A computer system/method program obtains two sets of data, a first set comprising data corresponding to a synthetic image representing a birds-eye-view of an area generated based on sensor data of a vehicle in the area, wherein the synthetic image identifies an object in the area and a second data set corresponding a camera image representing a viewpoint of the vehicle in the area, wherein the camera image depicts the object. These two sets are used to train a machine leaming model including at least one neural network to process the sets of data and which accepts as input data from each of the data sets to provide as output a predicted motion of the object corresponding to the input data. The trained model is then transmitted to a destination vehicle configured to apply the trained model to sensor data of the destination vehicle to predict motion of a target object identified within the sensor data.
Motion prediction in an autonomous vehicle using fused synthetic and camera images
2023-12-06
Patent
Elektronische Ressource
Englisch
IPC: | G06T Bilddatenverarbeitung oder Bilddatenerzeugung allgemein , IMAGE DATA PROCESSING OR GENERATION, IN GENERAL / B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion |
MOTION PREDICTION IN AN AUTONOMOUS VEHICLE USING FUSED SYNTHETIC AND CAMERA IMAGES
Europäisches Patentamt | 2023
|MOTION PREDICTION IN AN AUTONOMOUS VEHICLE USING FUSED SYNTHETIC AND CAMERA IMAGES
Europäisches Patentamt | 2023
|PARTITIONING IMAGES OBTAINED FROM AN AUTONOMOUS VEHICLE CAMERA
Europäisches Patentamt | 2021
|PARTITIONING IMAGES OBTAINED FROM AN AUTONOMOUS VEHICLE CAMERA
Europäisches Patentamt | 2021
|Partitioning images obtained from an autonomous vehicle camera
Europäisches Patentamt | 2022
|