公开(公告)号：US20240232616A9

公开(公告)日：2024-07-11

申请号：US18343291

申请日：2023-06-28

申请人： NVIDIA Corporation

发明人： Yilin Yang ,  Bala Siva Sashank Jujjavarapu ,  Pekka Janis ,  Zhaoting Ye ,  Sangmin Oh ,  Minwoo Park ,  Daniel Herrera Castro ,  Tommi Koivisto ,  David Nister

IPC分类号： G06N3/08 ,  B60W30/14 ,  B60W60/00 ,  G06F18/214 ,  G06V10/762 ,  G06V20/56

CPC分类号： G06N3/08 ,  B60W30/14 ,  B60W60/0011 ,  G06F18/2155 ,  G06V10/763 ,  G06V20/56

摘要： In various examples, a deep neural network (DNN) is trained to accurately predict, in deployment, distances to objects and obstacles using image data alone. The DNN may be trained with ground truth data that is generated and encoded using sensor data from any number of depth predicting sensors, such as, without limitation, RADAR sensors, LIDAR sensors, and/or SONAR sensors. Camera adaptation algorithms may be used in various embodiments to adapt the DNN for use with image data generated by cameras with varying parameters—such as varying fields of view. In some examples, a post-processing safety bounds operation may be executed on the predictions of the DNN to ensure that the predictions fall within a safety-permissible range.

公开(公告)号：US11704890B2

公开(公告)日：2023-07-18

申请号：US17522624

申请日：2021-11-09

申请人： NVIDIA Corporation

发明人： Yilin Yang ,  Bala Siva Jujjavarapu ,  Pekka Janis ,  Zhaoting Ye ,  Sangmin Oh ,  Minwoo Park ,  Daniel Herrera Castro ,  Tommi Koivisto ,  David Nister

IPC分类号： G06K9/00 ,  G06V10/25 ,  G06T7/536 ,  G06V20/58 ,  G06V10/70 ,  G06V10/82 ,  G06V10/44

CPC分类号： G06V10/25 ,  G06T7/536 ,  G06V10/454 ,  G06V10/70 ,  G06V10/82 ,  G06V20/58 ,  G06T2207/20084 ,  G06T2207/30261

摘要： In various examples, a deep neural network (DNN) is trained—using image data alone—to accurately predict distances to objects, obstacles, and/or a detected free-space boundary. The DNN may be trained with ground truth data that is generated using sensor data representative of motion of an ego-vehicle and/or sensor data from any number of depth predicting sensors—such as, without limitation, RADAR sensors, LIDAR sensors, and/or SONAR sensors. The DNN may be trained using two or more loss functions each corresponding to a particular portion of the environment that depth is predicted for, such that—in deployment—more accurate depth estimates for objects, obstacles, and/or the detected free-space boundary are computed by the DNN. In some embodiments, a sampling algorithm may be used to sample depth values corresponding to an input resolution of the DNN from a predicted depth map of the DNN at an output resolution of the DNN.

公开(公告)号：US11308338B2

公开(公告)日：2022-04-19

申请号：US16728595

申请日：2019-12-27

申请人： NVIDIA Corporation

发明人： Yilin Yang ,  Bala Siva Sashank Jujjavarapu ,  Pekka Janis ,  Zhaoting Ye ,  Sangmin Oh ,  Minwoo Park ,  Daniel Herrera Castro ,  Tommi Koivisto ,  David Nister

IPC分类号： G06K9/00 ,  G06N3/08 ,  G06N3/04 ,  G06K9/52 ,  G06K9/20 ,  G06K9/62

摘要： In various examples, a deep neural network (DNN) is trained to accurately predict, in deployment, distances to objects and obstacles using image data alone. The DNN may be trained with ground truth data that is generated and encoded using sensor data from any number of depth predicting sensors, such as, without limitation, RADAR sensors, LIDAR sensors, and/or SONAR sensors. Camera adaptation algorithms may be used in various embodiments to adapt the DNN for use with image data generated by cameras with varying parameters—such as varying fields of view. In some examples, a post-processing safety bounds operation may be executed on the predictions of the DNN to ensure that the predictions fall within a safety-permissible range.

