METHOD FOR MODELING ROADWAY AND METHOD FOR RECOGNIZING LANE MARKERS BASED ON THE SAME

Patent №

US 6,133,824

Granted

2000-10-17

Filed 1999

Owner

SAMSUNG ELECTRONICS CO., LTD.

Lab

AI components

1

vision

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

09379594

A method for modeling a roadway and a method for recognizing lane markers based on the modeling method. The method for recognizing lane markers of roadway for a vehicle by getting image information about the roadway and information about the speed and steering angle using a camera and a sensor attached to the vehicle, includes the steps of modeling the actual roadway on which the vehicle travels, as a structure having a plurality of rectangular plates linked to each other. The modeled plates are overlayed onto the image information about the actual roadway, photographed by the camera, pixels forming the lane markers are extracted, and linear lane marker information is then obtained from the pixels forming the land markers. Then, the linear lane marker information is overlayed onto the modeled plates to recalculate lane marker information using the plates as a frame, and predetermined limitations of the features of the lane markers are applied to the plates onto which the linear lane marker information has been overlayed, to optimize the lane marker information. Then, the roadway on which the vehicle is traveling, is remodeled using the optimized lane marker information, the information about the speed and steering angle of the vehicle measured by the sensor, and the information about the modeled plates, and the position and orientation of the remodeled plates are calculated. Therefore, roadway recognition can be easily achieved using a modeled structure of the roadway, in which a plurality of rectangular plates are linked. Also, the model roadway is repeatedly mapped onto the actual roadway image, so that reliability in recognition of roadway increases.

VisionB60Q 9/008G01S 13/931G06V 10/44G06V 20/588G01S 2013/932

AI classification

Vision1.00
Machine learning0.40
AI hardware0.01
Natural language0.00
Knowledge representation0.00
Speech0.00
Planning0.00
Evolutionary computation0.00

Ownership

SAMSUNG ELECTRONICS CO., LTD.

assignment · 102040278

Assignors

LEE, SUK-HAN, LEE, JAE-WON, SHIN, DONG-MOK, KWON, WOONG, KIM, DONG-YOON, ROH, KYOUNG-SIG

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC