公开(公告)号：US20240203161A1

公开(公告)日：2024-06-20

申请号：US18535420

申请日：2023-12-11

Applicant: Korea Electronics Technology Institute

Inventor： Ju Hong YOON ,  Min Gyu PARK ,  Yong Hoon KWON ,  Je Woo KIM

IPC: G06V40/16 ,  G06V10/774 ,  G06V10/776 ,  G06V10/778 ,  G06V40/40

CPC classification number: G06V40/174 ,  G06V10/774 ,  G06V10/776 ,  G06V10/7788 ,  G06V40/169 ,  G06V40/40 ,  G06V10/82

Abstract: There is provided an emotion prediction method based on virtual facial expression image augmentation. The emotion prediction method may acquire a user facial image, may extract a facial expression feature from the acquired user facial image, and may predict a user emotion from the extracted facial expression feature. The emotion prediction method may extract the facial expression feature by using a facial expression recognition network, the facial expression recognition network being an AI model that is trained to receive a user facial image and to extract a facial expression feature. The facial expression recognition network is retrained with virtual facial images which are augmented from a facial image that causes a failure in emotion recognition. Accordingly, by augmenting features of a facial expression image that causes a failure in prediction through error feedback, facial expression recognition performance can be enhanced.

公开(公告)号：US20250104344A1

公开(公告)日：2025-03-27

申请号：US18573736

申请日：2022-12-13

Applicant: Korea Electronics Technology Institute

Inventor： Min Gyu PARK ,  Ju Hong YOON ,  Ju Mi KANG ,  Je Woo KIM ,  Yong Hoon KWON

IPC: G06T17/00 ,  G06V10/44 ,  G06V10/56

Abstract: There are provided an apparatus and a method for reconstructing a 3D human object in real time based on a monocular color image. A 3D human object reconstruction apparatus according to an embodiment extracts a pixel-aligned feature from a monocular image, extracts a ray-invariant feature from the pixel-aligned feature, generates encoded position information by encoding position information of a point, predicts a SD of a point from the ray-invariant feature and the encoded position information which are extracted, and reconstructs a 3D human object by using the predicted SD. Accordingly, the ray-invariant feature extracted from the pixel-aligned feature, and the encoded position information are used, so that an amount of computation for predicting SDs of points of a 3D space can be noticeably reduced and a speed can be remarkably enhanced.

公开(公告)号：US20240212267A1

公开(公告)日：2024-06-27

申请号：US18539462

申请日：2023-12-14

Applicant: Korea Electronics Technology Institute

Inventor： Min Gyu PARK ,  Ju Hong YOON ,  Ju Mi KANG ,  Je Woo KIM

IPC: G06T17/00 ,  G06V10/44

CPC classification number: G06T17/00 ,  G06V10/44

Abstract: There are provided an apparatus and a method for reconstructing a 3D human object based on a monocular image through depth image-based implicit function learning. A 3D human object reconstruction method according to an embodiment includes: predicting a double-sided orthographic depth map from a front perspective color image of a human object; predicting a signed distance (SD) regarding points on a 3D space from the predicted double-sided orthographic depth map; and reconstructing a 3D human object by using the predicted SD. Accordingly, a human object and details can be naturally reconstructed with respect to not only an area visible through a front perspective color image of the human object but also an invisible area.

公开(公告)号：US20240202951A1

公开(公告)日：2024-06-20

申请号：US18539832

申请日：2023-12-14

Applicant: Korea Electronics Technology Institute

Inventor： Min Gyu PARK ,  Ju Hong YOON ,  Min Ho LEE ,  Je Woo KIM

IPC: G06T7/593 ,  G01S17/89 ,  G06V10/771

CPC classification number: G06T7/593 ,  G01S17/89 ,  G06V10/771 ,  G06T2207/20081

Abstract: There is provided a depth estimation method for a small baseline-stereo camera through LiDAR sensor fusion. A depth map estimation method according to an embodiment may estimate a high-resolution depth map from a small baseline-stereo image based on deep learning, by using transfer learning from a deep learning network that is trained to estimate a depth map from a wide baseline-stereo image. Accordingly, in a device which has a small baseline-stereo camera installed therein due to structural constraints, such as a smartphone, a wearable AR/VR device, a drone, 3D image quality can be enhanced. In addition, according to embodiments, pseudo-LiDAR data may be generated by using a depth map estimated from a small baseline-stereo image, and may be used for replacing or reinforcing LiDAR data.

公开(公告)号：US20210334553A1

公开(公告)日：2021-10-28

申请号：US17137832

申请日：2020-12-30

Applicant: Korea Electronics Technology Institute

Inventor： Min Gyu PARK ,  Ju Hong YOON ,  Je Woo KIM

IPC: G06K9/00 ,  G06N3/08 ,  G06N3/04 ,  G06N20/00

Abstract: A method and an apparatus for detecting a lane is provided. The lane detection apparatus according to an embodiment includes: an acquisition unit configured to acquire a front image of a vehicle; and a processor configured to input the image acquired through the acquisition unit to an AI model, and to detect information of a lane on a road, and the AI model is trained to detect lane information that is expressed in a plane form from an input image. Accordingly, data imbalance between a lane area and a non-lane area can be solved by using the AI model which learns/predicts lane information that is expressed in a plane form, not in a segment form such as a straight line or curved line.