Self-supervised 3D keypoint learning for ego-motion estimation

A method for learning depth-aware keypoints and associated descriptors from monocular video for ego-motion estimation is described. The method includes training a keypoint network and a depth network to learn depth-aware keypoints and the associated descriptors. The training is based on a target ima...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Pillai, Sudeep, Guizilini, Vitor, Ambrus, Rares A, Tang, Jiexiong, Gaidon, Adrien David, Kim, Hanme
Format:	Patent
Sprache:	eng
Schlagworte:	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE ORDIFFERENT FUNCTION CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PERFORMING OPERATIONS PHYSICS ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TOTHE CONTROL OF A PARTICULAR SUB-UNIT TRANSPORTING VEHICLES IN GENERAL
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	A method for learning depth-aware keypoints and associated descriptors from monocular video for ego-motion estimation is described. The method includes training a keypoint network and a depth network to learn depth-aware keypoints and the associated descriptors. The training is based on a target image and a context image from successive images of the monocular video. The method also includes lifting 2D keypoints from the target image to learn 3D keypoints based on a learned depth map from the depth network. The method further includes estimating ego-motion from the target image to the context image based on the learned 3D keypoints.