Advanced Lane Finding Project
The goals / steps of this project are the following:
- Compute the camera calibration matrix and distortion coefficients given a set of chessboard images.
- Apply a distortion correction to raw images.
- Use color transforms, gradients, etc., to create a thresholded binary image.
- Apply a perspective transform to rectify binary image ("birds-eye view").
- Detect lane pixels and fit to find the lane boundary.
- Determine the curvature of the lane and vehicle position with respect to center.
- Warp the detected lane boundaries back onto the original image.
- Output visual display of the lane boundaries and numerical estimation of lane curvature and vehicle position.
Here I will consider the rubric points individually and describe how I addressed each point in my implementation.
1. Provide a Writeup / README that includes all the rubric points and how you addressed each one. You can submit your writeup as markdown or pdf. Here is a template writeup for this project you can use as a guide and a starting point.
You're reading it!
1. Briefly state how you computed the camera matrix and distortion coefficients. Provide an example of a distortion corrected calibration image.
The code for this step is contained in the first code cell of the IPython notebook located in "./examples/example.ipynb" (or in lines # through # of the file called some_file.py).
I start by preparing "object points", which will be the (x, y, z) coordinates of the chessboard corners in the world. Here I am assuming the chessboard is fixed on the (x, y) plane at z=0, such that the object points are the same for each calibration image. Thus, objp is just a replicated array of coordinates, and objpoints will be appended with a copy of it every time I successfully detect all chessboard corners in a test image. imgpoints will be appended with the (x, y) pixel position of each of the corners in the image plane with each successful chessboard detection.
I then used the output objpoints and imgpoints to compute the camera calibration and distortion coefficients using the cv2.calibrateCamera() function. I applied this distortion correction to the test image using the cv2.undistort() function and obtained this result:
To demonstrate this step, I will describe how I apply the distortion correction to one of the test images like this one:
2. Describe how (and identify where in your code) you used color transforms, gradients or other methods to create a thresholded binary image. Provide an example of a binary image result.
I used a combination of color and gradient thresholds to generate a binary image (thresholding steps at function pipeline). Here's an example of my output for this step.
3. Describe how (and identify where in your code) you performed a perspective transform and provide an example of a transformed image.
The code for my perspective transform includes a function called warper(). The warper() function takes as inputs an image (img), as well as source (src) and destination (dst) points. I chose to hardcode the source in the following manner, for the dest points, I calculated them by subtracting an offset from the 4 corners of the destination image.
src = np.float32([[560,470],[730,470],[1100,720],[200,720]])
dst = np.float32([[offset, offset], [img_size[0]-offset, offset],
[img_size[0]-offset, img_size[1]-offset],
[offset, img_size[1]-offset]])I verified that my perspective transform was working as expected by drawing the src and dst points onto a test image and its warped counterpart to verify that the lines appear parallel in the warped image.
!
Another example of a warped image:
4. Describe how (and identify where in your code) you identified lane-line pixels and fit their positions with a polynomial?
Then I did some other stuff and fit my lane lines with a 2nd order polynomial kinda like this:
5. Describe how (and identify where in your code) you calculated the radius of curvature of the lane and the position of the vehicle with respect to center.
I did this in the function calculate_curvature which takes the coefficients of the line and a previous n curvature values, if the curvature of the current frame cannot be calculated, I return the average of previous n values.
6. Provide an example image of your result plotted back down onto the road such that the lane area is identified clearly.
I implemented this step in the function draw_on_origianl_img() which maps the fitted lines back into the original image. Here is an example of my result on a test image:
1. Provide a link to your final video output. Your pipeline should perform reasonably well on the entire project video (wobbly lines are ok but no catastrophic failures that would cause the car to drive off the road!).
Here's a link to my video result
1. Briefly discuss any problems / issues you faced in your implementation of this project. Where will your pipeline likely fail? What could you do to make it more robust?
My pipeline failed when there is so much noise around the lane lines. What I did was:- 1- Identify where exactly in the video the lines were not detected well. 2- Take a snapshot of the video at that point and save it 3- Perform more tuning of the extra images I added, changing thresholding values, I also added a mask to clear the noise in the polygon formed by connecting the two lane lines by two horizontal lines. The code for this masking is in methong mask_region().
I know the pipeline needs further improvement, for example, if there is a lane with two different colors of the asphalt to the right and to the left of the center of the car, the pipeline will fail to detect it. Also I need to try my pipeline on night drive, I think thresholding values should be lessened.
I use averaging of previous n fits to make a prediction of lane lines if the current frame is too noisy that the lines are not detectable. I use Python Deques to store previous n fits, I think this is a dequate data structure in my case because it provided the ability to auto remove old item when a new item is inserted if the deque max length is reached.