公开(公告)号：US20200005086A1

公开(公告)日：2020-01-02

申请号：US16147962

申请日：2018-10-01

Applicant: Korea Electronics Technology Institute

Inventor： Sang Ki KO ,  Choong Sang CHO ,  Hye Dong JUNG ,  Young Han LEE

IPC: G06K9/62 ,  G06K9/00 ,  G06K9/46 ,  G06K9/42

Abstract: Deep learning-based automatic gesture recognition method and system are provided. The training method according to an embodiment includes: extracting a plurality of contours from an input image; generating training data by normalizing pieces of contour information forming each of the contours; and training an AI model for gesture recognition by using the generated training data. Accordingly, robust and high-performance automatic gesture recognition can be performed, without being influenced by an environment and a condition even while using less training data.

公开(公告)号：US20190286931A1

公开(公告)日：2019-09-19

申请号：US16043338

申请日：2018-07-24

Applicant: Korea Electronics Technology Institute

Inventor： Bo Eun KIM ,  Choong Sang CHO ,  Hye Dong JUNG ,  Young Han LEE

IPC: G06K9/46 ,  G06F17/24 ,  G06F17/27 ,  G06N5/04 ,  G06N3/08 ,  G06T7/00

Abstract: A method and a system for automatic image caption generation are provided. The automatic image caption generation method according to an embodiment of the present disclosure includes: extracting a distinctive attribute from example captions of a learning image; training a first neural network for predicting a distinctive attribute from an image, by using a pair of the extracted distinctive attribute and the learning image; inferring a distinctive attribute by inputting the learning image to the trained first neural network; and training a second neural network for generating a caption of an image by using a pair of the inferred distinctive attribute and the learning image. Accordingly, a caption well indicating a feature of a given image is automatically generated, such that an image can be more exactly explained and a difference from other images can be clearly distinguished.

公开(公告)号：US20230004866A1

公开(公告)日：2023-01-05

申请号：US17852531

申请日：2022-06-29

Applicant: Korea Electronics Technology Institute

Inventor： Choong Sang CHO ,  Young Han LEE

IPC: G06N20/00 ,  G06K9/62

Abstract: There are provided AI model learning method and system based on self-learning for focusing on specific areas. According to an embodiment, a network learning system includes: a detection module configured to detect a specific area from unlabeled images, and to generate unlabeled area images; a configuration module configured to configure self-learning data by using the generated area images; and a learning module to cause a backbone network to perform self-learning by using the configured self-learning data. Accordingly, an AI model may be trained based on self-learning for focusing on a desired specific area according to a desired purpose, and high-performance analysis specified for various purposes and characteristics of various types of specific areas is possible.

公开(公告)号：US20220383104A1

公开(公告)日：2022-12-01

申请号：US17512463

申请日：2021-10-27

Applicant: Korea Electronics Technology Institute

Inventor： Choong Sang CHO ,  Young Han LEE

IPC: G06N3/08 ,  G06N3/04 ,  G06T7/11 ,  G06K9/62

Abstract: There are provided a method and a system for image segmentation utilizing a GAN architecture. A method for training an image segmentation network according to an embodiment includes: inputting an image to a first network which is trained to output a region segmentation result regarding an input image, and generating a region segmentation result; and inputting the region segmentation result generated at the generation step and a ground truth (GT) to a second network, and acquiring a discrimination result, the second network being trained to discriminate inputted region segmentation results as a result generated by the first network and a GT, respectively; and training the first network and the second network by using the discrimination result. Accordingly, region segmentation performance of a semantic segmentation network regarding various images can be enhanced, and a very small image region can be exactly segmented.

公开(公告)号：US20240062522A1

公开(公告)日：2024-02-22

申请号：US17968986

申请日：2022-10-19

Applicant: Korea Electronics Technology Institute

Inventor： Choong Sang CHO ,  Ju Hong YOON ,  Young Han LEE

IPC: G06V10/774 ,  G06V20/40

CPC classification number: G06V10/774 ,  G06V20/46

Abstract: There is provided a self-directed visual intelligence system, The self-directed visual intelligence system according to an embodiment prepares data necessary for training a visual intelligence model when a change in a visual context of a real world is recognized, configures a visual intelligence model and configures training data of the visual intelligence model, based on the changed visual context of the real world, trains the configured visual intelligence model with the training data, and evaluates performance of the trained visual intelligence model. Accordingly, the visual intelligence model is corrected/improved in a self-directed way according to a change in a visual context of a real world, and is grown/advanced by itself, so that performance of the visual intelligence model is maintained in a best state even in response to any change in the context of the real world.

