def run(argv):
mode = argv
if (mode == 0):
#check Arrow
sensor.reset()
'''sensor.set_auto_gain(False)
sensor.set_contrast(1)
sensor.set_gainceiling(16)
#sensor.set_windowing((200, 200)) # 240x240 center pixels of VGA
sensor.set_framesize(sensor.QQVGA)
sensor.set_pixformat(sensor.GRAYSCALE)
sensor.set_auto_whitebal(False)
'''
sensor.set_pixformat(sensor.GRAYSCALE)
sensor.set_framesize(sensor.QQVGA)
sensor.set_vflip(True)
sensor.set_hmirror(True)
sensor.skip_frames(time=2000)
findArrow()
else:
#check signal mode
sensor.reset()
sensor.set_auto_gain(False)
sensor.set_auto_whitebal(True)
sensor.set_contrast(-3)
sensor.set_brightness(-3)
sensor.set_gainceiling(8)
sensor.set_pixformat(sensor.RGB565)
sensor.set_vflip(True)
sensor.set_framesize(sensor.VGA)
sensor.set_windowing((240, 240)) # 240x240 center pixels of VGA
#sensor.set_windowing((200, 200)) # 200x200 center pixels of VGA
sensor.skip_frames(time=800)
checkSignal()
def init(is_debug, pixformat, delay_time):
#关闭串口，防止初始化过程溢出
uart.deinit()
uart2.deinit()
sensor.reset()
sensor.set_pixformat(sensor.RGB565) #RGB565
sensor.set_framesize(sensor.QVGA) #320*240
sensor.set_gainceiling(128) #增益上限 2,4,8,16,32,64,128
sensor.set_contrast(3) #对比度 -3至3
sensor.set_brightness(0) #亮度。-3至+3
sensor.set_saturation(3) #饱和度。-3至+3
sensor.set_auto_exposure(True) #自动曝光
sensor.skip_frames(time=delay_time)
sensor.set_auto_gain(False) # 在进行颜色追踪时，必须关闭
sensor.set_auto_whitebal(False) # 在进行颜色追踪时，必须关闭
#重新打开串口
uart.init(115200, timeout_char=1000)
uart2.init(115200, timeout_char=1000)
#判断是否debug模式
global CompetitionScene
if is_debug == True:
CompetitionScene = 0
else:
CompetitionScene = 1
def CorrTest(loopCnt = 220, barLen=120):
sensor.reset()
# Sensor settings
sensor.set_contrast(1)
sensor.set_gainceiling(16)
sensor.set_framesize(sensor.QVGA)
sensor.set_pixformat(sensor.RGB565)
#sensor.set_windowing((480,272))
clock = time.clock()
avg = 0.0
startTick = time.ticks()
corr = 0.3
while (True):
if time.ticks() - startTick > loopCnt:
break
clock.tick()
img = sensor.snapshot()
for i in range(7):
img.draw_rectangle(160-i*15, 120-i*15, i*15*2, i*15*2)
corr += 0.05
if corr >= 4.0:
corr = 0.3
img.lens_corr(corr)
lnLen = (barLen * (loopCnt - (time.ticks() - startTick))) // loopCnt
DrawPgsBar(img, barLen, loopCnt, startTick)
img.draw_string(4,4,'Lens correction %.2f' % (corr), color=(0,0,0))
def face_detect():
print("Detecting face...")
sensor.reset()
sensor.set_contrast(1)
sensor.set_gainceiling(16)
sensor.set_framesize(sensor.HQVGA)
sensor.set_pixformat(sensor.GRAYSCALE)
clock = time.clock()
LED.on()
for i in range(60):
img = sensor.snapshot()
objects = img.find_features(face_cascade, threshold=0.75, scale_factor=1.25)
# Draw objects
if objects:
for r in objects:
img.draw_rectangle(r)
cx=r[0]+r[2]//2
cy=r[1]+r[3]//2
img.draw_cross(cx,cy)
obj = find_max(objects)
cx_array.append(obj[0]+obj[2]//2)
cy_array.append(obj[1]+obj[3]//2)
h_array.append(obj[2])
h_threshold = obj[2]
if len(cx_array) == filter_stages:
LED.off()
print('Face detected.\nStart tracking...')
return True
LED.off()
print('No face detected.\nTrying color mode...')
return False
def FaceTest():
sensor.reset()
# Sensor settings
sensor.set_contrast(1)
sensor.set_gainceiling(16)
# HQVGA and GRAYSCALE are the best for face tracking.
sensor.set_framesize(sensor.VGA)
sensor.set_windowing((320, 240))
#sensor.set_framesize(sensor.QVGA)
sensor.set_pixformat(sensor.GRAYSCALE)
#sensor.set_framerate(2<<9|3<<11)
# Load Haar Cascade
# By default this will use all stages, lower satges is faster but less accurate.
face_cascade = image.HaarCascade("frontalface", stages=25)
print(face_cascade)
clock = time.clock()
for i in range(250):
clock.tick()
img = sensor.snapshot()
objects = img.find_features(face_cascade,
threshold=0.75,
scale_factor=1.25)
fID = 0
for r in objects:
img.draw_rectangle(r, color=(0, 0, 0), thickness=3)
#img.draw_rectangle(r[0], r[1], 48, 10, fill=True, color=(0,0,0))
fID += 1
s = 'face %d' % (fID)
img.draw_string(r[0], r[1], s)
print(clock.fps())
def facetrack_camInit():
print("INIT Facetrack")
# Reset sensor
sensor.reset()
sensor.set_contrast(3)
sensor.set_gainceiling(16)
sensor.set_framesize(sensor.VGA)
sensor.set_windowing((200, 200))
sensor.set_pixformat(sensor.GRAYSCALE)
sensor.skip_frames(time = 2000)
def face_recog(calc_time, vi_ip):
pin = pyb.millis()
print(pin)
print(calc_time)
cc = 0
#pyb.elapsed_millis(start)
while pyb.elapsed_millis(pin) < calc_time:
print("top of face recog function")
#snapshot on face detection
RED_LED_PIN = 1
BLUE_LED_PIN = 3
sensor.reset() # Initialize the camera sensor.
