A method for generating training data comprises executing a simulation process, wherein the process includes traversing a virtual camera (sensor data) over a virtual road surface or through a virtual driving environment having at least one virtual precipitation condition and at least one virtual no precipitation condition such as rain, snow, fog. Recording frames of image data streams 42 corresponding to signals output by the virtual cameras during the traversing; converting the recorded frames to training data by annotating 44 each frame with ground truth data indicating a virtual precipitation condition. Preferably the virtual camera is moved with respect to the virtual driving environment as dictated by a vehicle-motion model modeling motion of a vehicle driving through the virtual driving environment while carrying the virtual camera. The virtual sensor data 12 may correspond to what a real sensor would have output had it sensed the virtual driving environment in the real world.
Virtual sensor-data-generation system and method supporting development of vision-based rain-detection algorithms
2018-04-04
Patent
Electronic Resource
English
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 / H04N PICTORIAL COMMUNICATION, e.g. TELEVISION , Bildübertragung, z.B. Fernsehen |
Effect of Adherent Rain on Vision-Based Object Detection Algorithms
British Library Conference Proceedings | 2020
|Effect of Adherent Rain on Vision-Based Object Detection Algorithms
SAE Technical Papers | 2020
|Effect of Adherent Rain on Vision-Based Object Detection Algorithms
British Library Conference Proceedings | 2020
|European Patent Office | 2021
|European Patent Office | 2018
|