公开(公告)号：US11769052B2

公开(公告)日：2023-09-26

申请号：US17449310

申请日：2021-09-29

Applicant: NVIDIA Corporation

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

IPC: G06K9/00 ,  G06N3/08 ,  B60W30/14 ,  B60W60/00 ,  G06V20/56 ,  G06F18/214 ,  G06V10/762

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

Abstract: 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：US20230186640A1

公开(公告)日：2023-06-15

申请号：US17551986

申请日：2021-12-15

Applicant: NVIDIA Corporation

Inventor： Mehmet K. Kocamaz ,  Ke Xu ,  Sangmin Oh ,  Junghyun Kwon

IPC: G06V20/58 ,  G06K9/62 ,  G06V10/82 ,  G06V10/46 ,  G06V10/22 ,  G06T7/246 ,  B60W60/00 ,  G06N3/08

CPC classification number: G06V20/58 ,  G06K9/6232 ,  G06V10/82 ,  G06V10/46 ,  G06V10/225 ,  G06T7/246 ,  B60W60/001 ,  G06N3/08 ,  G06T2207/30252 ,  G06T2207/20084 ,  G06T2207/20081 ,  B60W2420/42

Abstract: In various examples, live perception from sensors of a vehicle may be leveraged to generate object tracking paths for the vehicle to facilitate navigational controls in real-time or near real-time. For example, a deep neural network (DNN) may be trained to compute various outputs—such as feature descriptor maps including feature descriptor vectors corresponding to objects included in a sensor(s) field of view. The outputs may be decoded and/or otherwise post-processed to reconstruct object tracking and to determine proposed or potential paths for navigating the vehicle.

公开(公告)号：US20220253706A1

公开(公告)日：2022-08-11

申请号：US17723195

申请日：2022-04-18

Applicant: NVIDIA Corporation

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

IPC: G06N3/08 ,  B60W30/14 ,  B60W60/00 ,  G06K9/62 ,  G06V20/56

Abstract: 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：US20220108465A1

公开(公告)日：2022-04-07

申请号：US17522624

申请日：2021-11-09

Applicant: NVIDIA Corporation

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

IPC: G06T7/536 ,  G06V20/58

Abstract: 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：US20220092855A1

公开(公告)日：2022-03-24

申请号：US17457825

申请日：2021-12-06

Applicant: NVIDIA Corporation

Inventor： Dongwoo Lee ,  Junghyun Kwon ,  Sangmin Oh ,  Wenchao Zheng ,  Hae-Jong Seo ,  David Nister ,  Berta Rodriguez Hervas

IPC: G06T17/30 ,  G06T7/40

Abstract: A neural network may be used to determine corner points of a skewed polygon (e.g., as displacement values to anchor box corner points) that accurately delineate a region in an image that defines a parking space. Further, the neural network may output confidence values predicting likelihoods that corner points of an anchor box correspond to an entrance to the parking spot. The confidence values may be used to select a subset of the corner points of the anchor box and/or skewed polygon in order to define the entrance to the parking spot. A minimum aggregate distance between corner points of a skewed polygon predicted using the CNN(s) and ground truth corner points of a parking spot may be used simplify a determination as to whether an anchor box should be used as a positive sample for training.

公开(公告)号：US20220019893A1

公开(公告)日：2022-01-20

申请号：US17449310

申请日：2021-09-29

Applicant: NVIDIA Corporation

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

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

Abstract: 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：US20210272304A1

公开(公告)日：2021-09-02

申请号：US16728598

申请日：2019-12-27

Applicant: NVIDIA Corporation

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

IPC: G06T7/536 ,  G06K9/00

Abstract: 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：US20210264175A1

公开(公告)日：2021-08-26

申请号：US17187228

申请日：2021-02-26

Applicant: NVIDIA Corporation

Inventor： Dong Zhang ,  Sangmin Oh ,  Junghyun Kwon ,  Baris Evrim Demiroz ,  Tae Eun Choe ,  Minwoo Park ,  Chethan Ningaraju ,  Hao Tsui ,  Eric Viscito ,  Jagadeesh Sankaran ,  Yongqing Liang

IPC: G06K9/00 ,  G06K9/62 ,  G06K9/32 ,  G06N3/08 ,  B60W60/00

Abstract: Systems and methods are disclosed that use a geometric approach to detect objects on a road surface. A set of points within a region of interest between a first frame and a second frame are captured and tracked to determine a difference in location between the set of points in two frames. The first frame may be aligned with the second frame and the first pixel values of the first frame may be compared with the second pixel values of the second frame to generate a disparity image including third pixels. One or more subsets of the third pixels that have an disparity image value about a first threshold may be combined, and the third pixels may be scored and associated with disparity values for each pixel of the one or more subsets of the third pixels. A bounding shape may be generated based on the scoring that corresponds to the object.

公开(公告)号：US20210156963A1

公开(公告)日：2021-05-27

申请号：US16836618

申请日：2020-03-31

Applicant: NVIDIA Corporation

Inventor： Alexander Popov ,  Nikolai Smolyanskiy ,  Ryan Oldja ,  Shane Murray ,  Tilman Wekel ,  David Nister ,  Joachim Pehserl ,  Ruchi Bhargava ,  Sangmin Oh

IPC: G01S7/41 ,  G01S13/86 ,  G01S13/89 ,  G06N3/08 ,  G06N3/04

Abstract: In various examples, a deep neural network(s) (e.g., a convolutional neural network) may be trained to detect moving and stationary obstacles from RADAR data of a three dimensional (3D) space. In some embodiments, ground truth training data for the neural network(s) may be generated from LIDAR data. More specifically, a scene may be observed with RADAR and LIDAR sensors to collect RADAR data and LIDAR data for a particular time slice. The RADAR data may be used for input training data, and the LIDAR data associated with the same or closest time slice as the RADAR data may be annotated with ground truth labels identifying objects to be detected. The LIDAR labels may be propagated to the RADAR data, and LIDAR labels containing less than some threshold number of RADAR detections may be omitted. The (remaining) LIDAR labels may be used to generate ground truth data.

公开(公告)号：US20200294310A1

公开(公告)日：2020-09-17

申请号：US16820164

申请日：2020-03-16

Applicant: NVIDIA CORPORATION

Inventor： Dongwoo Lee ,  Junghyun Kwon ,  Sangmin Oh ,  Wenchao Zheng ,  Hae-Jong Seo ,  David Nister ,  Berta Rodriguez Hervas

IPC: G06T17/30 ,  G06T7/40

Abstract: A neural network may be used to determine corner points of a skewed polygon (e.g., as displacement values to anchor box corner points) that accurately delineate a region in an image that defines a parking space. Further, the neural network may output confidence values predicting likelihoods that corner points of an anchor box correspond to an entrance to the parking spot. The confidence values may be used to select a subset of the corner points of the anchor box and/or skewed polygon in order to define the entrance to the parking spot. A minimum aggregate distance between corner points of a skewed polygon predicted using the CNN(s) and ground truth corner points of a parking spot may be used simplify a determination as to whether an anchor box should be used as a positive sample for training.