-
Notifications
You must be signed in to change notification settings - Fork 3
/
helpers.py
435 lines (384 loc) · 18.4 KB
/
helpers.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
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
import numpy as np
import cv2
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
import pickle
import glob
from moviepy.editor import VideoFileClip
mtx = None
dist = None
M = None
Minv = None
line_prev = None
num_full_search = 0
class Line():
def __init__(self):
self.fullsearch = False
self.left_lane_inds = None
self.right_lane_inds = None
self.left_fit = None
self.right_fit = None
self.left_fit_cr = None
self.right_fit_cr = None
self.yvals = None
self.left_fitx = None
self.right_fitx = None
self.y_bottom = None
self.y_top = None
self.left_x_bottom = None
self.left_x_top = None
self.right_x_bottom = None
self.right_x_top = None
self.left_curverads = None
self.right_curverads = None
self.mean_left_curverad = None
self.mean_right_curverad = None
def display(img, tag1, undist, tag2):
f, (ax1, ax2) = plt.subplots(1, 2, figsize=(24, 9))
f.tight_layout()
ax1.imshow(img)
ax1.set_title(tag1, fontsize=50)
ax2.imshow(undist)
ax2.set_title(tag2, fontsize=50)
plt.subplots_adjust(left=0., right=1, top=0.9, bottom=0.)
plt.show()
def display_poly_fit(binary_warped, left_lane_inds, right_lane_inds, out_img, plotSearchArea=False):
left_fit, right_fit = fit_curve(binary_warped, left_lane_inds, right_lane_inds)
nonzero = binary_warped.nonzero()
nonzeroy = np.array(nonzero[0])
nonzerox = np.array(nonzero[1])
margin = 100
# Generate x and y values for plotting
fity = np.linspace(0, binary_warped.shape[0]-1, binary_warped.shape[0] )
fit_leftx = left_fit[0]*fity**2 + left_fit[1]*fity + left_fit[2]
fit_rightx = right_fit[0]*fity**2 + right_fit[1]*fity + right_fit[2]
# 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]
result = None
if plotSearchArea == True:
window_img = np.zeros_like(out_img)
# 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([fit_leftx-margin, fity]))])
left_line_window2 = np.array([np.flipud(np.transpose(np.vstack([fit_leftx+margin, fity])))])
left_line_pts = np.hstack((left_line_window1, left_line_window2))
right_line_window1 = np.array([np.transpose(np.vstack([fit_rightx-margin, fity]))])
right_line_window2 = np.array([np.flipud(np.transpose(np.vstack([fit_rightx+margin, fity])))])
right_line_pts = np.hstack((right_line_window1, right_line_window2))
# Draw the lane onto the warped blank image
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)
else:
result = out_img
plt.imshow(result)
plt.plot(fit_leftx, fity, color='yellow')
plt.plot(fit_rightx, fity, color='yellow')
plt.xlim(0, 1280)
plt.ylim(720, 0)
plt.show()
def cal_undistort(img, mtx, dist):
undist = cv2.undistort(img, mtx, dist, None, mtx)
return undist
def find_corners(images):
# prepare object points, like (0,0,0), (1,0,0), (2,0,0) ....,(6,5,0)
objp = np.zeros((6*9,3), np.float32)
objp[:,:2] = np.mgrid[0:9, 0:6].T.reshape(-1,2)
# Arrays to store object points and image points from all the images.
objpoints = [] # 3d points in real world space
imgpoints = [] # 2d points in image plane.
image_dims = None
# Step through the list and search for chessboard corners
for idx, fname in enumerate(images):
img = cv2.imread(fname)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# Find the chessboard corners
ret, corners = cv2.findChessboardCorners(gray, (9,6), None)
# If found, add object points, image points
if ret == True:
objpoints.append(objp)
imgpoints.append(corners)
image_dims = (img.shape[0], img.shape[1])
return objpoints, imgpoints, image_dims
def calibrate_camera(path):
images = glob.glob(path)
objpoints, imgpoints, image_dims = find_corners(images)
ret, mtx, dist, rvecs, tvecs = cv2.calibrateCamera(objpoints, imgpoints, image_dims, None, None)
return mtx, dist
def abs_sobel_thresh(gray, orient='x', sobel_kernel=3, thresh=(0, 255)):
# Apply the following steps to img
# 1) Convert to grayscale
# 2) Take the derivative in x or y given orient = 'x' or 'y'
# 3) Take the absolute value of the derivative or gradient
# 4) Scale to 8-bit (0 - 255) then convert to type = np.uint8
# 5) Create a mask of 1's where the scaled gradient magnitude
# is > thresh_min and < thresh_max
# 6) Return this mask as your binary_output image
sobel = None
if orient == 'x':
