-
1.发明申请公开(公告)号：US20180325442A1
公开(公告)日：2018-11-15
申请号：US16034436
申请日：2018-07-13
发明人： Dong Hwa LEE , Chang Hyun KIM , Eun Soo SHIM , Ki Hwan CHOI , Hyun Jin CHOI
IPC分类号： A61B5/18 , A61B3/10 , B60W30/00 , G05D1/02 , G06N3/04 , A61B3/00 , A61B5/024 , A61B5/0402 , A61B5/22 , A61B5/0476
摘要： Disclosed is an apparatus and method to train an autonomous driving model. The apparatus includes a driver information collection processor configured to collect driver information while a vehicle is being driven. The apparatus also includes a sensor information collection processor configured to collect sensor information from a sensor installed in the vehicle while the vehicle is being driven, and a model training processor configured to train the autonomous driving model based on the driver information and the sensor information.
-
2.发明公开公开(公告)号：US20240357824A1
公开(公告)日：2024-10-24
申请号：US18526285
申请日：2023-12-01
发明人： Byong Ju KIM , Dong Sung CHOI , Won Jun PARK , Dong Hwa LEE , Jae Min JUNG , Chang Heon CHEON
摘要： There is provided a semiconductor memory device having improved reliability. The semiconductor memory device includes a cell substrate, a mold stack including mold insulating layers and gate electrodes, which are alternately stacked on the cell substrate, a semiconductor layer extended in a vertical direction crossing an upper surface of the cell substrate to pass through the mold stack, a blocking insulating pattern between the semiconductor layer and each of the gate electrodes, a charge storage layer including a charge trap portion between the semiconductor layer and the blocking insulating pattern and a first charge blocking portion between the semiconductor layer and each of the mold insulating layers, and a tunnel insulating layer between the semiconductor layer and the charge storage layer, wherein an oxygen concentration of the first charge blocking portion is higher than that of the charge trap portion.
-
3.发明申请公开(公告)号：US20170135621A1
公开(公告)日：2017-05-18
申请号：US15351629
申请日：2016-11-15
发明人： Dong Hwa LEE , Chang Hyun KIM , Eun Soo SHIM , Ki Hwan CHOI , Hyun Jin CHOI
IPC分类号： A61B5/18 , G06N99/00 , A61B3/00 , A61B5/0402 , A61B5/0476 , A61B3/10 , G05D1/00 , A61B5/024
CPC分类号： A61B5/18 , A61B3/0025 , A61B3/10 , A61B5/024 , A61B5/0402 , A61B5/0476 , A61B5/225 , B60W30/00 , G05D1/0221 , G06N3/0454
摘要： Disclosed is an apparatus and method to train an autonomous driving model. The apparatus includes a driver information collection processor configured to collect driver information while a vehicle is being driven. The apparatus also includes a sensor information collection processor configured to collect sensor information from a sensor installed in the vehicle while the vehicle is being driven, and a model training processor configured to train the autonomous driving model based on the driver information and the sensor information.
-
公开(公告)号：US20170083772A1
公开(公告)日：2017-03-23
申请号：US15266231
申请日：2016-09-15
发明人： Chang Hyun KIM , Tae Sup MOON , Dong Hwa LEE , Hyun Jin CHOI , Ki Hwan CHOI
CPC分类号： G06K9/00791 , B60Q9/00 , G06K9/4642 , G06K9/6223 , G06K9/6226 , G06K9/72 , G06N3/0445 , G06N3/08 , G06N7/005
摘要： Disclosed are methods and apparatuses for object recognition using an artificial neural network. An object recognition apparatus includes an adjacent pixel setter configured to set the neighboring pixel pairs in the image frame, each neighboring pixel pair including first pixel and one or more second pixels adjacent to the first pixel, a labeler configured to label the first pixel using deep neural network-based model based on probability density function value of the neighboring pixel pairs, and an object recognizer configured to recognize an object based on the labeled first pixel.
-
5.发明申请公开(公告)号：US20200090008A1
公开(公告)日：2020-03-19
申请号：US16683455
申请日：2019-11-14
发明人： Hyun Jin CHOI , Chang Hyun KIM , Eun Soo SHIM , Dong Hwa LEE , Ki Hwan CHOI
摘要： Apparatuses and methods for image processing are provided. The image processing apparatus performs area classification and object detection in an image, and includes a feature map generator configured to generate the feature map of the input image using the neural network, and an image processor configured to classify the areas and to detect the objects in the image using the generated feature map.
-
6.发明申请公开(公告)号：US20170169313A1
公开(公告)日：2017-06-15
申请号：US15271476
申请日：2016-09-21
发明人： Hyun Jin CHOI , Chang Hyun KIM , Eun Soo SHIM , Dong Hwa LEE , Ki Hwan CHOI
CPC分类号： G06K9/6267 , G06K9/3241 , G06K9/4604 , G06K9/4628 , G06K9/52 , G06K9/66
摘要： Apparatuses and methods for image processing are provided. The image processing apparatus performs area classification and object detection in an image, and includes a feature map generator configured to generate the feature map of the input image using the neural network, and an image processor configured to classify the areas and to detect the objects in the image using the generated feature map.
-
-
-
-
-
搜索结果
6 条记录 (耗时 0.014 秒)
