-
Notifications
You must be signed in to change notification settings - Fork 0
/
image_processing.py
338 lines (291 loc) · 14.3 KB
/
image_processing.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
import cv2
import numpy as np
import matplotlib.pyplot as plt
def plot_perp(points, shape='.'):
"""
Input 4 points(x,y) and plot them clockwise
"""
if (len(points) != 4):
raise Exception('must be 4 points with x and ys')
plt.plot(points[0][0], points[0][1], shape)
plt.plot(points[1][0], points[1][1], shape)
plt.plot(points[2][0], points[2][1], shape)
plt.plot(points[3][0], points[3][1], shape)
def wrap(img, left=0, right=0, top=0, bottom=0):
"Perspective View to Top Down Projection"
img_size = (img.shape[1], img.shape[0])
# Define the region
# We consider a default perspective plane and offset it if required
src = np.float32(
[[120 + left, 720 + bottom],
[550 + left, 470 + top],
[700 + right, 470 + top],
[1160 + right, 720 + bottom]])
# four source coordinates
# src = np.float32(area_of_interest)
# src = np.float32([[690, 450], [1050, 680], [250, 680], [590, 450]])
# plt.imshow(img,cmap='gray')
# plot_perp(src)
# plt.show()
# Choose an offset from image corners to plot detected corners
offset1 = 200 # offset for dst points x value
offset2 = 0 # offset for dst points bottom y value
offset3 = 0 # offset for dst points top y value
# four desired coordinates
# dst = np.float32([[offset1, offset3],
# [img_size[0] - offset1, offset3],
# [img_size[0] - offset1, img_size[1] - offset2],
# [offset1, img_size[1] - offset2]])
dst = np.float32(
[[200, 720],
[200, 0],
[1080, 0],
[1080, 720]])
# Compute the persective transform M
M = cv2.getPerspectiveTransform(src, dst)
Minv = cv2.getPerspectiveTransform(dst, src)
# Create wrapped Image use linear interpolation
wraped = cv2.warpPerspective(img, M, img_size, flags=cv2.INTER_LINEAR)
return wraped, M, Minv
def abs_sobel_thresh(img, orient='x', thresh=(0, 255)):
# Apply the following steps to img
# 1) Convert to grayscale
# gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
# 2) Take the derivative in x or y given orient = 'x' or 'y'
if orient == 'x':
derivative = cv2.Sobel(img, cv2.CV_64F, 1, 0)
elif orient == 'y':
derivative = cv2.Sobel(img, cv2.CV_64F, 0, 1)
else:
print("Error: orient must be either x or y.")
derivative = 0
# 3) Take the absolute value of the derivative or gradient
abs_derivative = np.absolute(derivative)
# 4) Scale to 8-bit (0 - 255) then convert to type = np.uint8
scaled_sobel = np.uint8(255 * abs_derivative / np.max(abs_derivative))
# 5) Create a mask of 1's where the scaled gradient magnitude
# is > thresh_min and < thresh_max
# So there are 1s where #s are within our thresholds and 0s otherwise.
grad_binary = np.zeros_like(scaled_sobel)
grad_binary[(scaled_sobel >= thresh[0]) & (scaled_sobel <= thresh[1])] = 1
# 6) Return this mask as your binary_output image
return grad_binary
def mag_thresh(img, sobel_kernel=9, mag_thresh=(0, 255), is_gray=True, sobelx=None, sobely=None):
# Apply the following steps to img
# 1) Convert to grayscale
if (is_gray == False):
gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
else:
gray = img
# Take both Sobel x and y gradients
if (sobelx == None):
sobelx = cv2.Sobel(gray, cv2.CV_64F, 1, 0, ksize=sobel_kernel)
if (sobely == None):
sobely = cv2.Sobel(gray, cv2.CV_64F, 0, 1, ksize=sobel_kernel)
# Calculate the gradient magnitude
gradmag = np.sqrt(sobelx ** 2 + sobely ** 2)
# Rescale to 8 bit
scale_factor = np.max(gradmag) / 255
gradmag = (gradmag / scale_factor).astype(np.uint8)
# Create a binary image of ones where threshold is met, zeros otherwise
binary_output = np.zeros_like(gradmag)
binary_output[(gradmag >= mag_thresh[0]) & (gradmag <= mag_thresh[1])] = 1
# Return the binary image
return binary_output
def dir_threshold(image, sobel_kernel=3, thresh=(0, np.pi / 2), is_gray=True, sobelx=None, sobely=None):
# Apply the following steps to img
# 1) Convert to grayscale
if is_gray is False:
gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
else:
gray = image
# Calculate the x and y gradients
if sobelx is None:
