Browsing by Author "Han, Ping-Hsuan"

Now showing 1 - 4 of 4

AR-Arm: Augmented Visualization for Guiding Arm Movement in the First-Person Perspective
(2016)
Han, Ping-Hsuan
;
Chen, Kuan-Wen
;
Hsieh, Chen-Hsin
;
Huang, Yu-Jie
;
Hung, Yi-Ping
In many activities, such as martial arts, physical exercise, and physiotherapy, the users are asked to perform a sequence of body movements with highly accurate arm positions. Sometimes, the movements are too complicated for users to learn, even by imitating the action of the coach directly. This paper presents a fully immersive augmented reality (AR) system, which provides egocentric hints to guide the arm movement of the user via a video see-through head-mounted display (HMD). By using this system, the user can perform the exactitude of arm movement simply by moving his arms to follow and match the virtual arms, rendered from coach\'s movement of database, in the first-person view. To ensure the rendered virtual arms correctly aligned with the user\'s real shoulders, a calibration method is proposed to estimate the length of the user\'s arms and the positions of his head and shoulders in advance. In addition, we apply the system to Tai-Chi-Chuan practicing, our preliminary study has shown that the proposed egocentric hints can provide intuitive guidance for users to follow the arm movement of the coach with exactitude.
Dunhuang Mural Restoration using Deep Learning
(2018-01-01)
Wang, Han-Lei
;
Han, Ping-Hsuan
;
Chen, Yu-Mu
;
Chen, Kuan-Wen
;
Lin, XinYi
As time goes by, the art pieces inside Dunhuang Grottoes have suffered from tremendous damage such as mural deterioration, and they are usually difficult to be repaired. Although we can achieve digital preservation by modeling the caves and preserving mural as textures in virtual environment, we still cannot have a glimpse of how the grottoes look like without damage. In this work, we propose a systematic restoration framework, which is based on Generative Adversarial Network (GAN) technique, for these high-resolution but deteriorated mural textures. The main idea is to make the machine learn the transformation between deteriorated mural textures and restored mural textures. However, the resolution of training texture images (i.e. 8192x8192) is too high to be applied with GAN technology directly due to GPU RAM limitation. Instead, our method restores a set of high-resolution yet color-inconsistent textures patch-by-patch and a set of low-resolution but color-consistent full textures, and then combines them to get the final high-resolution and color-consistent result.
Estimating the Simulator Sickness in Immersive Virtual Reality with Optical Flow Analysis
(2017-01-01)
Lee, Jiun-Yu
;
Han, Ping-Hsuan
;
Tsai, Ling
;
Peng, Rih-Ding
;
Chen, Yang-Sheng
Lotus: Enhancing the Immersive Experience in Virtual Environment with Mist-based Olfactory Display
(2018-01-01)
Chen, Yang-Sheng
;
Han, Ping-Hsuan
;
Lee, Kong-Chang
;
Hsieh, Chiao-En
;
Hsiao, Jui-Chun
With the advance of virtual reality (VR) headset and haptic technologies, users can have a great experience when they are immersed in the virtual environment (VE). A fewer of research allow users to perceive the odor from the VE simultaneously. Based on the five senses, olfaction is one of the human sense that can perceive chemical information from the environment, which is also important for recreating the VE. In the past, some research groups have shown the techniques of olfactory display. However, to create the olfactory feedback for immersive VR when the user moving around in the tracking area, where a moveable display or a lightweight portable device is required, due to the user's nose is the only human receptor for perceiving the scent. We present Lotus, a steerable mist-based olfactory display with an airflow guiding module for simulating environments with olfaction. It can provide two kinds of VEs simultaneously for enhancing the immersive experience without carrying the weighty liquid.