METHOD AND APPARATUS FOR COMPUTER VISION BASED ON NEURAL EXPOSURE FUSION FOR HIGH-DYNAMIC RANGE OBJECT DETECTION

METHOD AND APPARATUS FOR COMPUTER VISION BASED ON NEURAL EXPOSURE FUSION FOR HIGH-DYNAMIC RANGE OBJECT DETECTION

Departing from conventional HIDR image fusion approach, a learned task-driven fusion in the feature domain is disclosed. Instead of using a single companded image, the disclosed method exploits semantic features from all exposures learned in an end-to-end fashion with supervision from downstream det...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mannan, Fahim, Onzon, Emmanuel Luc Julien, Heide, Felix, Bömer, Maximilian Rufus
Format: Patent
Sprache:eng
Schlagworte:
CALCULATING
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Departing from conventional HIDR image fusion approach, a learned task-driven fusion in the feature domain is disclosed. Instead of using a single companded image, the disclosed method exploits semantic features from all exposures learned in an end-to-end fashion with supervision from downstream detection losses. The method outperforms all tested conventional HDR exposure fusion and auto-exposure methods in challenging automotive HIDR scenarios.