조성윤 교수

In synthesizing intermediate views from two stereo images with the help of stereo matching, we suggest an efficient method for removing occlusion. The proposed method can deal with the problems: noise correction from stereo matching using photometric method, occlusion removal for high fidelity rendering using disparity consistency, and parallel computing for real-time synthesis. The proposed algorithm is compared with the state-of-the-art algorithms to show the better performance in rendering an

Objective: This paper proposes a prototype of the vehicle augmented reality (AR) information system which overlays relevant information about environment around the vehicle in the form of AR in a head-up display (HUD). Background: The dangers of inattentive driving are well known. One example is navigation equipments near the instrument cluster often distracting the drivers from their usual viewpoint. Thus HUD systems gain popularity recently to display relevant information within the driver’s r

In synthesizing multiple intermediate views from two stereo using stereo-matching, we suggest an efficient method for removing occlusion. We dealt with the noise correction from stereo matching, occlusion removal for high fidelity rendering, and parallel computing for real-time synthesis. The proposed algorithm shows the better performance in rendering quality and computational speed.

Recent advancements in wearable robots have focused on developing soft, compliant, and lightweight structures to provide comfort for the users and to achieve the primary function of assisting body motions. The interaction forces induced by physical human-robot interaction (pHRI) not only cause skin discomfort or pain due to relatively high localized pressures but also degrade the wearability and the safety of the wearer's joints by unnaturally altering the joint reaction forces (JRFs) and the jo