sobelx = cv2.Sobel(gray, cv2.CV_64F, 1, 0, ksize=sobel_kernel)
if sobely is None:
sobely = cv2.Sobel(gray, cv2.CV_64F, 0, 1, ksize=sobel_kernel)
# Take the absolute value of the gradient direction,
# apply a threshold, and create a binary image result
# 3) Take the absolute value of the x and y gradients
absgraddir = np.arctan2(np.absolute(sobely), np.absolute(sobelx))
binary_output = np.zeros_like(absgraddir)
binary_output[(absgraddir >= thresh[0]) & (absgraddir <= thresh[1])] = 1
# Return the binary image
return binary_output
def hls_select(img, thresh=(170, 255)):
hls = cv2.cvtColor(img, cv2.COLOR_RGB2HLS)
s_channel = hls[:, :, 2]
binary_output = np.zeros_like(s_channel)
binary_output[(s_channel >= thresh[0]) & (s_channel <= thresh[1])] = 1
return binary_output
def apply_thresholds(image, ksize=3, show_detailed_image=False):
thresh_mag = (50, 255)
thresh_dir = (0.75, 1.15)
# Make a copy of gray image
gray = np.copy(image)
gray = cv2.cvtColor(gray, cv2.COLOR_RGB2GRAY)
if (show_detailed_image):
plt.title('Gray')
plt.imshow(gray, cmap='gray')
plt.show()
# pre-calculate sobel X and Y for magnitude and direction threshold
gradX = abs_sobel_thresh(gray, 'x', (150, 255))
sobelx = cv2.Sobel(gray, cv2.CV_64F, 1, 0, ksize=9)
sobely = cv2.Sobel(gray, cv2.CV_64F, 1, 0, ksize=9)
mag_binary = mag_thresh(gray, sobel_kernel=ksize*3, mag_thresh=thresh_mag, is_gray=True, sobelx=sobelx, sobely=sobely)
dir_binary = dir_threshold(gray, sobel_kernel=ksize, thresh=thresh_dir, is_gray=True, sobelx=sobelx, sobely=sobely)
if (show_detailed_image):
plt.title('Direction Threshold')
plt.imshow(dir_binary, cmap='gray')
plt.show()
# Combine thresholds
combined = np.zeros_like(dir_binary)
# & (grady == 1)
combined[((gradX == 1)) | ((mag_binary == 1) & (dir_binary == 1))] = 1
# Threshold color channel
# HLS
image_s = hls_select(image, (170, 255))
color_binary = np.zeros_like(gray)
color_binary[(image_s == 1) | (combined > 0)] = 255
if (show_detailed_image):
plt.title(("color Binary"))
plt.imshow(color_binary, cmap='gray')
plt.show()
return color_binary
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
## 5. Detect lane pixels and fit to find lane boundary.
def histogram_pixels_v3(binary_warped, show_step_images=False):
# Take a histogram of the bottom half of the image
histogram = np.sum(binary_warped[binary_warped.shape[0] / 2:, :], axis=0)
# Create an output image to draw on and visualize the result
out_img = np.dstack((binary_warped, binary_warped, binary_warped)) * 255
# Find the peak of the left and right halves of the histogram
# These will be the starting point for the left and right lines
midpoint = np.int(histogram.shape[0] / 2)
leftx_base = np.argmax(histogram[:midpoint])
rightx_base = np.argmax(histogram[midpoint:]) + midpoint
# Choose the number of sliding windows
nwindows = 9
# Set height of windows
window_height = np.int(binary_warped.shape[0] / nwindows)
# Identify the x and y positions of all nonzero pixels in the image
nonzero = binary_warped.nonzero()
nonzeroy = np.array(nonzero[0])
nonzerox = np.array(nonzero[1])
# Current positions to be updated for each window
leftx_current = leftx_base
rightx_current = rightx_base
# Set the width of the windows +/- margin
margin = 100
# Set minimum number of pixels found to recenter window
minpix = 50
# Create empty lists to receive left and right lane pixel indices
left_lane_inds = []
right_lane_inds = []
# Step through the windows one by one
for window in range(nwindows):
# Identify window boundaries in x and y (and right and left)
win_y_low = binary_warped.shape[0] - (window + 1) * window_height
win_y_high = binary_warped.shape[0] - window * window_height
win_xleft_low = leftx_current - margin
win_xleft_high = leftx_current + margin
win_xright_low = rightx_current - margin
win_xright_high = rightx_current + margin
# Draw the windows on the visualization image
cv2.rectangle(out_img, (win_xleft_low, win_y_low), (win_xleft_high, win_y_high), (0, 255, 0), 2)
cv2.rectangle(out_img, (win_xright_low, win_y_low), (win_xright_high, win_y_high), (0, 255, 0), 2)
