-
公开(公告)号：US11967088B2
公开(公告)日：2024-04-23
申请号：US18073737
申请日：2022-12-02
Applicant: Samsung Electronics Co., Ltd.
Inventor： HyunJeong Lee , Changbeom Park , Hana Lee , Sung Kwang Cho
CPC classification number: G06T7/246 , G06F18/213 , G06F18/22 , G06T7/73 , G06V10/40 , G06V10/451 , G06V10/761 , G06V20/00
Abstract: A target tracking method and apparatus is provided. The target tracking apparatus includes a memory configured to store a neural network, and a processor configured to extract feature information of each of a target included in a target region in a first input image, a background included in the target region, and a searching region in a second input image, using the neural network, obtain similarity information of the target and the searching region and similarity information of the background and the searching region based on the extracted feature information, obtain a score matrix including activated feature values based on the obtained similarity information, and estimate a position of the target in the searching region from the score matrix.
-
公开(公告)号：US11741617B2
公开(公告)日：2023-08-29
申请号：US17528501
申请日：2021-11-17
Applicant: Samsung Electronics Co., Ltd.
Inventor： Hyunjeong Lee , SeungWook Kim , Changbeom Park , Ju Hwan Song , Byung In Yoo
IPC: G06K9/00 , G06T7/246 , G06V10/22 , G06F18/213
CPC classification number: G06T7/248 , G06F18/213 , G06V10/22 , G06T2207/20084
Abstract: A processor-implemented method with object tracking includes: determining an initial template image based on an input bounding box and an input image; generating an initial feature map by extracting features from the initial template image; generating a transformed feature map by performing feature transformation adapted to objectness on the initial feature map; generating an objectness probability map and a bounding box map indicating bounding box information corresponding to each coordinate of the objectness probability map by performing objectness-based bounding box regression analysis on the transformed feature map; and determining a refined bounding box based on the objectness probability map and the bounding box map.
-
公开(公告)号：US11335012B2
公开(公告)日：2022-05-17
申请号：US17227719
申请日：2021-04-12
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Seung Wook Kim , Hyunjeong Lee , Changbeom Park , Changyong Son , Seohyung Lee
Abstract: An object tracking method includes generating a feature map of a search image and generating a feature map of a target image, obtaining an object classification result and a basic bounding box based on the feature map of the search image and the feature map of the target image, obtaining an auxiliary bounding box based on the feature map of the search image, obtaining a final bounding box based on the basic bounding box and the auxiliary bounding box, and tracking an object based on the object classification result and the final bounding box.
-
公开(公告)号：US20210295532A1
公开(公告)日：2021-09-23
申请号：US17126513
申请日：2020-12-18
Applicant: Samsung Electronics Co., Ltd.
Inventor： HyunJeong Lee , Changbeom Park , Hana Lee , Sung Kwang Cho
Abstract: A target tracking method and apparatus is provided. The target tracking apparatus includes a memory configured to store a neural network, and a processor configured to extract feature information of each of a target included in a target region in a first input image, a background included in the target region, and a searching region in a second input image, using the neural network, obtain similarity information of the target and the searching region and similarity information of the background and the searching region based on the extracted feature information, obtain a score matrix including activated feature values based on the obtained similarity information, and estimate a position of the target in the searching region from the score matrix.
-
Patent Agency Ranking
公开(公告)号：US12243243B2
公开(公告)日：2025-03-04
申请号：US17668513
申请日：2022-02-10
Inventor： Youngjun Kwak , Taekyung Kim , Changick Kim , Byeongjun Park , Changbeom Park
IPC: G06T7/246 , G06T3/18 , G06T3/4007 , G06T7/55 , G06V20/40
Abstract: A scene flow estimation method and apparatus are provided. The scene flow estimation method includes receiving a first feature pyramid and a second feature pyramid by encoding a first frame and a second frame of an input image through the same encoder, extracting a depth feature based on the first feature pyramid, extracting a motion feature based on the first feature pyramid and the second feature pyramid, generating an overall feature based on the depth feature and the motion feature, and estimating a scene flow based on the overall feature.
-
公开(公告)号：US12002218B2
公开(公告)日：2024-06-04
申请号：US17531972
申请日：2021-11-22
Applicant: Samsung Electronics Co., Ltd.
Inventor： Hyunjeong Lee , Seungwook Kim , Changbeom Park , Byung In Yoo
CPC classification number: G06T7/194 , G06F18/22 , G06T7/136 , G06T7/248 , G06V10/751 , G06T2207/10024
Abstract: A method, apparatus, and system with tracking are disclosed. The apparatus is configured to acquire a feature map of a template image, a color histogram of a foreground of the template image that has an object, and a color histogram of a background of the template image other than the foreground, acquire a feature score map, and a bounding box map corresponding to the feature score map, based on the feature map of the template image and a feature map of a search image, acquire a color score map based on the color histogram of the foreground, the color histogram of the background, and a color value of the search image, acquire a final score map, and a bounding box map corresponding to the final score map, based on the feature score map, the color score map, and the bounding box map, and output the corresponding bounding box.
-
公开(公告)号：US11715216B2
公开(公告)日：2023-08-01
申请号：US17404413
申请日：2021-08-17
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Ju Hwan Song , Hyunjeong Lee , Changbeom Park , Changyong Son , Byung In Yoo
CPC classification number: G06T7/248 , G06V10/22 , G06V10/44 , G06T2207/20216
Abstract: A processor-implemented object tracking method includes: setting a suppressed region in a template image based on a shape of a target box of the template image; refining a template feature map of the template image by suppressing an influence of feature data corresponding to the suppressed region in the template feature map; and tracking an object by determining a bounding box corresponding to the target box in a search image based on the refined template feature map.
-
公开(公告)号：US11544855B2
公开(公告)日：2023-01-03
申请号：US17126513
申请日：2020-12-18
Applicant: Samsung Electronics Co., Ltd.
Inventor： HyunJeong Lee , Changbeom Park , Hana Lee , Sung Kwang Cho
Abstract: A target tracking method and apparatus is provided. The target tracking apparatus includes a memory configured to store a neural network, and a processor configured to extract feature information of each of a target included in a target region in a first input image, a background included in the target region, and a searching region in a second input image, using the neural network, obtain similarity information of the target and the searching region and similarity information of the background and the searching region based on the extracted feature information, obtain a score matrix including activated feature values based on the obtained similarity information, and estimate a position of the target in the searching region from the score matrix.
-
公开(公告)号：US11508075B2
公开(公告)日：2022-11-22
申请号：US17027756
申请日：2020-09-22
Applicant: Samsung Electronics Co., Ltd.
Inventor： Sung Kwang Cho , Changbeom Park , Byung In Yoo , Hyunjeong Lee , Jaejoon Han
Abstract: Disclosed are target tracking methods and apparatuses. The target tracking apparatus performs target tracking on an input image obtained in a first time period within a single time frame, using a light neural network in a second time period of the single time frame. The target tracking apparatus may perform target tracking on input images generated within the same time frame.
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.018 seconds)
