公开(公告)号：US11699072B2

公开(公告)日：2023-07-11

申请号：US16700834

申请日：2019-12-02

Applicant: Korea Advanced Institute of Science and Technology

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：US11252371B2

公开(公告)日：2022-02-15

申请号：US16985333

申请日：2020-08-05

Applicant: KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： YongMan Ro ,  Hak Gu Kim ,  Sangmin Lee

IPC: H04N7/01 ,  G06N3/08 ,  G06T7/00 ,  G06T7/20

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.

公开(公告)号：US20200327408A1

公开(公告)日：2020-10-15

申请号：US16700834

申请日：2019-12-02

Applicant: Korea Advanced Institute of Science and Technology

Inventor： YongMan Ro ,  Hak Gu Kim ,  Sangmin Lee

IPC: G06N3/08 ,  G06N3/04 ,  G06K9/62 ,  G06K9/00 ,  G09B3/06 ,  G06T19/00

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.