Lane Departure Warning System Based on Future Virtual Driving Path Prediction
| Autor: | Chin-Sheng Chang, 張晉昇 |
|---|---|
| Rok vydání: | 2013 |
| Druh dokumentu: | 學位論文 ; thesis |
| Popis: | 101 Car accidents cause not just financial damage but physical damage as well. Many accidents occur as a result of negligent driving, by drivers who drift outside of the marked lanes. Recently, research has been done on Lane Departure Warning (LDW) systems with the aim of minimizing car accidents. This research using computer vision technology detects the lane markings, and to record the amount of deviation between the past vehicle route and lane marking, which are used to project future virtual lanes and then predict if the car is going to deviate from these lanes. This research using the Kalman filter to predict the updated lane marking, and to create the Region of Interest. Image preprocessing uses the k-means clustering method to proceed on binarization of the image and the Sobel operator to extract the edges of the images of the lane markings. Using morphology to reduce the noise in the marginal image, and enhance and repair lane marking. The ROI combined with Hough transform detect the lane markings from the preprocessed image, and using a least squares fit, the location of the lane markings is obtained. Finally, the grey theory is applied to predict the future of the vehicle virtual path. As the result of the experiment, it has clearly shown that the prediction of the vehicle route can further estimate the time to lane crossing (TLC), and the distance to lane crossing (DLC). By using TLC and DLC, it can help drivers to make sure they are driving in the correct lane, and prevent them from traffic accidents. The system is adaptive since the virtual path estimation is based on past driving paths. |
| Databáze: | Networked Digital Library of Theses & Dissertations |
| Externí odkaz: |
|