W
Whoi-Yul Kim
Researcher at Hanyang University
Publications - 188
Citations - 3004
Whoi-Yul Kim is an academic researcher from Hanyang University. The author has contributed to research in topics: Image retrieval & Image processing. The author has an hindex of 26, co-authored 186 publications receiving 2782 citations. Previous affiliations of Whoi-Yul Kim include SK Hynix & Electronics and Telecommunications Research Institute.
Papers
More filters
Journal ArticleDOI
Specular Detection on Glossy Surface Using Geometric Characteristics of Specularity in Top-View Images.
TL;DR: Zhang et al. as mentioned in this paper proposed two methods to estimate specular pixels in the top-view image, which can be used to distinguish the specular region in images and improve line detection performance.
Journal Article
An Effective Shadow Elimination Method Using Adaptive Parameters Update
TL;DR: A method for shadow elimination which is based on shadow modeling by color information and Bayesian classification framework is proposed, able to correspond adaptively to illumination changes.
Book ChapterDOI
Selective motion estimation for fast video encoding
TL;DR: A method to minimize the use of MEMC is presented, which will further reduce the computational complexity with the reasonable visual quality and experimental results indicated that the proposed coding scheme can reduce about 55–75 percent over the MPEG-4 video reference software.
Journal ArticleDOI
An Automatic Calibration Method for AVM Cameras
Yun Hee Lee,Whoi-Yul Kim +1 more
TL;DR: A robust method that considers various environments using parallel parking lines that can be easily installed in general service centers for the efficient calibration of around-view-monitoring (AVM) cameras is introduced.
Proceedings ArticleDOI
A method of detecting parking slot in hough space and pose estimation using rear view image for autonomous parking system
TL;DR: An algorithm for parking assist system that detects a parking slot and estimates the pose of the parking slot using NCC (Normalized Cross Correlation) and separates the process of pose estimation into phase 1 and phase 2 according to applied template shape.