| Seon Joo Kim | |||||
| Home | Research | Publications | Teaching | Links | |
|
-
Radiometric calibration (radiometry in computer vision) - Tracking
|
|||||
| Radiometric Calibration | |||||
| I
have been working on radiometric calibration which is a problem of how
brightness (radiance) in the real
world is mapped in images. Factors involved in this mapping are
● Robust radiometric
calibration and vignetting correction from correspondence I
introduced an algorithm that robustly estimates the radiometric response
function, exposures, and the vignetting effect given multiple images taken
with
▪ Seon Joo Kim and Marc
Pollefeys, "Robust Radiometric Calibration and Vignetting Correction",
IEEE Transactions on Pattern
Analysis and Machine Intelligence ▪ Seon Joo Kim and Marc
Pollefeys, "Radiometric Alignment of Image Sequences", Proc. IEEE Conference
on Computer Vision and Pattern Recognition (CVPR),
● Joint Feature Tracking and
Radiometric Calibration
I presented an algorithm suited
for video data taken with auto-exposure where the correspondence (feature
tracks) and the radiometric response function
along with the
▪ Seon Joo Kim,
David Gallup, Jan-Michael Frahm and Marc Pollefeys, "Joint radiometric
calibration and feature tracking system with an application to stereo" ,
▪ Seon Joo Kim,
Jan-Michael Frahm and Marc Pollefeys, "Joint Feature Tracking and
Radiometric Calibration from
Auto-Exposure Video",
- Video1
(Feature Tracking Comparison)
- Video2
(Tracking & Radiometric Calibration) - Video3 (Tracking & Exposure
Computation) The system is
suited for videos taken in a high dynamic range scene. The graph above compares the exposure
estimates to the ground truth. The joint method can be applied to build an adaptive stereo system.
Our method provides robust feature tracking, simpler stereo cost
function,
I introduced a new
algorithm to compute the radiometric response function and the exposure of
images given a sequence of images of a
static outdoor scene taken over
|
|||||
| Hyperspectral Imaging of Historical Documents | |||||
In a collaborative effort with the Nationaal Archief of the Netherlands (NAN) and Art Innovation, a manufacturerof hyperspectral imaging hardware, I am working on a project to develop tools to study and analyze hyperspectral images (HSI) of historical documents. We have developed a comprehensive visualization tool that offers an assortment of visualization and analysis methods, including interactive spectral selection, spectral similarity analysis, time-varying data analysis and visualization, and selective spectral band fusion to assist the work of our collaborators. One of the key features in our work is the interactive visualization of HSI data based on gradient domain fusion for enhancing the legibility of HSI data based on dynamic selection of spectral bands. There are two major contributions within this feature. First, we apply illustrative visualization to the fusion of HSI data to enhance the contextual details in the data. Second, the fusion technique makes use of the focus+context visualization by enabling the user to explore the fused result with focus on a local region while showing the regions outside with original appearance. This work is accepted for the presentation at IEEE Visualization 2010: ▪ Seon Joo Kim, Shaojie Zhou, Fanbo Deng, Chi-Wing Fu, Michael S. Brown,"Interactive Visualization of Hyperspectral Images of Historical Documents", IEEE Transactions on Visualization and Computer Graphics (TVCG) (Proc. of IEEE Visualization Conference), 2010, To appear.
(A) Contrast of some parts in the original RGB image (left) is enhanced with our gradient fusion method (middle). Side by side comparison of enhanced regions are shown on right. (B),(C) Enhancement using each band is shown locally through the hyperspectral lens. User can interactively choose the band that suits the application (highlighted with dashed line), where in this case is the contrast enhancement.
|
|||||
| Computational Photography | |||||
|
▪ Colorization for Single Image Super Resolution : http://www.comp.nus.edu.sg/~liu727/ECCV/index.htm
|
|||||
| Tracking | |||||
I am also interested in tracking. I worked on projects developing tracking system for automatic surveillance as an intern at GE Research (2005) and at Cortex-US(2004). Here are some videos of the
work done at GE. The goal is to detect salient motion from video (rotating
PTZ camera) that contains other
motions such as waving trees - Video1 (Blue regions indicate salient motion) - Video2 (Blue regions indicate salient motion / green regions indicate non-salient motion) - Video3 The work at GE was
presented in: I have also worked on tracking as class projects including face tracking and 3D active tracking. ▪ 3D active tracking demos ▪ Face tracking demos |
|||||
| Biometrics | |||||
I worked on fingerprint recognition for my Masters degree in one to start the project. Visit the following site for more details on biometrics. Biometrics Engineering Research Center at Yonsei University |
|||||