-
1.发明申请公开(公告)号：US20190180448A1
公开(公告)日：2019-06-13
申请号：US15882693
申请日：2018-01-29
Inventor： YongMan Ro , Hak Gu Kim
Abstract: A VR content sickness evaluating apparatus using a deep learning analysis of a motion mismatch and a method thereof are provided. The VR content sickness evaluating apparatus analyzes a motion mismatch phenomenon between visual recognition information and posture recognition information, which occurs when a user views VR content, using deep learning and predicts and evaluates a degree of VR sickness from a difference between motion features.
-
Patent Agency Ranking
2.发明授权公开(公告)号：US11699072B2
公开(公告)日：2023-07-11
申请号：US16700834
申请日：2019-12-02
Inventor： YongMan Ro , Hak Gu Kim , Sangmin Lee
IPC: G06N3/08 , G06T19/00 , G09B3/06 , G06V20/20 , G06F18/213 , G06F18/214 , G06N3/045 , G06V10/82 , G06V10/44
CPC classification number: G06N3/08 , G06F18/213 , G06F18/214 , G06N3/045 , G06T19/006 , G06V10/454 , G06V10/82 , G06V20/20 , G09B3/06
Abstract: A virtual reality (VR) sickness assessment method according to an embodiment includes receiving virtual reality content, and quantitatively evaluating virtual reality sickness for the received virtual reality content using a neural network based on a pre-trained neural mismatch model. The evaluating of the virtual reality sickness may include predicting an expected visual signal for an input visual signal of the virtual reality content based on the neural mismatch model, extracting a neural mismatch feature between the predicted expected visual signal based on the neural mismatch model and an input visual signal for a corresponding frame of the virtual reality content corresponding to the expected visual signal, and evaluating a level of the virtual reality sickness based on the neural mismatch model and the extracted neural mismatch feature.
-
公开(公告)号：US10657655B2
公开(公告)日：2020-05-19
申请号：US15882693
申请日：2018-01-29
Inventor： YongMan Ro , Hak Gu Kim
Abstract: A VR content sickness evaluating apparatus using a deep learning analysis of a motion mismatch and a method thereof are provided. The VR content sickness evaluating apparatus analyzes a motion mismatch phenomenon between visual recognition information and posture recognition information, which occurs when a user views VR content, using deep learning and predicts and evaluates a degree of VR sickness from a difference between motion features.
-
公开(公告)号：US11252371B2
公开(公告)日：2022-02-15
申请号：US16985333
申请日：2020-08-05
Inventor： YongMan Ro , Hak Gu Kim , Sangmin Lee
Abstract: Disclosed is an apparatus and method for VR sickness reduction based on VR sickness assessment. According to an embodiment of the inventive concept, an apparatus for reducing virtual reality (VR) content cybersickness includes a first module extracting feature information about each of predetermined cybersickness precipitating factors through analysis of VR content, and a second module determining a cybersickness precipitating factor requiring cybersickness reduction among the cybersickness precipitating factors based on the extracted feature information about each of the cybersickness precipitating factors, and generating the VR content as VR content having a cybersickness score not greater than a predetermined reference cybersickness score, by performing the cybersickness reduction on corresponding feature information, using a deep learning neural network pre-learned for each of the respective determined cybersickness precipitating factor.
-
5.发明申请公开(公告)号：US20200327408A1
公开(公告)日：2020-10-15
申请号：US16700834
申请日：2019-12-02
Inventor： YongMan Ro , Hak Gu Kim , Sangmin Lee
Abstract: Disclosed are a virtual reality (VR) sickness assessment method and an apparatus thereof considering a neural mismatch model. The virtual reality (VR) sickness assessment method according to an embodiment includes receiving virtual reality content, and quantitatively evaluating virtual reality sickness for the received virtual reality content using a neural network based on a pre-trained neural mismatch model. The evaluating of the virtual reality sickness may include predicting an expected visual signal for an input visual signal of the virtual reality content based on the neural mismatch model, extracting a neural mismatch feature between the predicted expected visual signal based on the neural mismatch model and an input visual signal for a corresponding frame of the virtual reality content corresponding to the expected visual signal, and evaluating a level of the virtual reality sickness based on the neural mismatch model and the extracted neural mismatch feature.
-
公开(公告)号：US10578787B2
公开(公告)日：2020-03-03
申请号：US15629163
申请日：2017-06-21
Inventor： Jin-sung Lee , YongMan Ro , Hak Gu Kim , Jong-sul Min
IPC: G02B5/32
Abstract: A hologram generating apparatus is provided. The apparatus includes a hologram signal generating unit configured to, based on light projected on at least some points corresponding to an object, generate a hologram signal corresponding to the at least some points on at least one two-dimensional plane, a processor configured to calculate a sparsity corresponding to the two-dimensional plane based on the hologram signal, and to calculate a fringe pattern based on at least some of the hologram signal, and a pattern writing unit configured to record the fringe pattern on a computer-generated holography (CGH) plane, wherein the processor is further configured to repeatedly calculate a fringe pattern until a number of dominant signals of the calculated fringe pattern coincides with a predetermined threshold value determined based on the sparsity.
-
-
-
-
-
Search Results
6
records
(took 0.017 seconds)
