公开(公告)号：US12235353B2

公开(公告)日：2025-02-25

申请号：US17454389

申请日：2021-11-10

Applicant: NVIDIA Corporation

Inventor： Gang Pan ,  Joachim Pehserl ,  Dong Zhang ,  Baris Evrim Demiroz ,  Samuel Rupp Ogden ,  Tae Eun Choe ,  Sangmin Oh

IPC: G01S13/931 ,  G01S13/86 ,  G01S17/86 ,  G01S17/931

Abstract: In various examples, a hazard detection system fuses outputs from multiple sensors over time to determine a probability that a stationary object or hazard exists at a location. The system may then use sensor data to calculate a detection bounding shape for detected objects and, using the bounding shape, may generate a set of particles, each including a confidence value that an object exists at a corresponding location. The system may then capture additional sensor data by one or more sensors of the ego-machine that are different from those used to capture the first sensor data. To improve the accuracy of the confidences of the particles, the system may determine a correspondence between the first sensor data and the additional sensor data (e.g., depth sensor data), which may be used to filter out a portion of the particles and improve the depth predictions corresponding to the object.

公开(公告)号：US20230139772A1

公开(公告)日：2023-05-04

申请号：US17452749

申请日：2021-10-28

Applicant: NVIDIA Corporation

Inventor： Kang Wang ,  Yue Wu ,  Minwoo Park ,  Gang Pan

IPC: G06T17/20 ,  G06T7/11 ,  G06K9/62 ,  G06T7/40 ,  G06N3/08 ,  B60W60/00 ,  B60W50/06 ,  B60W40/06 ,  B60W30/14

Abstract: In various examples, to support training a deep neural network (DNN) to predict a dense representation of a 3D surface structure of interest, a training dataset is generated using a simulated environment. For example, a simulation may be run to simulate a virtual world or environment, render frames of virtual sensor data (e.g., images), and generate corresponding depth maps and segmentation masks (identifying a component of the simulated environment such as a road). To generate input training data, 3D structure estimation may be performed on a rendered frame to generate a representation of a 3D surface structure of the road. To generate corresponding ground truth training data, a corresponding depth map and segmentation mask may be used to generate a dense representation of the 3D surface structure.

公开(公告)号：US20230135234A1

公开(公告)日：2023-05-04

申请号：US17452752

申请日：2021-10-28

Applicant: NVIDIA Corporation

Inventor： Kang Wang ,  Yue Wu ,  Minwoo Park ,  Gang Pan

IPC: G06K9/00 ,  G06K9/62 ,  G01S17/931 ,  G01S17/89

Abstract: In various examples, to support training a deep neural network (DNN) to predict a dense representation of a 3D surface structure of interest, a training dataset is generated from real-world data. For example, one or more vehicles may collect image data and LiDAR data while navigating through a real-world environment. To generate input training data, 3D surface structure estimation may be performed on captured image data to generate a sparse representation of a 3D surface structure of interest (e.g., a 3D road surface). To generate corresponding ground truth training data, captured LiDAR data may be smoothed, subject to outlier removal, subject to triangulation to filling missing values, accumulated from multiple LiDAR sensors, aligned with corresponding frames of image data, and/or annotated to identify 3D points on the 3D surface of interest, and the identified 3D points may be projected to generate a dense representation of the 3D surface structure.