# Identify the nonzero pixels in x and y within the window
good_left_inds = ((nonzeroy >= win_y_low) & (nonzeroy < win_y_high) & (nonzerox >= win_xleft_low) & (
nonzerox < win_xleft_high)).nonzero()[0]
good_right_inds = ((nonzeroy >= win_y_low) & (nonzeroy < win_y_high) & (nonzerox >= win_xright_low) & (
nonzerox < win_xright_high)).nonzero()[0]
# Append these indices to the lists
left_lane_inds.append(good_left_inds)
right_lane_inds.append(good_right_inds)
# If you found > minpix pixels, recenter next window on their mean position
if len(good_left_inds) > minpix:
leftx_current = np.int(np.mean(nonzerox[good_left_inds]))
if len(good_right_inds) > minpix:
rightx_current = np.int(np.mean(nonzerox[good_right_inds]))
# Concatenate the arrays of indices
left_lane_inds = np.concatenate(left_lane_inds)
right_lane_inds = np.concatenate(right_lane_inds)
# Extract left and right line pixel positions
leftx = nonzerox[left_lane_inds]
lefty = nonzeroy[left_lane_inds]
rightx = nonzerox[right_lane_inds]
righty = nonzeroy[right_lane_inds]
# Fit a second order polynomial to each
left_fit = np.polyfit(lefty, leftx, 2)
right_fit = np.polyfit(righty, rightx, 2)
# Generate x and y values for plotting
ploty = np.linspace(0, binary_warped.shape[0] - 1, binary_warped.shape[0])
left_fitx = left_fit[0] * ploty ** 2 + left_fit[1] * ploty + left_fit[2]
right_fitx = right_fit[0] * ploty ** 2 + right_fit[1] * ploty + right_fit[2]
out_img[nonzeroy[left_lane_inds], nonzerox[left_lane_inds]] = [255, 0, 0]
out_img[nonzeroy[right_lane_inds], nonzerox[right_lane_inds]] = [0, 0, 255]
nonzero = binary_warped.nonzero()
nonzeroy = np.array(nonzero[0])
nonzerox = np.array(nonzero[1])
margin = 100
left_lane_inds = ((nonzerox > (left_fit[0] * (nonzeroy ** 2) + left_fit[1] * nonzeroy + left_fit[2] - margin)) & (
nonzerox < (left_fit[0] * (nonzeroy ** 2) + left_fit[1] * nonzeroy + left_fit[2] + margin)))
right_lane_inds = (
(nonzerox > (right_fit[0] * (nonzeroy ** 2) + right_fit[1] * nonzeroy + right_fit[2] - margin)) & (
nonzerox < (right_fit[0] * (nonzeroy ** 2) + right_fit[1] * nonzeroy + right_fit[2] + margin)))
# Again, extract left and right line pixel positions
leftx = nonzerox[left_lane_inds]
lefty = nonzeroy[left_lane_inds]
rightx = nonzerox[right_lane_inds]
righty = nonzeroy[right_lane_inds]
# Fit a second order polynomial to each
left_fit = np.polyfit(lefty, leftx, 2)
right_fit = np.polyfit(righty, rightx, 2)
# Generate x and y values for plotting
ploty = np.linspace(0, binary_warped.shape[0] - 1, binary_warped.shape[0])
left_fitx = left_fit[0] * ploty ** 2 + left_fit[1] * ploty + left_fit[2]
right_fitx = right_fit[0] * ploty ** 2 + right_fit[1] * ploty + right_fit[2]
# Create an image to draw on and an image to show the selection window
#out_img = np.dstack((binary_warped, binary_warped, binary_warped)) * 255
window_img = np.zeros_like(out_img)
# Color in left and right line pixels
#out_img[nonzeroy[left_lane_inds], nonzerox[left_lane_inds]] = [255, 0, 0]
#out_img[nonzeroy[right_lane_inds], nonzerox[right_lane_inds]] = [0, 0, 255]
# Generate a polygon to illustrate the search window area
# And recast the x and y points into usable format for cv2.fillPoly()
left_line_window1 = np.array([np.transpose(np.vstack([left_fitx - margin, ploty]))])
left_line_window2 = np.array([np.flipud(np.transpose(np.vstack([left_fitx + margin, ploty])))])
left_line_pts = np.hstack((left_line_window1, left_line_window2))
right_line_window1 = np.array([np.transpose(np.vstack([right_fitx - margin, ploty]))])
right_line_window2 = np.array([np.flipud(np.transpose(np.vstack([right_fitx + margin, ploty])))])
right_line_pts = np.hstack((right_line_window1, right_line_window2))
# Draw the lane onto the warped blank image
if (show_step_images):
cv2.fillPoly(window_img, np.int_([left_line_pts]), (0, 255, 0))
cv2.fillPoly(window_img, np.int_([right_line_pts]), (0, 255, 0))
result = cv2.addWeighted(out_img, 1, window_img, 0.3, 0)
plt.imshow(result)
plt.plot(left_fitx, ploty, color='yellow')
plt.plot(right_fitx, ploty, color='yellow')
plt.xlim(0, 1280)
plt.ylim(720, 0)
plt.show()
return leftx, lefty, rightx, righty