In [69]:
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
import numpy as np
import cv2
%matplotlib inline
In [70]:
import math
def grayscale(img):
"""Applies the Grayscale transform
This will return an image with only one color channel
but NOTE: to see the returned image as grayscale
(assuming your grayscaled image is called 'gray')
you should call plt.imshow(gray, cmap='gray')"""
return cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
# Or use BGR2GRAY if you read an image with cv2.imread()
# return cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
def canny(img, low_threshold, high_threshold):
"""Applies the Canny transform"""
return cv2.Canny(img, low_threshold, high_threshold)
def gaussian_blur(img, kernel_size):
"""Applies a Gaussian Noise kernel"""
return cv2.GaussianBlur(img, (kernel_size, kernel_size), 0)
def region_of_interest(img, vertices):
"""
Applies an image mask.
Only keeps the region of the image defined by the polygon
formed from `vertices`. The rest of the image is set to black.
"""
#defining a blank mask to start with
mask = np.zeros_like(img)
#defining a 3 channel or 1 channel color to fill the mask with depending on the input image
if len(img.shape) > 2:
channel_count = img.shape[2] # i.e. 3 or 4 depending on your image
ignore_mask_color = (255,) * channel_count
else:
ignore_mask_color = 255
#filling pixels inside the polygon defined by "vertices" with the fill color
cv2.fillPoly(mask, vertices, ignore_mask_color)
#returning the image only where mask pixels are nonzero
masked_image = cv2.bitwise_and(img, mask)
return masked_image
def draw_lines(img, lines, color=[255, 0, 0], thickness=2):
"""
NOTE: this is the function you might want to use as a starting point once you want to
average/extrapolate the line segments you detect to map out the full
extent of the lane (going from the result shown in raw-lines-example.mp4
to that shown in P1_example.mp4).
Think about things like separating line segments by their
slope ((y2-y1)/(x2-x1)) to decide which segments are part of the left
line vs. the right line. Then, you can average the position of each of
the lines and extrapolate to the top and bottom of the lane.
This function draws `lines` with `color` and `thickness`.
Lines are drawn on the image inplace (mutates the image).
If you want to make the lines semi-transparent, think about combining
this function with the weighted_img() function below
"""
imshape = image.shape
leftMinY = 0
leftMaxY = imshape[0]
leftMinX = 0
leftMaxX = 0
rightMinY = 0
rightMaxY = imshape[0]
rightMinX = 0
rightMaxX = 0
m1 = 1
m2 = 1
for line in lines:
for x1,y1,x2,y2 in line:
slope = (y2 - y1)/(x2- x1)
if slope < 0:
m1 = slope
if(leftMinY < y1):
leftMinY = y1
leftMinX = x1
if(leftMaxY > y2):
leftMaxY = y2
leftMaxX = x2
elif slope > 0:
m2 = slope
if(rightMinY < y2):
rightMinY = y2
rightMinX = x2
if(rightMaxY > y1):
rightMaxY = y1
rightMaxX = x1
leftMinX = np.uint16(leftMinX - ((leftMinY - imshape[0])/m1)) #x2 - (y2 - y1) / m1
rightMinX = np.uint16(rightMinX - ((rightMinY - imshape[0] )/m2))
cv2.line(img, (leftMinX, imshape[0]), (leftMaxX, leftMaxY), color, thickness)
cv2.line(img, (rightMinX, imshape[0]), (rightMaxX, rightMaxY), color, thickness)
#for line in lines:
#for x1,y1,x2,y2 in line:
#cv2.line(img, (x1, y1), (x2, y2), [255,255,0], thickness)
def hough_lines(img, rho, theta, threshold, min_line_len, max_line_gap):
"""
`img` should be the output of a Canny transform.
Returns an image with hough lines drawn.
"""
lines = cv2.HoughLinesP(img, rho, theta, threshold, np.array([]), minLineLength=min_line_len, maxLineGap=max_line_gap)
line_img = np.zeros((img.shape[0], img.shape[1], 3), dtype=np.uint8)
draw_lines(line_img, lines,thickness=6)
return line_img
# Python 3 has support for cool math symbols.
def weighted_img(img, initial_img, α=0.8, β=1., λ=0.):
"""
`img` is the output of the hough_lines(), An image with lines drawn on it.
Should be a blank image (all black) with lines drawn on it.
`initial_img` should be the image before any processing.
The result image is computed as follows:
initial_img * α + img * β + λ
NOTE: initial_img and img must be the same shape!
