Tutorial 7 :
ToF (Time of Flight) Depth Sensor Image Processing: from Principle to Applications

Presenters:

Seungkyu Lee, Samsung Advanced Institute of Technology
James DK Kim, Samsung Advanced Institute of Technology
Seong-Jin Kim, Samsung Advanced Institute of Technology
Hwasup Lim, Samsung Advanced Institute of Technology
Miles Hansard, INRIA Rhone-Alpes

Abstract

Recently, Time-of-Flight (ToF) depth camera widely has been studied and adapted in various research topics such as novel view synthesis, 3D scene modeling & reconstruction, gesture recognition, 3D map construction etc. Due to its unique characteristics of depth image, image processing algorithms such as noise modeling, filtering, segmentation, compression and feature detection with depth image are attractive research topics. Especially, for imaging applications like 3D camera rather than sensor applications like Kinect for Xbox, depth accuracy and image quality enhancement is a critical issue that has to be addressed. Motivated by recent explosive interest in depth image processing and applications in computer vision and computer graphics community, we organize this timely and unique tutorial to introduce basic principles, in-depth discussion on the cutting edge of technical issues, potential ideas, challenges. This tutorial will provide well organized presentations on ToF Depth sensor from architectural issues to state of the art image processing algorithms. More importantly, the tutorial will provide the depth image processing issues: from principle to applications as described in the following session. This tutorial will be a good starting point for new researchers in the literature who are considering depth image for their work. For the researchers who already have an experience in this field also can share their experiences/problems and join technical discussions on practical issues. Finally, we hope more researchers to submit their novel depth based image processing algorithms to the ICIP main conference in the future.

Outline

I - Introduction to recent academic & industrial achievements in ToF sensor research.

II - The principle of ToF Depth Sensor

III - Image processing algorithms for depth image quality improvement

IV - Color+Depth based 3D capturing and modeling

V - 3D Data Acquisition from Color+Depth

Biography of the presenters

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.

Prof. Albert J.P. Theuwissen received the Ph.D. degree in electrical engineering, Catholic University of Leuven, Belgium. In 1983, he joined the Micro Circuits Division of the Philips Research Laboratories in Eindhoven(the Netherlands) as a member of the scientific staff. In 1991 he became Department Head of the division Imaging Devices, including CCD as well as CMOS solid-state imaging activities. He was co-editor of the IEEE Transactions on Electron Devices special issues on Solid-State Image Sensors and of IEEE Micro special issue on Digital Imaging. He is part-time professor at the Delft University of Technology, Netherlands. He is founder of Harvest Imaging and focusing on training, coaching and teaching in the field of solid-state imaging technology. He is member of editorial board of the magazine 'Photonics Spectra', an IEEE Fellow and member of SPIE.

Prof. Radu Horaud received his Ph.D degree in control engineering, Grenoble Institute of Technology, France. He holds a position of director of research at INRIA Grenoble Rhone-Alpes, France. He is the leader of the PERCEPTION team. He is an area editor for the Computer Vision and Image Understanding (Elsevier), a member of the advisory board for the International Journal of Robotics Research (Sage), and a member of the editorial board for the International Journal of Computer Vision (Kluwer). His research interests cover computational vision, audio-visual scene analysis, machine learning, and robotics.

Dr. Miles Hansard received his Ph.D degree in computer vision, University College London, UK. He is a Research Engineer at INRIA Rhone-Alpes. His research interest is the representation of 3D scenes in human and computer vision.

Dr. Hwasup Lim received his Ph.D degree in Electrical Engineering from Penn State University, US. He is currently a principal research scientist, Advanced Media Lab., Samsung Advanced Institute of Technology. His research interests include 3D modeling & reconstruction, color/depth image processing and depth image based rendering (DIBR).

Dr. Seong-Jin Kim received his M.S. and Ph.D. degree in Electrical Engineering from Korea Advanced Institute of Science and Technology (KAIST), South Korea. He has been a pre-doctoral researcher at theUniversity of Minnesota in Minneapolis, US, where he carried out research on CMOS sensors especially for DNA detection bio chip applications. He is currently a principal research scientist, Advanced Media Lab., Samsung Advanced Institute of Technology. His research interests include CMOS imagers for 3-D image capturing, CMOS Bio sensing and VLSI circuit design.