公开(公告)号：US20150206026A1

公开(公告)日：2015-07-23

申请号：US14562948

申请日：2014-12-08

Applicant: Samsung Electronics Co., Ltd.

Inventor： Won Jun KIM ,  Byung In YOO ,  Jae Joon HAN

IPC: G06K9/46 ,  G06K9/00

CPC classification number: G06K9/4642 ,  G06K9/00335 ,  G06K9/4604

Abstract: Example embodiments disclose a method of generating a feature vector, a method of generating a histogram, a learning unit classifier, a recognition apparatus, and a detection apparatus, in which a feature point is detected from an input image based on a dominant direction analysis of a gradient distribution, and a feature vector corresponding to the detected feature point is generated.

Abstract translation: 示例性实施例公开了一种生成特征向量的方法，生成直方图的方法，学习单元分类器，识别装置和检测装置，其中基于主导方向分析从输入图像检测特征点 生成与检测出的特征点对应的梯度分布和特征向量。

公开(公告)号：US20130182958A1

公开(公告)日：2013-07-18

申请号：US13713351

申请日：2012-12-13

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Byung In YOO ,  Hee Seob RYU ,  Chang Kyu CHOI ,  Chang Kyo LEE ,  Jae Joon HAN

IPC: G06K9/00

CPC classification number: G06K9/00369

Abstract: An apparatus and method for analyzing body part association. The apparatus and method may recognize at least one body part from a user image extracted from an observed image, select at least one candidate body part based on association of the at least one body part, and output a user pose skeleton related to the user image based on the selected at least one candidate body part.

Abstract translation: 一种用于分析身体部位关联的装置和方法。 该装置和方法可以从从观察图像提取的用户图像中识别至少一个身体部位，基于至少一个身体部位的关联来选择至少一个候选人体部分，并且输出与用户图像相关的用户姿势骨架 基于所选择的至少一个候选身体部位。

公开(公告)号：US20250166384A1

公开(公告)日：2025-05-22

申请号：US18939432

申请日：2024-11-06

Applicant: Samsung Electronics Co., Ltd.

Inventor： Junchen REN ,  Seungin PARK ,  Ying MIN ,  Zao YAO ,  Byung In YOO ,  Ju Hwan SONG ,  YunHao ZHANG ,  Feng ZHU

IPC: G06V20/52 ,  G06T5/20 ,  G06T7/20

Abstract: A method of estimating a state includes: predicting current state prediction data of a target object by using previous state estimation data of a previous image frame of an image sequence in which the target object is represented, the previous image frame previous to a current image frame; acquiring current target detection data of the target object for the current image frame of the image sequence; and determining current state estimation data of the target object of the current image frame by updating the current state prediction data by using the current target detection data and by using a detection reliability of the current target detection data.

公开(公告)号：US20250148800A1

公开(公告)日：2025-05-08

申请号：US18636331

申请日：2024-04-16

Applicant: Samsung Electronics Co., Ltd.

Inventor： Solae LEE ,  Park SEUNGIN ,  Hyeongseok SON ,  Byung In YOO ,  Minki JEONG

IPC: G06V20/58 ,  G01S17/86 ,  G01S17/89 ,  G01S17/931 ,  G06V10/40 ,  G06V10/80

Abstract: An object detection method and an object detection apparatus for detecting an object based on multi-features are provided. The object detection method includes: obtaining first-sensor data from a first sensor and obtaining second-sensor data from a second sensor, wherein the first sensor is a different type of sensor than the second sensor; extracting a first feature from the first-sensor data and extracting a second feature from the second-sensor data; determining a target feature-type by inputting the first and second features to a feature-type selection model which, based thereon, predicts the target feature-type; determining a target feature to be used for object detection according to the determined target feature-type; and determining an object detection result based on the determined target feature.

公开(公告)号：US20250148262A1

公开(公告)日：2025-05-08

申请号：US18642167

申请日：2024-04-22

Applicant: Samsung Electronics Co., Ltd.

Inventor： Wonjun CHOI ,  Byung In YOO ,  Dongwook LEE

IPC: G06N3/045 ,  G06N5/022

Abstract: A method and apparatus with a feature-level ensemble model are provided. A method of operating an ensemble model based on feature-level consolidation includes: obtaining queries by inputting a same input data item to respective transformer models, the transformer models generating respective queries from the input data item; forming an ensemble query corresponding to the queries; and generating a predicted value of the input data item by applying the ensemble query to a prediction model that includes a transformer decoder, the prediction model inferring the predicted value from the ensemble query.

