/
main.py
executable file
·240 lines (189 loc) · 7.68 KB
/
main.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
import math
import cv
import freenect
import frame_convert
import pyglet
import pyglet.image
import Image
import speechd
import os
import thread
import threading
import time
count = 0
class Converter(object):
raw_depth_image = cv.CreateImage((640,480), 8, 1)
thresh_depth_image = cv.CreateImage((640,480), 8, 1)
contour_depth_image = cv.CreateImage((640,480), 8, 1)
raw_video_image = cv.CreateImage((640,480), 8, 3)
raw_masked_image = cv.CreateImage((640,480), 8, 3)
def __init__(self):
super(Converter, self).__init__()
def get_data(self):
self.raw_depth_image = frame_convert.pretty_depth_cv(freenect.sync_get_depth()[0])
self.raw_video_image = frame_convert.video_cv(freenect.sync_get_video()[0])
cv.Flip(self.raw_depth_image,None,-1)
cv.Flip(self.raw_video_image,None,-1)
def get_depth(self):
width, height = cv.GetSize(self.raw_depth_image)
depth_image = pyglet.image.ImageData(width, height, "L", self.raw_depth_image.tostring())
return depth_image
def get_contour_image(self):
cv.Not(self.raw_depth_image,self.raw_depth_image)
cv.Threshold(self.raw_depth_image, self.thresh_depth_image, 128, 255, cv.CV_THRESH_BINARY)
contour_depth_image = cv.CreateImage((640,480),8,1)
cv.Dilate(self.thresh_depth_image,contour_depth_image, None, 18)
cv.Erode(contour_depth_image,contour_depth_image, None, 10)
return contour_depth_image
def get_centers(self):
contour_depth_image = self.get_contour_image()
storage = cv.CreateMemStorage(0)
contour = cv.FindContours(contour_depth_image, storage, cv.CV_RETR_CCOMP, cv.CV_CHAIN_APPROX_SIMPLE)
depth_points = []
while contour:
bound_rect = cv.BoundingRect(list(contour))
contour = contour.h_next()
pt1 = (bound_rect[0], bound_rect[1])
pt2 = (bound_rect[0] + bound_rect[2], bound_rect[1] + bound_rect[3])
points = []
points.append(pt1)
points.append(pt2)
if len(points):
depth_points.extend(reduce(lambda a, b: ((a[0] + b[0]) / 2, (a[1] + b[1]) / 2), points))
return depth_points
def get_video(self):
width, height = cv.GetSize(self.raw_video_image)
video_image = pyglet.image.ImageData(width, height, "BGR", self.raw_video_image.tostring())
return video_image
def get_masked(self):
contour_depth_image_bgr = cv.CreateImage((640,480), self.raw_video_image.depth, self.raw_video_image.nChannels)
self.raw_masked_image = cv.CreateImage((640,480), self.raw_video_image.depth, self.raw_video_image.nChannels)
#cv.Not(self.raw_depth_image,self.raw_depth_image)
cv.CvtColor(self.raw_depth_image,contour_depth_image_bgr, cv.CV_GRAY2BGR)
cv.And(self.raw_video_image,contour_depth_image_bgr,self.raw_masked_image)
masked_image = pyglet.image.ImageData(640,480, "BGR", self.raw_masked_image.tostring())
return masked_image
if __name__ == '__main__':
cv.NamedWindow("Depth")
converter = Converter()
#os.system('espeak -v en "this is convertor" ')
window = pyglet.window.Window()
def speak_message():
global count
if (count == 200):
os.system('espeak -v en+f4 "today we will play with apple" ')
# count = count + 1
time.sleep(1)
elif (count == 510):
os.system('espeak -v en+f4 "a for apple" ')
# count = count + 1
time.sleep(1)
