Lane Detection Using Classical Computer Vision Methods
Objective To learn and apply classical computer vision techniques in application of automated driving. Udacity’s Self-Driving Car Nanodegree program has publicly released a problem that perfectly addresses this objective. The task is to identify the left and right lane marking in a vehicle’s front camera view. Once identified, lines are drawn on the camera image to visualize what the algorithm believes to be lane lines. For the assignment, it is recommended to follow the setup instructions i.e. using Anaconda and virtual environment however you are free to set up your own custom environment as long as deliverables are met. Resources and Instructions Environment Setup: See the README at https://github.com/udacity/CarND-Term1-Starter-Kit Assignment: See the README at https://github.com/udacity/CarND-LaneLines-P1 Clone/download the repository in a location of your choice and follow the instructions in the README file. As part of the assignment, you will develop the lane detection pipeline sequentially in a Jupyter notebook. The notebook explains all the development steps, code templates, and solution ideas. Simply follow the instructions in the README and the Jupyter notebook. Deliverable HTML output: In the Jupyter notebook, go to File > Download as > HTML (.html) Submit a ZIP file containing the HTML output, write-up, and sample output videos with lines identified. Please follow the naming convention of your zip file: a1_.zip