公开(公告)号：US20200043465A1

公开(公告)日：2020-02-06

申请号：US16256835

申请日：2019-01-24

Applicant: Korea Electronics Technology Institute

Inventor： Jong Yeol YANG ,  Young Han LEE ,  Choong Sang CHO ,  Hye Dong JUNG

IPC: G10L13/10 ,  G06K9/00 ,  H04N21/233

Abstract: An audio synthesis method adapted to video characteristics is provided. The audio synthesis method according to an embodiment includes: extracting characteristics x from a video in a time-series way; extracting characteristics p of phonemes from a text; and generating an audio spectrum characteristic St used to generate an audio to be synthesized with a video at a time t, based on correlations between an audio spectrum characteristic St-1, which is used to generate an audio to be synthesized with a video at a time t−1, and the characteristics x. Accordingly, an audio can be synthesized according to video characteristics, and speech according to a video can be easily added.

公开(公告)号：US20240394546A1

公开(公告)日：2024-11-28

申请号：US18225304

申请日：2023-07-24

Applicant: Korea Electronics Technology Institute

Inventor： Choong Sang CHO ,  Young Han LEE ,  Ju Hong YOON ,  Gui Sik KIM

IPC: G06N3/0895

Abstract: There is provided a learning method and system of a backbone network for visual intelligence based on self-supervised learning and multi-head. A network learning system according to an embodiment generates a plurality of first modified vectors by modifying a first feature vector outputted from a teacher network, generates a plurality of second modified vectors by modifying a second feature vector outputted from a student network, calculates a loss by using the first modified vectors and the second modified vectors, and optimizes parameters of the student network. Accordingly, the effect of learning by knowledge distillation may be enhanced by training the backbone network for visual intelligence like group learning is performed by various teacher networks and student networks.

公开(公告)号：US20220028084A1

公开(公告)日：2022-01-27

申请号：US17126299

申请日：2020-12-18

Applicant: Korea Electronics Technology Institute

Inventor： Choong Sang CHO ,  Charles Hyok SONG ,  Young Han LEE

IPC: G06T7/11 ,  H04N19/176 ,  H04N19/167

Abstract: An image region segmentation method and system suing self-spatial adaptive normalization is provided. The image region segmentation system includes: an encoder configured to encode an image for segmenting a region by using a plurality of encoding blocks; and a decoder configured to decode the image encoded by the encoder and to generate a region-segmented image by using a plurality of decoding blocks, wherein each of the encoding blocks processes an inputted image into a convolution layer, performs spatial adaptive normalization, and then reduces the image and delivers the image to the next encoding block. Accordingly, spatial characteristics of the image are considered in an encoding process and a decoding process, so that region segmentation can be exactly performed with respect to various images.

公开(公告)号：US20250095341A1

公开(公告)日：2025-03-20

申请号：US18741942

申请日：2024-06-13

Applicant: Korea Electronics Technology Institute

Inventor： Choong Sang CHO ,  Young Han LEE ,  Gui Sik KIM ,  Tae Woo KIM

IPC: G06V10/776 ,  G06V10/22 ,  G06V10/74 ,  G06V10/764 ,  G06V10/77

Abstract: There are provided a method and a system for acquiring visual explanation information independent of the purpose, type, and structure of a visual intelligence model. The visual explanation information acquisition system of the visual intelligence model according to an embodiment may input N transformed images which are generated by diversifying an input image to a deep learning-based visual intelligence model and may acquire outputted results, may generate attributes of the visual intelligence model from the acquired results, may derive, from losses of the visual intelligence model which are calculated from the generated attributes, basic data for generating a visual explanation map for visually explaining a result derivation rationale of the visual intelligence model, and may generate a visual explanation map from the derived basic data. Accordingly, visual explanation information may be acquired from various visual intelligence models through one system independently of the purpose, type, and structure of the visual intelligence model.

公开(公告)号：US20210158153A1

公开(公告)日：2021-05-27

申请号：US16952481

申请日：2020-11-19

Applicant: Korea Electronics Technology Institute

Inventor： Young Han LEE ,  Sung Ho LEE ,  Min Geon SHIN

IPC: G06N3/08 ,  G01S13/34 ,  G01S7/35

Abstract: A method and a system for processing an FMCW radar signal by using a lightweight deep learning network are provided. The data processing method using an AI model includes: converting n-dimensional data into a plurality of pieces of 2D data; inputting the plurality of pieces of 2D data into the AI model through different channels; and processing the plurality of pieces of 2D data inputted to the AI model by analyzing. Accordingly, an amount of computation and a memory usage can be reduced and characteristics of an object can be learned and inferred by the lightweight deep learning network.