sobel = cv2.Sobel(gray, cv2.CV_64F, 1, 0, ksize=sobel_kernel)
else:
sobel = cv2.Sobel(gray, cv2.CV_64F, 0, 1, ksize=sobel_kernel)
abs_sobel = np.absolute(sobel)
scaled_sobel = np.uint8(255*abs_sobel/np.max(abs_sobel))
binary_output = np.zeros_like(scaled_sobel)
binary_output[(scaled_sobel >= thresh[0]) & (scaled_sobel <= thresh[1])] = 1
return binary_output
def binary_thresholding(img, s_thresh=(175, 250), sx_thresh=(30, 150)):
# Convert to HSV color space and separate the V channel
gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
hsv = cv2.cvtColor(img, cv2.COLOR_RGB2HLS).astype(np.float)
l_channel = hsv[:,:,1]
s_channel = hsv[:,:,2]
# Sobel
ksize = 3
sobel = abs_sobel_thresh(gray, orient='x', sobel_kernel=ksize, thresh=sx_thresh)
# Threshold color channel
s_binary = np.zeros_like(s_channel)
s_binary[(s_channel >= s_thresh[0]) & (s_channel <= s_thresh[1])] = 1
combined = np.zeros_like(gray)
combined[(s_binary == 1) | (sobel == 1)] = 1
return combined
def perspective_transform(img):
# define 4 source points for perspective transformation
src = np.float32([[220,719],[1220,719],[750,480],[550,480]])
# define 4 destination points for perspective transformation
dst = np.float32([[240,719],[1040,719],[1040,300],[240,300]])
# Given src and dst points, calculate the perspective transform matrix
M = cv2.getPerspectiveTransform(src, dst)
# Warp the image using OpenCV warpPerspective()
warped = cv2.warpPerspective(img, M, (img.shape[1], img.shape[0]))
# Return the resulting image
return warped, M
def naive_find_lines(binary_warped):
# 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)
return left_lane_inds, right_lane_inds, out_img
def smart_find_lines(binary_warped, left_fit, right_fit):
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_new = np.polyfit(lefty, leftx, 2)
right_fit_new = np.polyfit(righty, rightx, 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
return left_lane_inds, right_lane_inds, out_img
def fit_curve(binary_warped, left_lane_inds, right_lane_inds):
nonzero = binary_warped.nonzero()
nonzeroy = np.array(nonzero[0])
nonzerox = np.array(nonzero[1])
# 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)
return left_fit, right_fit
def fit_pixel_to_meters(binary_warped, left_lane_inds, right_lane_inds):
nonzero = binary_warped.nonzero()
nonzeroy = np.array(nonzero[0])
nonzerox = np.array(nonzero[1])
# 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]
# Define conversions in x and y from pixels space to meters
ym_per_pix = 30/720 # meters per pixel in y dimension
xm_per_pix = 3.7/700 # meters per pixel in x dimension
# Fit new polynomials to x,y in world space
left_fit_cr = np.polyfit(lefty*ym_per_pix, leftx*xm_per_pix, 2)
right_fit_cr = np.polyfit(righty*ym_per_pix, rightx*xm_per_pix, 2)
return left_fit_cr, right_fit_cr
def radius_of_curvatures(yvals, left_fit, right_fit):
left_curverads = ((1 + (2*left_fit[0]*yvals + left_fit[1])**2)**1.5) / np.absolute(2*left_fit[0])
right_curverads = ((1 + (2*right_fit[0]*yvals + right_fit[1])**2)**1.5) / np.absolute(2*right_fit[0])
return left_curverads, right_curverads
def fit_lines(binary_warped, left_fit, right_fit):
yvals = np.linspace(0, binary_warped.shape[0]-1, binary_warped.shape[0] )
left_fitx = left_fit[0]*yvals**2 + left_fit[1]*yvals + left_fit[2]
right_fitx = right_fit[0]*yvals**2 + right_fit[1]*yvals + right_fit[2]
return yvals, left_fitx, right_fitx
def draw_lines(undist, warped, yvals, left_fitx, right_fitx, Minv):
# Create an image to draw the lines on
warp_zero = np.zeros_like(warped).astype(np.uint8)
color_warp = np.dstack((warp_zero, warp_zero, warp_zero))
# Recast the x and y points into usable format for cv2.fillPoly()
pts_left = np.array([np.transpose(np.vstack([left_fitx, yvals]))])
pts_right = np.array([np.flipud(np.transpose(np.vstack([right_fitx, yvals])))])
pts = np.hstack((pts_left, pts_right))
# Draw the lane onto the warped blank image
cv2.fillPoly(color_warp, np.int_([pts]), (0,255, 0))
# Warp the blank back to original image space using inverse perspective matrix (mtxinv)
newwarp = cv2.warpPerspective(color_warp, Minv, (color_warp.shape[1], color_warp.shape[0]))
# Combine the result with the original image
result = cv2.addWeighted(undist, 1, newwarp, 0.3, 0)
return result
def is_good_fit(prev, curr):
# check if left_x_bottom and right_x_bottom are within 15 pixels
if abs(prev.left_x_bottom - curr.left_x_bottom) <= 15:
