Real-time detection of lanes and boundaries by autonomous vehicles

US11676364B2 · kind B2 · utility

Assignee

• NVIDIA Corporation · US

Inventors

• Yifang Xu · San Jose, US
• Xin Liu · Pleasanton, US
• Chia-Chih Chen · Hsinchu, TW
• Carolina Parada · Boulder, US
• Davide Onofrio · San Francisco, US
• Minwoo Park · Saratoga, US
• Mehdi Sajjadi Mohammadabadi · Santa Clara, US
• Vijay Chintalapudi · Sunnyvale, US
• Ozan Tonkal · Munich, DE
• John Zedlewski · San Francisco, US
• Pekka Janis · Sandbacka, FI
• Jan Nikolaus Fritsch · Santa Clara, US
• Gordon Grigor · San Francisco, US
• Zuoguan Wang · Los Gatos, US
• I-Kuei Chen · Milpitas, US
• Miguel Sainz · Tlaquepaque, MX

Key dates

• Filing date: Apr 5, 2021
• Grant date: Jun 13, 2023
• Expiry date: Apr 30, 2041

Classification

• Technology area (CPC G): Physics
• CPC primary: G06V10/471
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

In various examples, sensor data representative of an image of a field of view of a vehicle sensor may be received and the sensor data may be applied to a machine learning model. The machine learning model may compute a segmentation mask representative of portions of the image corresponding to lane markings of the driving surface of the vehicle. Analysis of the segmentation mask may be performed to determine lane marking types, and lane boundaries may be generated by performing curve fitting on the lane markings corresponding to each of the lane marking types. The data representative of the lane boundaries may then be sent to a component of the vehicle for use in navigating the vehicle through the driving surface.