Systems and methods for deep learning-based beam control are provided. Sensor data associated with the environment and corresponding detected objects from a recognition system are obtained. Object features and image features are extracted. The extracted object and image features are fused into fused features. A beam control state is predicted according to the fused features, where the beam control state represents the high beam illumination intensity or low beam illumination intensity of a light emitting device.
딥러닝 기반 빔 제어를 위한 시스템들 및 방법들이 제공된다. 환경과 연관된 센서 데이터 및 인지 시스템으로부터의 대응하는 검출된 대상체들이 획득된다. 대상체 특징들 및 이미지 특징들이 추출된다. 추출된 대상체 특징들과 이미지 특징들이 융합된 특징들로 융합된다. 융합된 특징들에 따라 빔 제어 상태가 예측되며, 여기서 빔 제어 상태는 발광 소자의 하이 빔 조명 강도 또는 로우 빔 조명 강도를 나타낸다.
DEEP LEARNING BASED BEAM CONTROL FOR AUTONOMOUS VEHICLES
자율 주행 차량을 위한 딥 러닝 기반 빔 제어
2023-05-25
Patent
Elektronische Ressource
Koreanisch
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 / B60Q ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL , Anordnung von Signal- oder Beleuchtungsvorrichtungen, deren Einbau oder Halterung oder deren Schaltkreise bei Fahrzeugen allgemein / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen |
Deep learning based beam control for autonomous vehicles
Europäisches Patentamt | 2023
|Deep learning based beam control for autonomous vehicles
Europäisches Patentamt | 2023
|Deep Learning Based Beam Control for Autonomous Vehicles
Europäisches Patentamt | 2023
|Deep Learning & Autonomous Vehicles
TIBKAT | 2018
|