A method provided for 3D object localization predicts pairs of 2D bounding boxes. Each pair corresponds to a detected object in each of the two consecutive input monocular images. The method generates, for each detected object, a relative motion estimation specifying a relative motion between the two images. The method constructs an object cost volume by aggregating temporal features from the two images using the pairs of 2D bounding boxes and the relative motion estimation to predict a range of object depth candidates and a confidence score for each object depth candidate and an object depth from the object depth candidates. The method updates the relative motion estimation based on the object cost volume and the object depth to provide a refined object motion and a refined object depth. The method reconstructs a 3D bounding box for each detected object based on the refined object motion and refined object depth.
MONOCULAR 3D OBJECT LOCALIZATION FROM TEMPORAL AGGREGATION
2022-03-03
Patent
Electronic Resource
English
IPC: | 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 / G06K Erkennen von Daten , RECOGNITION OF DATA / G06T Bilddatenverarbeitung oder Bilddatenerzeugung allgemein , IMAGE DATA PROCESSING OR GENERATION, IN GENERAL / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
Monocular 3D object localization from temporal aggregation
European Patent Office | 2024
|An Innovative Monocular Mobile Object Self-localization Approach Based on Ceiling Vision
BASE | 2021
|Monocular Localization of a Mobile Robot
British Library Conference Proceedings | 1993
|