The goal of the project is to create an image processing algorithm using Advanced computer vision techniques, to Correct distorted images/ videos, correctly identify lane lines on the road, calculate radius of curvature of road and also position of the vehicle with respect to center. The algorithm should be robust enough to work on a series of images (video) with varying conditions like changing light conditions and color variations from shadows, etc.
-
Code for the algorithm is contained in the IPython notebook as well as python script Python Script File
-
A writeup detailing the results of the project and describing the procedure for identifying the lane lines.
-
The processed videos (the same algorithm was used to process video):
- A video with a Annotated project video
This project was developed using Python 3.5. The IPython notebook can be run using Jupyter Notebooks. The project depends on the,