-
公开(公告)号：US11508158B2
公开(公告)日：2022-11-22
申请号：US16978866
申请日：2019-03-06
发明人： Jaeyong Ju , Myungsik Kim , Seunghoon Han , Taegyu Lim , Boseok Moon
IPC分类号： G06V20/58 , B60W30/095 , G06T7/246 , G06N3/02
摘要： An electronic device for and a method of assisting vehicle driving are provided. The electronic device includes a plurality of cameras configured to capture a surrounding image around a vehicle; at least one sensor configured to sense an object around the vehicle; and a processor configured to obtain, during vehicle driving, a plurality of image frames as the surrounding image of the vehicle is captured based on a preset time interval by using the plurality of cameras, based on the object is sensed using the at least one sensor while the vehicle is being driven, extract an image frame corresponding to a time point when and a location where the object has been sensed, from among the obtained plurality of image frames, perform object detection from the extracted image frame, and perform object tracking of tracking a change in the object, from a plurality of image frames obtained after the extracted image frame. The present disclosure also relates to an artificial intelligence (AI) system that utilizes a machine learning algorithm, such as deep learning, and applications of the AI system.
-
公开(公告)号：US20240233340A9
公开(公告)日：2024-07-11
申请号：US18384549
申请日：2023-10-27
发明人： Jaeyong Ju
IPC分类号： G06V10/774 , G06T7/80 , G06V10/82 , G06V20/70 , H04N23/90
CPC分类号： G06V10/774 , G06T7/80 , G06V10/82 , G06V20/70 , H04N23/90 , G06T2207/20081 , G06T2207/20084 , G06T2207/30204 , G06T2207/30244
摘要： Provided is a computer-implemented method of training a neural network model by augmenting images representing objects. The method includes: obtaining a first object recognition result predicted by a first neural network model using, as an input, a first image captured by a first camera capturing, from a first viewpoint, a space including at least one object; converting the obtained first object recognition result, based on a conversion relationship between a first camera coordinate system corresponding to the first camera and a second camera coordinate system corresponding to a second camera capturing, from a second viewpoint, the space; generating, based on the first object recognition result converted with respect to the second viewpoint, training data by performing labeling on a second image that corresponds to the first image, the second image being captured by the second camera; and training a second neural network model by using the generated training data.
-
公开(公告)号：US20210149498A1
公开(公告)日：2021-05-20
申请号：US17081597
申请日：2020-10-27
发明人： Joonah PARK , Jaeyong Ju , Taehyeong Kim , Jaeha Lee
摘要： An electronic apparatus is provided. The electronic apparatus includes a camera; a memory configured to store at least one instruction; and at least one processor configured to execute the at least one instruction to: detect at least one object included in an image captured by the camera; identify information on an engagement of each of the at least one object with the electronic apparatus; obtain gesture information of each of the at least one object; obtain a target object from among the at least one object based on an operation status of the electronic apparatus, the information on the engagement of each of the at least one object, and the obtained gesture information of each of the at least one object; identify a function corresponding to gesture information of the target object; and execute the identified function.
-
公开(公告)号：US20240135686A1
公开(公告)日：2024-04-25
申请号：US18384549
申请日：2023-10-26
发明人： Jaeyong Ju
IPC分类号： G06V10/774 , G06T7/80 , G06V10/82 , G06V20/70 , H04N23/90
CPC分类号： G06V10/774 , G06T7/80 , G06V10/82 , G06V20/70 , H04N23/90 , G06T2207/20081 , G06T2207/20084 , G06T2207/30204 , G06T2207/30244
摘要： Provided is a computer-implemented method of training a neural network model by augmenting images representing objects. The method includes: obtaining a first object recognition result predicted by a first neural network model using, as an input, a first image captured by a first camera capturing, from a first viewpoint, a space including at least one object; converting the obtained first object recognition result, based on a conversion relationship between a first camera coordinate system corresponding to the first camera and a second camera coordinate system corresponding to a second camera capturing, from a second viewpoint, the space; generating, based on the first object recognition result converted with respect to the second viewpoint, training data by performing labeling on a second image that corresponds to the first image, the second image being captured by the second camera; and training a second neural network model by using the generated training data.
-
公开(公告)号：US11801602B2
公开(公告)日：2023-10-31
申请号：US17420859
申请日：2020-01-02
发明人： Jaeyong Ju , Hyeran Lee , Hyunjung Nam , Miyoung Kim , Jaebum Park , Joonah Park
CPC分类号： B25J9/1664 , B25J9/1697 , B25J11/0005 , B25J19/023 , G05D1/0246
摘要： Provided are a mobile robot and a method of driving the same. A method in which the mobile robot moves along with a user includes photographing surroundings of the mobile robot, detecting the user from an image captured by the photographing, tracking a location of the user within the image as the user moves, predicting a movement direction of the user, based on a last location of the user within the image, when the tracking of the location of the user is stopped, and determining a traveling path of the mobile robot, based on the predicted movement direction of the user.
-
公开(公告)号：US11635821B2
公开(公告)日：2023-04-25
申请号：US17081597
申请日：2020-10-27
发明人： Joonah Park , Jaeyong Ju , Taehyeong Kim , Jaeha Lee
摘要： An electronic apparatus is provided. The electronic apparatus includes a camera; a memory configured to store at least one instruction; and at least one processor configured to execute the at least one instruction to: detect at least one object included in an image captured by the camera; identify information on an engagement of each of the at least one object with the electronic apparatus; obtain gesture information of each of the at least one object; obtain a target object from among the at least one object based on an operation status of the electronic apparatus, the information on the engagement of each of the at least one object, and the obtained gesture information of each of the at least one object; identify a function corresponding to gesture information of the target object; and execute the identified function.
-
-
-
-
-
搜索结果
6 条记录 (耗时 0.016 秒)
