Abstract
-
The prevalence of affordable RGB-D cameras, such as
Microsoft’s Kinect and ASUS’s Xtion Pro Live, is driving a revolution
of the landscape of computer vision and its related researches. The
pixel-level depth and color information provided by an RGB-D
camera not only enables robust vision applications but also opens
up new research problems and opportunities across a wide range
of areas including 3D perception, robotics, human machine interactions,
intelligent surveillance, and health care. With the depth
information, many intractable computer vision problems are
becoming possible, but they are by no means solved. New visual
representations and paradigms are needed to effectively leverage
the new sensors and develop robust vision systems. Since the first
release of Microsoft Kinect sensors in November 2010, we have
witnessed a rapid growth of research in visual understanding and
applications with RBG-D cameras. This special issue brings together
the most recent advances in this direction. There are 19 high
quality papers covering various aspects of RGB-D camera based visual
understanding including human action recognition, pose and
gait recognition, object recognition, segmentation, tracking, sensor
fusion, and novel applications. From these papers, the readers will
obtain an excellent understanding on the state of the art of this
new research area.