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：US20150365766A1

公开(公告)日：2015-12-17

申请号：US14553188

申请日：2014-11-25

Applicant: KOREA ELECTRONICS TECHNOLOGY INSTITUTE

Inventor： Choong Sang CHO ,  Je Woo KIM ,  Byeong Ho CHOI ,  Hwa Seon SHIN

IPC: H04R5/04

CPC classification number: G10L21/0272

Abstract: A method for separating audio sources and an audio system using the same are provided. The method introduces the concept of a residual signal to separate a mixed audio signal into audio sources, and separates an audio signal corresponding to at least two of the audio sources as a residual signal and processes the audio signal separately. Therefore, audio separation performance can be improved. In addition, the method re-separates a separated residual signal and adds the separated residual signals to corresponding audio sources. Therefore, audio sources can be separated more safely.

Abstract translation: 提供了一种用于分离音频源的方法和使用其的音频系统。 该方法引入残留信号的概念以将混合音频信号分离成音频源，并且将与至少两个音频源相对应的音频信号分离为残差信号并分别处理音频信号。 因此，可以提高音频分离性能。 此外，该方法重新分离分离的残差信号，并将分离的残留信号添加到相应的音频源。 因此，音频源可以更安全地分离。

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.

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：US20150245006A1

公开(公告)日：2015-08-27

申请号：US14681443

申请日：2015-04-08

Applicant: Korea Electronics Technology Institute

Inventor： Byeong Ho CHOI ,  Je Woo KIM ,  Hwa Seon SHIN

IPC: H04N13/00 ,  H04N21/434 ,  H04N21/81

CPC classification number: H04N13/156 ,  H04N21/4345 ,  H04N21/816

Abstract: The present invention relates to a method for selecting an appropriate mode when performing a new broadcast, such as a 3D stereo broadcast, a UHDTV broadcast, and a multi-view broadcast, among others, while maintaining compatibility with existing broadcasting channels in an MPEG-2-TS format for transmitting and receiving digital TV, and to a method for recognizing a descriptor. To this end, the present invention suggests providing the descriptor which is related to synthesizing left and right images using the type of stream, existence of the descriptor, and a frame-compatible mode flag.

Abstract translation: 本发明涉及一种用于在执行诸如3D立体广播，UHDTV广播和多视点广播等新广播时选择适当模式的方法，同时保持与MPEG- 用于发送和接收数字TV的2-TS格式，以及用于识别描述符的方法。 为此，本发明提出使用流的类型，描述符的存在以及帧兼容模式标志来提供与合成左图像和右图像有关的描述符。