Time-of-Flight Depth Image Enhancement
Seungkyu Lee, Hyunjung Shim, Ouk Choi
Abstract
Depth cameras, e.g., time-of-flight and structured-light sensors, have become increasingly popular for the last couple of years. These devices are able to provide depth images at 30 frames per second, at a resolution ranging between 0.03 and 0.3 million pixels, and at a very affordable price. For the last two decades, researchers have been concerned with the processing and understanding of visual information available with one or several 2D images and videos. Meanwhile, recent developments in 3D sensor technologies brought us direct 3-dimensional information accompanied by unique noise and quality characteristics. While depth cameras are very attractiveve because they provide 3D information instantaneously, they are based on active lighting, e.g., time of flight or structured light. A direct consequence of these active sensing technologies is that 3D cameras are limited in range, have low resolution and unique noises in the presence of scattering or non-Lambertian surfaces. Depth image processing algorithms such as noise modeling, filtering, removing range ambiguity, segmentation, compression and feature detection are attractive research topics to enhance the quality of depth images for extensive applications. This tutorial will provide well organized presentations on ToF Depth image processing issues and algorithms.
Speakers
Seungkyu Lee
Dr. Seungkyu Lee received his Ph.D degree in Computer Science & Engineering from Penn State University, US. He has been a research engineer in Korea Broadcasting System Technical Research Institute where he carried out research on HD image processing, MPEG4-AVC and the standardization of Terrestrial-Digital Mobile Broadcasting. He is currently a principal research scientist, Advanced Media Lab., Samsung Advanced Institute of Technology. His research interests include color/depth image processing, symmetry-based computer vision and 3D modeling & reconstruction.
Hyunjung Shim
Dr. Hyunjung Shim is a research staff member at the Samsung Advanced Institute of Technology, Samsung Electronics, since 2008. She received her PhD and MS degrees in Electrical and Computer Engineering from Carnegie Mellon University in 2008. Her research interests include 3D modeling and reconstruction, inverse lighting and reflectometry, face modeling, image-based relighting and rendering, light field capturing and processing algorithms, and color enhancement algorithms. Most recently, her research activities focus on depth image-based scene understanding and analysis.
Ouk Choi
Dr. Ouk Choi is a research scientist at Samsung Advanced Institute of Technology (SAIT), Republic of Korea. His research interests include computer vision, 3D image processing, and medical imaging. During his Ph.D. and M.Sc. studies in KAIST, he made contributions in robotics and computer vision problems such as image matching, segmentation, and registration; object recognition; and visual navigation. In 2009, he joined Samsung Advanced Institute of Technology and carried out extensive research projects ranging from ToF sensing architecture to depth image processing, and especially has devoted on phase unwrapping, depth image super-resolution and noise reduction.