公开(公告)号：US10997435B2

公开(公告)日：2021-05-04

申请号：US16535440

申请日：2019-08-08

申请人： NVIDIA Corporation

发明人： Josh Abbott ,  Miguel Sainz Serra ,  Zhaoting Ye ,  David Nister

IPC分类号： G06K9/00 ,  G06T11/20 ,  G06T7/12 ,  G06T7/70

摘要： In various examples, object fence corresponding to objects detected by an ego-vehicle may be used to determine overlap of the object fences with lanes on a driving surface. A lane mask may be generated corresponding to the lanes on the driving surface, and the object fences may be compared to the lanes of the lane mask to determine the overlap. Where an object fence is located in more than one lane, a boundary scoring approach may be used to determine a ratio of overlap of the boundary fence, and thus the object, with each of the lanes. The overlap with one or more lanes for each object may be used to determine lane assignments for the objects, and the lane assignments may be used by the ego-vehicle to determine a path or trajectory along the driving surface.

公开(公告)号：US20240362928A1

公开(公告)日：2024-10-31

申请号：US18766127

申请日：2024-07-08

申请人： NVIDIA Corporation

发明人： Josh Abbott ,  Miguel Sainz Serra ,  Zhaoting Ye ,  David Nister

IPC分类号： G06V20/56 ,  G06T7/12 ,  G06T7/70 ,  G06T11/20

CPC分类号： G06V20/588 ,  G06T7/12 ,  G06T7/70 ,  G06T11/20 ,  G06T2207/20084 ,  G06T2207/20132 ,  G06T2207/30256 ,  G06T2210/12

摘要： In various examples, object fence corresponding to objects detected by an ego-vehicle may be used to determine overlap of the object fences with lanes on a driving surface. A lane mask may be generated corresponding to the lanes on the driving surface, and the object fences may be compared to the lanes of the lane mask to determine the overlap. Where an object fence is located in more than one lane, a boundary scoring approach may be used to determine a ratio of overlap of the boundary fence, and thus the object, with each of the lanes. The overlap with one or more lanes for each object may be used to determine lane assignments for the objects, and the lane assignments may be used by the ego-vehicle to determine a path or trajectory along the driving surface.

公开(公告)号：US20240135173A1

公开(公告)日：2024-04-25

申请号：US18343291

申请日：2023-06-27

申请人： NVIDIA Corporation

发明人： Yilin Yang ,  Bala Siva Sashank Jujjavarapu ,  Pekka Janis ,  Zhaoting Ye ,  Sangmin Oh ,  Minwoo Park ,  Daniel Herrera Castro ,  Tommi Koivisto ,  David Nister

IPC分类号： G06N3/08 ,  B60W30/14 ,  B60W60/00 ,  G06F18/214 ,  G06V10/762 ,  G06V20/56

CPC分类号： G06N3/08 ,  B60W30/14 ,  B60W60/0011 ,  G06F18/2155 ,  G06V10/763 ,  G06V20/56

摘要： In various examples, a deep neural network (DNN) is trained to accurately predict, in deployment, distances to objects and obstacles using image data alone. The DNN may be trained with ground truth data that is generated and encoded using sensor data from any number of depth predicting sensors, such as, without limitation, RADAR sensors, LIDAR sensors, and/or SONAR sensors. Camera adaptation algorithms may be used in various embodiments to adapt the DNN for use with image data generated by cameras with varying parameters—such as varying fields of view. In some examples, a post-processing safety bounds operation may be executed on the predictions of the DNN to ensure that the predictions fall within a safety-permissible range.

