-
Notifications
You must be signed in to change notification settings - Fork 4
/
Copy pathvideo_gen.py
176 lines (135 loc) · 7.6 KB
/
video_gen.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
import numpy as np
import cv2
import pickle
import glob
from tracker import tracker
from moviepy.editor import VideoFileClip
from IPython.display import HTML
dist_pickle = pickle.load(open("calibration_pickle.p", "rb"))
mtx = dist_pickle["mtx"]
dist = dist_pickle["dist"]
def abs_sobel_thresh(img, orient='x', sobel_kernel=3, thresh=(0,255)):
gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
if orient == 'x':
abs_sobel = np.absolute(cv2.Sobel(gray, cv2.CV_64F, 1, 0))
if orient == 'y':
abs_sobel = np.absolute(cv2.Sobel(gray, cv2.CV_64F, 0, 1))
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 mag_thresh(img, sobel_kernel=3, mag_thresh=(0,255)):
gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
sobelx = cv2.Sobel(gray, cv2.CV_64F, 1, 0, ksize=sobel_kernel)
sobely = cv2.Sobel(gray, cv2.CV_64F, 0, 1, ksize=sobel_kernel)
gradmag = np.sqrt(sobelx**2+sobely**2)
scale_factor = np.max(gradmag)/255
gradmag = (gradmag/scale_factor).astype(np.uint8)
binary_output = np.zeros_like(gradmag)
binary_output[(gradmag >= mag_thresh[0]) & (gradmag <= mag_thresh[1])] = 1
return binary_output
def dir_threshold(image, sobel_kernel=3, thresh=(0, np.pi/2)):
gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
sobelx = cv2.Sobel(gray, cv2.CV_64F, 1, 0, ksize=sobel_kernel)
sobely = cv2.Sobel(gray, cv2.CV_64F, 0, 1, ksize=sobel_kernel)
with np.errstate(divide='ignore', invalid='ignore'):
absgraddir = np.absolute(np.arctan(sobely/sobelx))
binary_output = np.zeros_like(absgraddir)
binary_output[(absgraddir >= thresh[0]) & (absgraddir <= thresh[1])] = 1
return binary_output
def color_threshold(image, sthresh=(0,255), vthresh=(0,255), lthresh=(0,255)):
hls = cv2.cvtColor(image, cv2.COLOR_RGB2HLS)
s_channel = hls[:,:,2]
s_binary = np.zeros_like(s_channel)
s_binary[(s_channel >= sthresh[0]) & (s_channel <= sthresh[1])] = 1
hsv = cv2.cvtColor(image, cv2.COLOR_RGB2HSV)
v_channel = hsv[:,:,2]
v_binary = np.zeros_like(v_channel)
v_binary[(v_channel >= vthresh[0]) & (v_channel <= vthresh[1])] = 1
output = np.zeros_like(s_channel)
output[(s_binary == 1) & (v_binary == 1)] = 1
return output
def window_mask(width, height, img_ref, center, level):
output = np.zeros_like(img_ref)
output[int(img_ref.shape[0] - (level + 1) * height):int(img_ref.shape[0] - level * height),
max(0, int(center - width / 2)):min(int(center + width / 2), img_ref.shape[1])] = 1
return output
def process_image(image):
img = cv2.undistort(image, mtx, dist, None, mtx)
preprocessImage = np.zeros_like(img[:,:,0])
gradx = abs_sobel_thresh(img, orient='x', thresh=(12,255))
grady = abs_sobel_thresh(img, orient='x', thresh=(25,255))
c_binary = color_threshold(img, sthresh=(100,255),vthresh=(50,255))
preprocessImage[((gradx==1)&(grady==1)|(c_binary==1))] = 255
img_size = (img.shape[1], img.shape[0])
bot_width = .75 #changed from .76
mid_width = .1 #changed this value - seemed to work a lot better than 0.08
height_pct = .62
bottom_trim = .935
src = np.float32([[img.shape[1]*(.5-mid_width/2),img.shape[0]*height_pct],[img.shape[1]*(.5+mid_width/2),img.shape[0]*height_pct],
[img.shape[1]*(.5+bot_width/2),img.shape[0]*bottom_trim],[img.shape[1]*(.5-bot_width/2),img.shape[0]*bottom_trim]])
offset = img_size[0]*.25
dst = np.float32([[offset, 0], [img_size[0]-offset, 0],[img_size[0]-offset, img_size[1]],[offset, img_size[1]]])
M = cv2.getPerspectiveTransform(src, dst)
Minv = cv2.getPerspectiveTransform(dst, src)
