Despite the natural synergy among video processing, video understanding, and human-computer interaction, research on computer vision such as video surveillance, audiovisual information compression such as video coding, and the human visual system such as perceptual quality evaluation, have been carried out mostly in isolation. Computer vision researchers have so far concentrated on various analysis techniques without giving much attention to the quality of the images that are directly used from the image capturing devices in raw formats. Video coding researchers, on the other hand, have concentrated on extreme compression in the face of limited communication bandwidth without caring much about the end users' receiving somehow distorted lossy images. Perceptual quality researchers have concentrated on evaluating the end product of images without providing enough human perceived feedback for image processing and image understanding. For high performance, we need to integrate the knowledge from computer vision, video coding technology, and human-computer interaction. This need arises due to the recent expansion of new technologies such as the burgeoning Internet, large deployment of close-circuits security cameras for surveillance, availability of mobile devices and wireless communication, acceptability of home entertainment, innovation of human-mind-reader eye tracking technology, and the popularity of the internet video service YouTube.This book will cover recent research on single view, multi-view, and free viewpoint video coding using computer vision and human-computer interactive feedback to gain better subjective and objective quality. The book concludes with a discussion of future trend of coding and compression.
|Place of Publication||United States|
|Publisher||John Wiley & Sons|
|Number of pages||400|
|Publication status||Accepted/In press - 06 Mar 2020|