-
公开(公告)号：US10984286B2
公开(公告)日：2021-04-20
申请号：US16265725
申请日：2019-02-01
Applicant: NVIDIA Corporation
Inventor： Aysegul Dundar , Ming-Yu Liu , Ting-Chun Wang , John Zedlewski , Jan Kautz
IPC: G06K9/62 , G06K9/32 , G06K9/00 , G01N3/08 , G06N3/04 , G06T7/10 , G06T3/00 , G06T11/00 , G06T15/00 , G06N3/08
Abstract: A style transfer neural network may be used to generate stylized synthetic images, where real images provide the style (e.g., seasons, weather, lighting) for transfer to synthetic images. The stylized synthetic images may then be used to train a recognition neural network. In turn, the trained neural network may be used to predict semantic labels for the real images, providing recognition data for the real images. Finally, the real training dataset (real images and predicted recognition data) and the synthetic training dataset are used by the style transfer neural network to generate stylized synthetic images. The training of the neural network, prediction of recognition data for the real images, and stylizing of the synthetic images may be repeated for a number of iterations. The stylization operation more closely aligns a covariate of the synthetic images to the covariate of the real images, improving accuracy of the recognition neural network.
-
公开(公告)号：US20190303759A1
公开(公告)日：2019-10-03
申请号：US16366875
申请日：2019-03-27
Applicant: NVIDIA Corporation
Inventor： Clement Farabet , John Zedlewski , Zachary Taylor , Greg Heinrich , Claire Delaunay , Mark Daly , Matthew Campbell , Curtis Beeson , Gary Hicok , Michael Cox , Rev Lebaredian , Tony Tamasi , David Auld
Abstract: In various examples, physical sensor data may be generated by a vehicle in a real-world environment. The physical sensor data may be used to train deep neural networks (DNNs). The DNNs may then be tested in a simulated environment—in some examples using hardware configured for installation in a vehicle to execute an autonomous driving software stack—to control a virtual vehicle in the simulated environment or to otherwise test, verify, or validate the outputs of the DNNs. Prior to use by the DNNs, virtual sensor data generated by virtual sensors within the simulated environment may be encoded to a format consistent with the format of the physical sensor data generated by the vehicle.
-
公开(公告)号：US20250111216A1
公开(公告)日：2025-04-03
申请号：US18980252
申请日：2024-12-13
Applicant: NVIDIA Corporation
Inventor： Clement Farabet , John Zedlewski , Zachary Taylor , Greg Heinrich , Claire Delaunay , Mark Daly , Matthew Campbell , Curtis Beeson , Gary Hicok , Michael Cox , Rev Lebaredian , Tony Tamasi , David Auld
IPC: G06N3/063 , G06F9/455 , G06F18/2413 , G06N3/045 , G06N3/08 , G06N20/00 , G06V10/44 , G06V10/764 , G06V10/82 , G06V20/56
Abstract: In various examples, physical sensor data may be generated by a vehicle in a real-world environment. The physical sensor data may be used to train deep neural networks (DNNs). The DNNs may then be tested in a simulated environment—in some examples using hardware configured for installation in a vehicle to execute an autonomous driving software stack—to control a virtual vehicle in the simulated environment or to otherwise test, verify, or validate the outputs of the DNNs. Prior to use by the DNNs, virtual sensor data generated by virtual sensors within the simulated environment may be encoded to a format consistent with the format of the physical sensor data generated by the vehicle.
