will include Pascal Challenge VOC 2008 winning object classification results, for which color information played an important role. Tentative List of TopicsI. Fundamentals:
II. Applications:
SLIDES: A pdf-version of the slides can be downloaded for part1, and part2. In case you want to use the powerpoint slides, contact me by email (joost AT cvc DOT uab DOT es). Relevant color research related to the research of the organizers:
|