公开(公告)号：US20250104259A1

公开(公告)日：2025-03-27

申请号：US18631836

申请日：2024-04-10

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hyeongseok SON ,  Seungin PARK ,  Byung In YOO ,  Dongwook LEE ,  Sangil JUNG

IPC: G06T7/50 ,  G06T5/20 ,  G06T7/12

Abstract: A method performed by one or more processors of an electronic device includes: processing an input image and point cloud data corresponding to the input image; projecting the point cloud data to generate a first depth map and adding new depth values to the first depth map based on the input image; obtaining a second depth map by inputting the input image to a depth estimation model configured to infer depth maps from input images; and training the depth estimation model based on a loss difference between the first depth map and the second depth map.

公开(公告)号：US20250078286A1

公开(公告)日：2025-03-06

申请号：US18803352

申请日：2024-08-13

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Zao YAO ,  Ju Hwan SONG ,  Ying MIN ,  Byung In YOO ,  Changbeom PARK ,  YunHao ZHANG ,  Junchen REN ,  Yuanzhang YAO ,  Sanqi LI

IPC: G06T7/246 ,  G06T7/80 ,  G06V10/28 ,  G06V10/42 ,  G06V10/80

Abstract: An apparatus and method for quantizing a transformer-based target tracking model are provided. The method includes obtaining a transformer-based target tracking model including a template branch, a search branch, a stitching module, and a first transformer module, generating an optimized target tracking model by removing the stitching module from the transformer-based target tracking model and dividing the first transformer module into a second transformer module and a third transformer module, and generating a quantization model corresponding to the optimized target tracking model by quantizing the divided second transformer module independently of quantizing the divided third transformer module.

公开(公告)号：US20240242082A1

公开(公告)日：2024-07-18

申请号：US18338732

申请日：2023-06-21

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Seohyung LEE ,  Jiho CHOI ,  Byung In YOO

IPC: G06N3/09 ,  G06N3/048

CPC classification number: G06N3/09 ,  G06N3/048

Abstract: An apparatus and method for training a neural network model for classification without a teacher model are disclosed. The includes: selecting classes from a database comprising a set of classes; generating a mean feature group comprising mean features extracted from the selected classes; receiving a batch comprising input data and extracting, by the neural network model, a feature from the input data, wherein the neural network model is to be trained according to a mean feature set; determining a first similarity between the extracted feature and a mean feature corresponding to the input data; determining a second similarity comprising a self-similarity of the mean feature; and updating a parameter of the neural network model based on the first similarity and the second similarity.

公开(公告)号：US20230351610A1

公开(公告)日：2023-11-02

申请号：US17987231

申请日：2022-11-15

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Dongwook LEE ,  Seohyung LEE ,  Changbeom PARK ,  Byung In YOO ,  Hyunjeong LEE

IPC: G06T7/20 ,  G06T7/00

CPC classification number: G06T7/20 ,  G06T7/97 ,  G06T2207/10016

Abstract: A processor-implemented method with object tracking includes: performing, using a first template, forward object tracking on first image frames in a first sequence group; determining a template candidate of a second template for second image frames in a second sequence group; performing backward object tracking on the first image frames using the template candidate; determining a confidence of the template candidate using a result of comparing a first tracking result determined by the forward object tracking performed on the first image frames and a second tracking result determined by the backward object tracking performed on the first image frames; determining the second template based on the confidence of the template candidate; and performing forward object tracking on the second image frames using the second template.

公开(公告)号：US20230283876A1

公开(公告)日：2023-09-07

申请号：US17958564

申请日：2022-10-03

Applicant: Samsung Electronics Co., Ltd.

Inventor： Byung In YOO ,  Youngjun KWAK ,  Sungyoul PARK ,  Solae LEE ,  Hana LEE ,  Jiho CHOI

IPC: H04N5/232

CPC classification number: H04N5/23218 ,  H04N5/23299 ,  H04N5/23296

Abstract: A device and method with object recognition is included. In one general aspect, an electronic device includes a camera sensor configured to capture a first image of a scene, the camera sensor is configured to perform at least one type of physical camera motion relative to the electronic device, the at least one type of physical camera motion includes rolling, panning, tilting, or zooming the camera sensor relative to the electronic device, and a processor configured to control the camera sensor to perform a physical motion of the physical camera motion type based on detecting an object in the first image, acquire a second image captured using the camera sensor as adjusted based on the performed physical motion, and recognize the object in the second image.