Vision-based Vehicle Lane-keeping Control System

碩士 === 國立清華大學 === 動力機械工程學系 === 94 === In this work, a control system of lane keeping by utilizing lane markers in the image as the image characteristics and the designed Proportional-Derivative (PD) or Proportional-Integral-Derivative (PID) controllers has been presented. The white lane markers pain...

Full description

Bibliographic Details
Main Authors: Yu Chiu, 邱瑜
Other Authors: Rongshun Chen
Format: Others
Language:en_US
Published: 2006
Online Access:http://ndltd.ncl.edu.tw/handle/78330048874644996368
Description
Summary:碩士 === 國立清華大學 === 動力機械工程學系 === 94 === In this work, a control system of lane keeping by utilizing lane markers in the image as the image characteristics and the designed Proportional-Derivative (PD) or Proportional-Integral-Derivative (PID) controllers has been presented. The white lane markers painted on the road were seized as the input image characteristics, and the time needed to handle the input data was decreased by using grayscale transformation, resizing, and Region of Interest (ROI). Then, a PD or PID controller is designed to keep the vehicle driving along the center line of current lane and the steering angle was employed as controller output. The proposed method in this thesis eliminated special lane marks as the input image characteristics, and was able to detect current vehicle orientation and lateral position in the lane without any special hardware. These advantages improved the current lane keeping system and could reduce the amount of traffic accidents.