-
公开(公告)号：US12182694B2
公开(公告)日：2024-12-31
申请号：US17898887
申请日：2022-08-30
Applicant: NVIDIA Corporation
Inventor： Clement Farabet , John Zedlewski , Zachary Taylor , Greg Heinrich , Claire Delaunay , Mark Daly , Matthew Campbell , Curtis Beeson , Gary Hicok , Michael Cox , Rev Lebaredian , Tony Tamasi , David Auld
IPC: G06F9/455 , G06F18/2413 , G06N3/045 , G06N3/063 , G06N3/08 , G06N20/00 , G06V10/44 , G06V10/764 , G06V10/82 , G06V20/56
Abstract: In various examples, physical sensor data may be generated by a vehicle in a real-world environment. The physical sensor data may be used to train deep neural networks (DNNs). The DNNs may then be tested in a simulated environment—in some examples using hardware configured for installation in a vehicle to execute an autonomous driving software stack—to control a virtual vehicle in the simulated environment or to otherwise test, verify, or validate the outputs of the DNNs. Prior to use by the DNNs, virtual sensor data generated by virtual sensors within the simulated environment may be encoded to a format consistent with the format of the physical sensor data generated by the vehicle.
-
公开(公告)号：US20230004801A1
公开(公告)日：2023-01-05
申请号：US17898887
申请日：2022-08-30
Applicant: NVIDIA Corporation
Inventor： Clement Farabet , John Zedlewski , Zachary Taylor , Greg Heinrich , Claire Delaunay , Mark Daly , Matthew Campbell , Curtis Beeson , Gary Hicok , Michael Cox , Rev Lebaredian , Tony Tamasi , David Auld
Abstract: In various examples, physical sensor data may be generated by a vehicle in a real-world environment. The physical sensor data may be used to train deep neural networks (DNNs). The DNNs may then be tested in a simulated environment—in some examples using hardware configured for installation in a vehicle to execute an autonomous driving software stack—to control a virtual vehicle in the simulated environment or to otherwise test, verify, or validate the outputs of the DNNs. Prior to use by the DNNs, virtual sensor data generated by virtual sensors within the simulated environment may be encoded to a format consistent with the format of the physical sensor data generated by the vehicle.
-
Patent Agency Ranking
公开(公告)号：US20190266418A1
公开(公告)日：2019-08-29
申请号：US16286329
申请日：2019-02-26
Applicant: NVIDIA Corporation
Inventor： Yifang Xu , Xin Liu , Chia-Chih Chen , Carolina Parada , Davide Onofrio , Minwoo Park , Mehdi Sajjadi Mohammadabadi , Vijay Chintalapudi , Ozan Tonkal , John Zedlewski , Pekka Janis , Jan Nikolaus Fritsch , Gordon Grigor , Zuoguan Wang , I-Kuei Chen , Miguel Sainz
Abstract: In various examples, sensor data representative of an image of a field of view of a vehicle sensor may be received and the sensor data may be applied to a machine learning model. The machine learning model may compute a segmentation mask representative of portions of the image corresponding to lane markings of the driving surface of the vehicle. Analysis of the segmentation mask may be performed to determine lane marking types, and lane boundaries may be generated by performing curve fitting on the lane markings corresponding to each of the lane marking types. The data representative of the lane boundaries may then be sent to a component of the vehicle for use in navigating the vehicle through the driving surface.
-
公开(公告)号：US20230267701A1
公开(公告)日：2023-08-24
申请号：US18309882
申请日：2023-05-01
Applicant: NVIDIA Corporation
Inventor： Yifang Xu , Xin Liu , Chia-Chin Chen , Carolina Parada , Davide Onofrio , Minwoo Park , Mehdi Sajjadi Mohammadabadi , Vijay Chintalapudi , Ozan Tonkal , John Zedlewski , Pekka Janis , Jan Nikolaus Fritsch , Gordon Grigor , Zuoguan Wang , I-Kuei Chen , Miguel Sainz
IPC: G06V10/44 , G06T7/10 , G05D1/00 , G06N3/084 , G05D1/02 , G06V20/56 , G06V10/46 , G06V20/40 , G06F18/2413 , G06V10/764 , G06V10/82
CPC classification number: G06V10/44 , G06T7/10 , G05D1/0088 , G06N3/084 , G05D1/0221 , G06V20/588 , G06V10/46 , G06V10/457 , G06V20/41 , G06F18/24143 , G06V10/764 , G06V10/82 , G06V10/471
Abstract: In various examples, sensor data representative of an image of a field of view of a vehicle sensor may be received and the sensor data may be applied to a machine learning model. The machine learning model may compute a segmentation mask representative of portions of the image corresponding to lane markings of the driving surface of the vehicle. Analysis of the segmentation mask may be performed to determine lane marking types, and lane boundaries may be generated by performing curve fitting on the lane markings corresponding to each of the lane marking types. The data representative of the lane boundaries may then be sent to a component of the vehicle for use in navigating the vehicle through the driving surface.
-
公开(公告)号：US11436484B2
公开(公告)日：2022-09-06
申请号：US16366875
申请日：2019-03-27
Applicant: NVIDIA Corporation
Inventor： Clement Farabet , John Zedlewski , Zachary Taylor , Greg Heinrich , Claire Delaunay , Mark Daly , Matthew Campbell , Curtis Beeson , Gary Hicok , Michael Cox , Rev Lebaredian , Tony Tamasi , David Auld
Abstract: In various examples, physical sensor data may be generated by a vehicle in a real-world environment. The physical sensor data may be used to train deep neural networks (DNNs). The DNNs may then be tested in a simulated environment—in some examples using hardware configured for installation in a vehicle to execute an autonomous driving software stack—to control a virtual vehicle in the simulated environment or to otherwise test, verify, or validate the outputs of the DNNs. Prior to use by the DNNs, virtual sensor data generated by virtual sensors within the simulated environment may be encoded to a format consistent with the format of the physical sensor data generated by the vehicle.
-
公开(公告)号：US12266148B2
公开(公告)日：2025-04-01
申请号：US18309882
申请日：2023-05-01
Applicant: NVIDIA Corporation
Inventor： Yifang Xu , Xin Liu , Chia-Chih Chen , Carolina Parada , Davide Onofrio , Minwoo Park , Mehdi Sajjadi Mohammadabadi , Vijay Chintalapudi , Ozan Tonkal , John Zedlewski , Pekka Janis , Jan Nikolaus Fritsch , Gordon Grigor , Zuoguan Wang , I-Kuei Chen , Miguel Sainz
IPC: G06V10/44 , G05D1/00 , G06F18/2413 , G06N3/084 , G06T7/10 , G06V10/46 , G06V10/764 , G06V10/82 , G06V20/40 , G06V20/56
Abstract: In various examples, sensor data representative of an image of a field of view of a vehicle sensor may be received and the sensor data may be applied to a machine learning model. The machine learning model may compute a segmentation mask representative of portions of the image corresponding to lane markings of the driving surface of the vehicle. Analysis of the segmentation mask may be performed to determine lane marking types, and lane boundaries may be generated by performing curve fitting on the lane markings corresponding to each of the lane marking types. The data representative of the lane boundaries may then be sent to a component of the vehicle for use in navigating the vehicle through the driving surface.
-
公开(公告)号：US20190244060A1
公开(公告)日：2019-08-08
申请号：US16265725
申请日：2019-02-01
Applicant: NVIDIA Corporation
Inventor： Aysegul Dundar , Ming-Yu Liu , Ting-Chun Wang , John Zedlewski , Jan Kautz
CPC classification number: G06K9/6256 , G06K9/3233 , G06K9/6267 , G06N3/0454 , G06N3/08 , G06T3/0056 , G06T7/10
Abstract: A style transfer neural network may be used to generate stylized synthetic images, where real images provide the style (e.g., seasons, weather, lighting) for transfer to synthetic images. The stylized synthetic images may then be used to train a recognition neural network. In turn, the trained neural network may be used to predict semantic labels for the real images, providing recognition data for the real images. Finally, the real training dataset (real images and predicted recognition data) and the synthetic training dataset are used by the style transfer neural network to generate stylized synthetic images. The training of the neural network, prediction of recognition data for the real images, and stylizing of the synthetic images may be repeated for a number of iterations. The stylization operation more closely aligns a covariate of the synthetic images to the covariate of the real images, improving accuracy of the recognition neural network.
-
-
-
-
-
-
-
-
-
Search Results
14
records
(took 0.018 seconds)
