Date: Nov. 6th, 09:00 am ~ 18:20 pm
Location: Daejeon convention center, Daejeon, Korea

(09:00 - 09:15) Opening Remarks 
(09:15 - 10:45) Session I - Depth Fusion & Reconstruction
"Exploring High-Level Plane Primitives for Indoor 3D Reconstruction with a Hand-held RGB-D Camera" 
    Mingsong Dou (UNC-CH), Li Guan (GE Global Research Center), 
    Jan-Michael Frahm (UNC), Henry Fuchs (UNC-CH)
"A Fusion Framework of Stereo Vision and Kinect for High-Quality Dense Depth Maps"
    Yucheng Wang (BIT), Yunde Jia (BIT)
"Robust Fall Detection by Combining 3D Data and Fuzzy Logic" 
    Rainer Planinc (Vienna University of Technology), 
    Martin Kampel (Vienna University of Technology)

(10:45 - 11:00) Coffee Break
(11:00 - 12:30) Session II - Human Activity Recognition
"KinectAvatar: Fully Automatic Body Capture Using a Single Kinect" 
    Yan Cui (DFKI), Will Chang (University of California, San Diego), 
    Tobias Nöll (DFKI), Didier Stricker (DFKI)
"Essential Body-Joint and Atomic Action Detection For Human Activity Recognition Using Longest Common Subsequence Algorithm" 
    Sou-Young Jin (KAIST), Ho-Jin Choi (KAIST)
"Exploiting Depth and Intensity Information for Head Pose Estimation with Random Forests and Tensor Models" 
    Sertan Kaymak (Queen Mary University of London), 
    Ioannis Patras (Queen Mary University of London) 
(12:30 - 14:00) Lunch Break
(14:00 - 14:50) Invited Talk & Demonstration

"ToF 3D Camera", Byongmin Kang (SAIT)
    :A Full-HD CMOS Image Sensor with Time-multiplexed 2D/3D Image Acquisition

: Time-of-Flight (ToF) depth cameras have received great interests from the computer vision community, expanding their applications to 3d modeling, user interaction, and object recognition. To acquire a color image as well as a depth image, an additional color camera is necessary, and the calibration between the cameras is required. This calibration process is non-trivial in the presence of systematic/random depth errors, and accurate alignment between the color and depth images is not guaranteed due to differences in viewpoints and spatial resolutions of the cameras.
In this talk, we present a new camera system that is able to acquire both color and depth images using only one lens and one sensor. We also demonstrate a prototype of our system, and explain the details of the system.

(14:50 - 15:00) Short Break 
(15:00 - 17:00) Session III - Object Shape Extraction & Matching
"Dynamic Hand Shape Manifold Embedding and Tracking from Depth Map" 
    Chan-Su Lee (Yeungnam University), Sung Yong Chun (Yeungnam University),
    Shin Won Park (Yeungnam University)
"View-Invariant Object Detection by Matching 3D Contours" 
    Tianyang Ma (Temple University), Meng Yi (Temple University), 
    Longin Jan Latecki (Temple University)
"Human Detection with Occlusion Handling by Over-segmentation and Clustering on Foreground Regions" 
    Li Wang (Nanyang Technological Univ.), Kap Luk Chan (Nanyang Technological Univ.), Gang Wang (Nanyang Technological Univ.)
"Spin Image Revisited: Fast Candidate Selection using Outlier Forest Search" 
    Young-Woon Cha (KIST), Hwasup Lim (KIST), Seong-Oh Lee (KIST)
    Hyoung-Gon Kim (KIST), Sang Chul Ahn (KIST)
(17:00 - 17:15) Coffee Break
(17:15 - 18:15) Session IV - Depth-based Applications
"Depth and Color Fusion for Better Corner Detection" 
    Nizar K. Sallem (LAAS - CNRS), Suat Gedikli (Willowgarage), 
    Michel Devy (LAAS-CNRS), Radu B. Rusu (Willowgarage)
"MRF Guided Anisotropic Depth Diffusion for Kinect Range Image Enhancement" 
    Karthik Mahesh Varadarajan (TU Wien), Markus Vincze (TU Wien)
(18:15 - 18:20) Closing Remarks

- If you have any questions, send an email to