if abs(prev.right_x_bottom - curr.right_x_bottom) <= 15:
if abs(curr.mean_left_curverad) < (abs(prev.mean_left_curverad*100)):
if abs(curr.mean_right_curverad) < (abs(prev.mean_right_curverad*100)):
return True
return False
def process_fit(binary_warped, left_lane_inds, right_lane_inds):
left_fit, right_fit = fit_curve(binary_warped, left_lane_inds, right_lane_inds)
left_fit_cr, right_fit_cr = fit_pixel_to_meters(binary_warped, left_lane_inds, right_lane_inds)
yvals, left_fitx, right_fitx = fit_lines(binary_warped, left_fit, right_fit)
line = Line()
line.left_lane_inds = left_lane_inds
line.right_lane_inds = right_lane_inds
line.left_fit = left_fit
line.right_fit = right_fit
line.left_fit_cr = left_fit_cr
line.right_fit_cr = right_fit_cr
line.yvals = yvals
line.left_fitx = left_fitx
line.right_fitx = right_fitx
line.y_bottom = np.min(yvals)
line.y_top = np.max(yvals)
line.left_x_bottom = left_fit[0]*line.y_bottom**2 + left_fit[1]*line.y_bottom + left_fit[2]
line.left_x_top = left_fit[0]*line.y_top**2 + left_fit[1]*line.y_top + left_fit[2]
line.right_x_bottom = right_fit[0]*line.y_bottom**2 + right_fit[1]*line.y_bottom + right_fit[2]
line.right_x_top = right_fit[0]*line.y_top**2 + right_fit[1]*line.y_top + right_fit[2]
left_curverads, right_curverads = radius_of_curvatures(line.yvals, left_fit_cr, right_fit_cr)
line.left_curverads = left_curverads
line.right_curverads = right_curverads
line.mean_left_curverad = np.mean(left_curverads)
line.mean_right_curverad = np.mean(right_curverads)
return line
def annotate_result(result, line):
lx = line.left_x_top
rx = line.right_x_top
xcenter = np.int(result.shape[1]/2)
offset = (rx - xcenter) - (xcenter - lx)
xm_per_pix = 3.7/700 # meters per pixel in x dimension
vehicle_offset = offset * xm_per_pix
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(result, 'Mean Radius of curvature (Left) = %.2f m' % (line.mean_left_curverad),
(10, 40), font, 1, (255, 255, 255), 2, cv2.LINE_AA)
cv2.putText(result, 'Mean Radius of curvature (Right) = %.2f m' % (line.mean_left_curverad),
(10, 70), font, 1, (255, 255, 255), 2, cv2.LINE_AA)
cv2.putText(result, 'Vehicle position = %.2f m from lane center' % (vehicle_offset),
(10, 100), font, 1, (255, 255, 255), 2, cv2.LINE_AA)
return result
def process_image(img):
global mtx, dist, line_prev, num_full_search
if mtx is None or dist is None:
mtx, dist = calibrate_camera("./camera_cal/calibration*.jpg")
undist_img = cal_undistort(img, mtx, dist)
s_thresh = (175, 250)
sx_thresh = (30, 150)
binary_threshold = binary_thresholding(undist_img, s_thresh=s_thresh, sx_thresh=sx_thresh)
binary_warped, M = perspective_transform(binary_threshold)
left_lane_inds = None
right_lane_inds = None
out_img = None
plotSearchArea = True
line = None
if line_prev is None:
left_lane_inds, right_lane_inds, out_img = naive_find_lines(binary_warped)
plotSearchArea = False
line = process_fit(binary_warped, left_lane_inds, right_lane_inds)
num_full_search = num_full_search + 1
else:
left_lane_inds, right_lane_inds, out_img = smart_find_lines(binary_warped,
line_prev.left_fit, line_prev.right_fit)
line = process_fit(binary_warped, left_lane_inds, right_lane_inds)
# check for a good fit
if is_good_fit(line_prev, line) is False:
left_lane_inds, right_lane_inds, out_img = naive_find_lines(binary_warped)
plotSearchArea = False
line = process_fit(binary_warped, left_lane_inds, right_lane_inds)
num_full_search = num_full_search + 1
result = draw_lines(undist_img, binary_warped, line.yvals, line.left_fitx, line.right_fitx, np.linalg.inv(M))
annotated_result = annotate_result(result, line)
#display(img, 'Original', binary_threshold, 'Thresholded')
#display(binary_threshold, 'Thresholded', binary_warped, 'Transformed')
#display_poly_fit(binary_warped, left_lane_inds, right_lane_inds, out_img, plotSearchArea)
#plt.imshow(result)
#plt.show()
line_prev = line
return annotated_result
def process_test():
img = cv2.imread('./camera_cal/distorted.png')
images = glob.glob('./test_images/*.jpg')
for idx, fname in enumerate(images):
img = cv2.imread(fname)
pipeline(img)
def process_video():
global num_full_search
output = 'lanelines_output.mp4'
clip1 = VideoFileClip("project_video.mp4")
output_clip = clip1.fl_image(process_image)
output_clip.write_videofile(output, audio=False)
print("Num full searches", num_full_search)
return output_clip