"""
return cv2.addWeighted(initial_img, α, img, β, λ)
def laneDetection(inputImage, boundaries, preProcessingFlag=True, intelligentFlag = True, extrapolateFlag= True, showMask=False,kernel_size = 5, min_line_len = 20,max_line_gap = 6 , low_threshold = 95,high_threshold = 120,rho = 1,theta = np.pi/180,threshold = 10, color=[255,0,0],thickness=2,alpha=5,beta=10):
#img = mpimg.imread(inputImage)
#img = (mpimg.imread(test)*255).astype('uint8')
img = inputImage
if preProcessingFlag==True:
img = preProcess(img, boundaries)
gray = grayscale(img) # convert image from RGB to gray
grayG = gaussian_blur(gray, kernel_size) #Gaussian filter is applied to remove the scharp edges
cannyImg = canny(grayG, low_threshold, high_threshold) # apply canny edge detection algorithm
# mask detection
if not intelligentFlag:
# add simple mask - handmade
imshape = cannyImg.shape
vertices = np.array([[(0,imshape[0]),(imshape[1]/2+3*imshape[0]/70, imshape[0]/3+imshape[0]/4), (imshape[1]/2+imshape[0]/70, imshape[0]/3+imshape[0]/4), (imshape[1],imshape[0])]], dtype=np.int32)
masked = region_of_interest(cannyImg,vertices)
else:
# find the horizon line - adaptive masking
# better way is finding slope and intersection between two lines
masked = cannyImg
houghImg, successfulFlag = hough_lines(masked, rho, theta, threshold, min_line_len, max_line_gap,color,thickness,intelligentFlag, extrapolateFlag,showMask,alpha,beta)
if successfulFlag==True:
houghRGB = np.dstack((houghImg*(color[0]//255), houghImg*(color[1]//255), houghImg*(color[2]//255))) # *(color[1]/255)
result = weighted_img(inputImage, houghRGB, α=1., β=0.8, λ=0.)
return result
else:
return inputImage
In [71]:
image = mpimg.imread('test_images/solidWhiteRight.jpg')
print('This image is:', type(image), 'with dimensions:', image.shape)
plt.imshow(image)
Out[71]:
In [72]:
import os
imgFolder = "test_images"
saveFolder = "testResults/images"
imgs = os.listdir(imgFolder)
for imageName in imgs:
inputImagePath = os.path.join(imgFolder, imageName)
image = cv2.imread(inputImagePath)
gray = grayscale(image)
kernel_size = 5
blur_gray = gaussian_blur(gray, kernel_size)
high_threshold = 150
low_threshold = high_threshold / 3
edges = canny(blur_gray, low_threshold, high_threshold)
imshape = image.shape
vertices = np.array([[(0, imshape[0]),(imshape[1],imshape[0]),(imshape[1]/2, imshape[0]/2 + 50) ]], dtype=np.int32)
masked_edges = region_of_interest(edges, vertices)
rho = 2
theta = np.pi/180
threshold = 25
min_line_len = 40
max_line_gap = 70
line_image = hough_lines(masked_edges, rho, theta, threshold, min_line_len, max_line_gap)
color_edges = np.dstack((edges, edges, edges))
result = weighted_img(color_edges, line_image)
outputImagePath = os.path.join(saveFolder, imageName)
cv2.imwrite(outputImagePath, result)
plt.imshow(result)
In [73]:
from moviepy.editor import VideoFileClip
from IPython.display import HTML
def process_image(image):
gray = grayscale(image)
kernel_size = 5
blur_gray = gaussian_blur(gray, kernel_size)
high_threshold = 150
low_threshold = high_threshold / 3
edges = canny(blur_gray, low_threshold, high_threshold)
imshape = image.shape
vertices = np.array([[(0, imshape[0]),(imshape[1],imshape[0]),(imshape[1]/2, imshape[1]/3 - 1) ]], dtype=np.int32)
masked_edges = region_of_interest(edges, vertices)
rho = 2
theta = np.pi/180
threshold = 25
min_line_len = 40
max_line_gap = 70
line_image = hough_lines(masked_edges, rho, theta, threshold, min_line_len, max_line_gap)
#color_edges = np.dstack((masked_edges, masked_edges, masked_edges))
result = weighted_img(image, line_image)
return result
whiteLaneVideo = VideoFileClip("test_videos/solidWhiteRight.mp4")
yellowLaneVideo = VideoFileClip("test_videos/solidYellowLeft.mp4")
whiteLaneResult = 'testResults/videos/solidWhiteRight.mp4'
yellowLaneResult = 'testResults/videos/solidYellowLeft.mp4'
whiteLaneProcessed = whiteLaneVideo.fl_image(process_image)
yellowLaneProcessed = yellowLaneVideo.fl_image(process_image)
%time whiteLaneProcessed.write_videofile(whiteLaneResult, audio=False)
%time yellowLaneProcessed.write_videofile(yellowLaneResult, audio=False)
In [74]:
HTML("""
<video width="960" height="540" controls>
<source src="{0}">
</video>
""".format(whiteLaneResult))
Out[74]:
In [75]:
HTML("""
<video width="960" height="540" controls>
<source src="{0}">
</video>
""".format(yellowLaneResult))
Out[75]:
The pipeline first detects lanes in a set of images and uses the same techinque to detect lanes in a stream of video. The RGB images are converted to grayscale and gaussian blur is applied over them. Using canny edge detection, we then find the edges and extrapolate lines over the strongest edges. For a video stream, we essentially perform the same operations over every video frame which is inturn an image. The fl_image method comes in handy during lane detection on video streams.
The above algorithm works best for smooth and straight lanes. When used on lanes with bumps and curves, this algorithm will fail to detect lanes. This algorithm will also fail in the event of bad weather.
The current implemntation has some jitters. Pre-processing the images would result in a smoother extrapolation. We can use the intelligent flag on hough lines coupled with other parameters to detect curved lanes.