warped = cv2.warpPerspective(preprocessImage, M, img_size,flags=cv2.INTER_LINEAR)
window_width = 25
window_height = 80
curve_centers = tracker(Mywindow_width=window_width,Mywindow_height=window_height,Mymargin=25,My_ym=10/720,My_xm=4/384,Mysmooth_factor=15)
window_centroids = curve_centers.find_window_centroids(warped)
l_points = np.zeros_like(warped)
r_points = np.zeros_like(warped)
rightx = []
leftx = []
for level in range(0,len(window_centroids)):
l_mask = window_mask(window_width,window_height,warped,window_centroids[level][0],level)
r_mask = window_mask(window_width,window_height,warped,window_centroids[level][1],level)
leftx.append(window_centroids[level][0])
rightx.append(window_centroids[level][1])
l_points[(l_points==255)|((l_mask==1))] = 255
r_points[(r_points==255)|((r_mask==1))] = 255
template = np.array(r_points+l_points,np.uint8)
zero_channel = np.zeros_like(template)
template = np.array(cv2.merge((zero_channel,template,zero_channel)),np.uint8)
warpage = np.array(cv2.merge((warped,warped,warped)),np.uint8)
result = cv2.addWeighted(warpage,1,template,0.5,0.0)
yvals = range(0,warped.shape[0])
res_yvals = np.arange(warped.shape[0]-(window_height/2),0,-window_height)
left_fit = np.polyfit(res_yvals,leftx,2)
left_fitx = left_fit[0]*yvals*yvals + left_fit[1]*yvals + left_fit[2]
left_fitx = np.array(left_fitx,np.int32)
right_fit = np.polyfit(res_yvals,rightx,2)
right_fitx = right_fit[0]*yvals*yvals + right_fit[1]*yvals + right_fit[2]
right_fitx = np.array(right_fitx,np.int32)
left_lane = np.array(list(zip(np.concatenate((left_fitx-window_width/2,left_fitx[::-1]+window_width/2),axis=0),np.concatenate((yvals,yvals[::-1]),axis=0))),np.int32)
right_lane = np.array(list(zip(np.concatenate((right_fitx-window_width/2,right_fitx[::-1]+window_width/2),axis=0),np.concatenate((yvals,yvals[::-1]),axis=0))),np.int32)
inner_lane = np.array(list(zip(np.concatenate((left_fitx+window_width/2,right_fitx[::-1]+window_width/2),axis=0),np.concatenate((yvals,yvals[::-1]),axis=0))),np.int32)
road = np.zeros_like(img)
road_bkg = np.zeros_like(img)
cv2.fillPoly(road,[left_lane],color=[255,0,0])
cv2.fillPoly(road,[inner_lane],color=[0,255,0])
cv2.fillPoly(road,[right_lane],color=[0,0,255])
cv2.fillPoly(road_bkg,[left_lane],color=[255,255,255])
cv2.fillPoly(road_bkg,[right_lane],color=[255,255,255])
road_warped = cv2.warpPerspective(road,Minv,img_size,flags=cv2.INTER_LINEAR)
road_warped_bkg = cv2.warpPerspective(road_bkg,Minv,img_size,flags=cv2.INTER_LINEAR)
base = cv2.addWeighted(img, 1.0, road_warped_bkg, -1.0, 0.0)
result = cv2.addWeighted(base,1.0,road_warped,0.7,0.0)
#measure pixels in y and x directions
ym_per_pix = curve_centers.ym_per_pix
xm_per_pix = curve_centers.xm_per_pix
curve_fit_cr = np.polyfit(np.array(res_yvals,np.float32)*ym_per_pix,np.array(leftx,np.float32)*xm_per_pix,2)
curverad = ((1+(2*curve_fit_cr[0]*yvals[-1]*ym_per_pix+curve_fit_cr[1])**2)**1.5)/np.absolute(2*curve_fit_cr[0]) #remember that it's the equation from the lesson (derivatives) - radius of curvature
camera_center = (left_fitx[-1] + right_fitx[-1])/2
center_diff = (camera_center-warped.shape[1]/2)*xm_per_pix
side_pos = 'left'
if center_diff <= 0:
side_pos = 'right'
cv2.putText(result,'Radius of curvature = '+str(round(curverad,3))+'(m)',(50,50),cv2.FONT_HERSHEY_SIMPLEX,1,(255,255,255),2)
cv2.putText(result,'Vehicle is '+str(abs(round(center_diff,3)))+'m '+side_pos+' of center',(50,100), cv2.FONT_HERSHEY_SIMPLEX,1,(255,255,255),2)
return result
output_vid = 'lane_tracker.mp4'
input_vid = 'project_video.mp4'
clip1 = VideoFileClip(input_vid)
video_clip = clip1.fl_image(process_image)
video_clip.write_videofile(output_vid, audio=False)