elif (count == 830):
os.system('espeak -v en+f4 "apple is a fruit" ')
# count = count + 1
time.sleep(1)
elif (count == 940):
os.system('espeak -v en+f4 "Here comes the red apple" ')
# count = count + 1
time.sleep(1)
elif (count == 1400):
os.system('espeak -v en+f4 "Here comes the green apple" ')
# count = count + 1
time.sleep(1)
def update_images(dt):
global converter, depth, video, masked, centers
converter.get_data()
depth = converter.get_depth()
centers = converter.get_centers()
video = converter.get_video()
masked = converter.get_masked()
#os.system('espeak -v en "a for apple" ')
pyglet.clock.schedule_interval(update_images, 1/30.0)
update_images(0.0)
## os.system('espeak -v en "a for apple" ')
## time.sleep(1)
## os.system('espeak -v en "apple is a fruit" ')
## time.sleep(1)
## os.system('espeak -v en "a is first alphabet" ')
## time.sleep(1)
## os.system('espeak -v en "Now lets play with apple" ')
## time.sleep(1)
#speech_output = speechd.Speaker('apple')
#speech_output.speak('a for apple')
# if depth is not None:
# depth_sprite = pyglet.sprite.Sprite(depth)
if video is not None:
video_sprite = pyglet.sprite.Sprite(video)
# masked_sprite = pyglet.sprite.Sprite(masked)
mike = pyglet.image.load("mike.jpg")
mike.anchor_x = mike.width // 2
mike.anchor_y = mike.height // 2
mike_sprite = pyglet.sprite.Sprite(mike)
mike1 = pyglet.image.load("apple.jpg")
mike1.anchor_x = mike.width // 2
mike1.anchor_y = mike.height // 2
mike1_sprite = pyglet.sprite.Sprite(mike1)
mike2 = pyglet.image.load("green_apple.jpg")
mike2.anchor_x = mike.width // 2
mike2.anchor_y = mike.height // 2
mike2_sprite = pyglet.sprite.Sprite(mike2)
start = True
#os.system('espeak -v en "a for apple" ')
@window.event
#os.system('espeak -v en "a for apple" ')
def on_draw():
global depth, video, masked, centers, start, x, y, angle, dist
global px, py, pa, ps
global count
window.width = 1280
window.height = 960
window.clear()
video_sprite.image = video
video_sprite.scale = 2
video_sprite.draw()
sx = sy = 0
ease = 0.35
if start:
x = y = angle = dist = 0
px = py = pa = ps = 0
#os.system('espeak -v en "a for apple" ')
start = False
if len(centers) == 4:
px = mike_sprite.x
py = mike_sprite.y
pa = mike_sprite.rotation
ps = mike_sprite.scale
for c in range(len(centers)):
if c % 2 == 0:
sx += centers[c]
else:
sy += centers[c]
x = (sx/(len(centers)/2) * 2 - px) * ease + px
y = (sy/(len(centers)/2) * 2 - py) * ease + py
dx = centers[2] - centers[0]
dy = centers[3] - centers[1]
#os.system('espeak -v en "a for apple" ')
if dx != 0:
angle = math.atan((dy*1.0)/dx) / math.pi * -180
#os.system('espeak -v en "a for apple" ')
dist = math.sqrt(dx*dx+dy*dy)
mike_sprite.x = x
mike_sprite.y = y
mike_sprite.rotation = (angle - pa) * ease + pa
mike_sprite.scale = (dist/320*2 - ps) * ease + ps
mike1_sprite.x = x-300
mike1_sprite.y = y-300
mike2_sprite.x = x + 300
mike2_sprite.y = y + 300
mike_sprite.draw()
if (count > 950):
mike1_sprite.draw()
if (count > 1420):
mike2_sprite.draw()
#os.system('espeak -v en "a for apple" ')
if (count < 1500):
speak_message()
count = count + 1
pyglet.app.run()
#thread.start_new_thread(os.system('espeak -v en "a for apple" '))
#thread.start_new_thread(pyglet.app.run())