公开(公告)号：US20230334317A1

公开(公告)日：2023-10-19

申请号：US18337854

申请日：2023-06-20

申请人： NVIDIA Corporation

发明人： Junghyun Kwon ,  Yilin Yang ,  Bala Siva Sashank Jujjavarapu ,  Zhaoting Ye ,  Sangmin Oh ,  Minwoo Park ,  David Nister

IPC分类号： G06N3/08 ,  B60W30/14 ,  B60W60/00 ,  G06V20/56 ,  G06F18/214 ,  G06V10/762

CPC分类号： G06N3/08 ,  B60W30/14 ,  B60W60/0011 ,  G06V20/56 ,  G06F18/2155 ,  G06V10/763

摘要： In various examples, a deep neural network (DNN) is trained—using image data alone—to accurately predict distances to objects, obstacles, and/or a detected free-space boundary. The DNN may be trained with ground truth data that is generated using sensor data representative of motion of an ego-vehicle and/or sensor data from any number of depth predicting sensors—such as, without limitation, RADAR sensors, LIDAR sensors, and/or SONAR sensors. The DNN may be trained using two or more loss functions each corresponding to a particular portion of the environment that depth is predicted for, such that—in deployment—more accurate depth estimates for objects, obstacles, and/or the detected free-space boundary are computed by the DNN.

公开(公告)号：US20200218979A1

公开(公告)日：2020-07-09

申请号：US16813306

申请日：2020-03-09

申请人： NVIDIA Corporation

发明人： Junghyun Kwon ,  Yilin Yang ,  Bala Siva Sashank Jujjavarapu ,  Zhaoting Ye ,  Sangmin Oh ,  Minwoo Park ,  David Nister

IPC分类号： G06N3/08 ,  B60W30/14 ,  G06K9/00 ,  G06K9/62 ,  B60W60/00

摘要： In various examples, a deep neural network (DNN) is trained—using image data alone—to accurately predict distances to objects, obstacles, and/or a detected free-space boundary. The DNN may be trained with ground truth data that is generated using sensor data representative of motion of an ego-vehicle and/or sensor data from any number of depth predicting sensors—such as, without limitation, RADAR sensors, LIDAR sensors, and/or SONAR sensors. The DNN may be trained using two or more loss functions each corresponding to a particular portion of the environment that depth is predicted for, such that—in deployment—more accurate depth estimates for objects, obstacles, and/or the detected free-space boundary are computed by the DNN. In some embodiments, a sampling algorithm may be used to sample depth values corresponding to an input resolution of the DNN from a predicted depth map of the DNN at an output resolution of the DNN.

公开(公告)号：US20210241005A1

公开(公告)日：2021-08-05

申请号：US17234487

申请日：2021-04-19

申请人： NVIDIA Corporation

发明人： Josh Abbott ,  Miguel Sainz Serra ,  Zhaoting Ye ,  David Nister

IPC分类号： G06K9/00 ,  G06T11/20 ,  G06T7/12 ,  G06T7/70

摘要： In various examples, object fence corresponding to objects detected by an ego-vehicle may be used to determine overlap of the object fences with lanes on a driving surface. A lane mask may be generated corresponding to the lanes on the driving surface, and the object fences may be compared to the lanes of the lane mask to determine the overlap. Where an object fence is located in more than one lane, a boundary scoring approach may be used to determine a ratio of overlap of the boundary fence, and thus the object, with each of the lanes. The overlap with one or more lanes for each object may be used to determine lane assignments for the objects, and the lane assignments may be used by the ego-vehicle to determine a path or trajectory along the driving surface.

公开(公告)号：US20210241004A1

公开(公告)日：2021-08-05

申请号：US17234475

申请日：2021-04-19

申请人： NVIDIA Corporation

发明人： Josh Abbott ,  Miguel Sainz Serra ,  Zhaoting Ye ,  David Nister

IPC分类号： G06K9/00 ,  G06T11/20 ,  G06T7/12 ,  G06T7/70

摘要： In various examples, object fence corresponding to objects detected by an ego-vehicle may be used to determine overlap of the object fences with lanes on a driving surface. A lane mask may be generated corresponding to the lanes on the driving surface, and the object fences may be compared to the lanes of the lane mask to determine the overlap. Where an object fence is located in more than one lane, a boundary scoring approach may be used to determine a ratio of overlap of the boundary fence, and thus the object, with each of the lanes. The overlap with one or more lanes for each object may be used to determine lane assignments for the objects, and the lane assignments may be used by the ego-vehicle to determine a path or trajectory along the driving surface.