sensor.set_contrast(3)
sensor.set_gainceiling(16)
sensor.set_pixformat(sensor.GRAYSCALE)
sensor.set_framesize(sensor.HQVGA) # or sensor.QQVGA (or others)
#sensor.alloc_extra_fb()
sensor.skip_frames(time=2000) # Let new settings take affect.
face_cascade = image.HaarCascade("frontalface", stages=25)
uos.chdir("/")
pyb.LED(RED_LED_PIN).on()
print("About to start detecting faces...")
sensor.skip_frames(time=2000) # Give the user time to get ready.
pyb.LED(RED_LED_PIN).off()
print("Now detecting faces!")
pyb.LED(BLUE_LED_PIN).on()
diff = 10 # We'll say we detected a face after 10 frames.
try:
while (diff):
img = sensor.snapshot()
sensor.alloc_extra_fb(img.width(), img.height(),
sensor.GRAYSCALE)
faces = img.find_features(face_cascade,
threshold=0.5,
scale_factor=1.5)
sensor.dealloc_extra_fb()
if faces:
diff -= 1
for r in faces:
img.draw_rectangle(r)
elif (pyb.elapsed_millis(pin)) > calc_time:
raise Exception
pyb.LED(BLUE_LED_PIN).off()
print("Face detected! Saving image...")
pic_name = "snapshot-person.pgm"
sensor.snapshot().save(
pic_name) # Save Pic. to root of SD card -- uos.chdir("/")
pyb.delay(100)
facial_recog(pic_name, vi_ip)
gc.collect()
except Exception as go:
print("we are in exception")
pyb.LED(BLUE_LED_PIN).off()
gc.collect()
def face_detect(init_start, calc_time):
print("~~~~~~~~~~~~~~~~FACE_DETECT~~~~~~~~~~~~~~~~~~~~~~")
gc.collect() #garbage collection
while pyb.elapsed_millis(init_start) < calc_time: #while time not expired
#snapshot on face detection
RED_LED_PIN = 1
BLUE_LED_PIN = 3
sensor.reset() # Initialize the camera sensor.
sensor.set_contrast(3) #set to highest contrast setting
sensor.set_gainceiling(16)
sensor.set_pixformat(
sensor.GRAYSCALE) #grayscale for facial recognition
sensor.set_framesize(sensor.HQVGA)
sensor.skip_frames(time=2000) # Let new settings take affect.
face_cascade = image.HaarCascade(
"frontalface",
stages=25) #Using Frontal Face Haar Cascade Classifier
uos.chdir("/")
pyb.LED(RED_LED_PIN).on()
print("About to start detecting faces...")
sensor.skip_frames(time=2000) # Give the user time to get ready.
pyb.LED(RED_LED_PIN).off()
print("Now detecting faces!")
pyb.LED(BLUE_LED_PIN).on()
diff = 10 # We'll say we detected a face after 10 frames.
try:
while (diff):
img = sensor.snapshot()
sensor.alloc_extra_fb(
img.width(), img.height(),
sensor.GRAYSCALE) #allocate more space for image
faces = img.find_features(
face_cascade, threshold=0.5,
scale_factor=1.5) #detecting face features
sensor.dealloc_extra_fb()
if faces:
diff -= 1
for r in faces:
img.draw_rectangle(r)
elif (pyb.elapsed_millis(init_start)
) > calc_time: #if time is expired, leave function
raise Exception
pyb.LED(BLUE_LED_PIN).off()
print("Face detected! Saving image...")
pic_name = "snapshot-person.pgm"
sensor.snapshot().save(pic_name) # Save Pic. to root of SD card
pyb.delay(100)
gc.collect() #garbage collection
return pic_name
except Exception as go:
print("exception - time expired")
pyb.LED(BLUE_LED_PIN).off()
gc.collect() #garbage collection
def CIFAR10Test(loopCnt=600, isFull=False, barLen=105):
pyb.LED(1).off()
sensor.reset() # Reset and initialize the sensor.
sensor.set_contrast(3)
sensor.set_pixformat(
sensor.RGB565) # Set pixel format to RGB565 (or GRAYSCALE)
sensor.set_framesize(sensor.VGA) # Set frame size to QVGA (320x240)
sensor.set_windowing((192, 192)) # Set window
sensor.skip_frames(time=300) # Wait for settings take effect.
sensor.set_auto_gain(False)
#sensor.set_framerate(0<<9|1<<12)
if isFull:
net = nn.load('/cifar10.network')
else:
net = nn.load('/cifar10_fast.network')
labels = [
'plane', 'auto', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship',
'truck'
]
clock = time.clock()
tAvg = 0.0
startTick = time.ticks()
while (True):
if time.ticks() - startTick > loopCnt:
break
clock.tick()
img = sensor.snapshot()
t0 = time.ticks()
lst = net.search(img, threshold=0.640, min_scale=1, scale_mul=0.8, \
x_overlap=-1, y_overlap=-1, contrast_threshold=0.5)
t1 = time.ticks() - t0
tAvg = tAvg * 0.9 + t1 * 0.1
img.draw_string(
4,
8,
'CIFAR-10: classify:\nplane,auto,cat,dog,\ndeer,horse,frog,ship,\ntruck,horse',
color=(0, 0, 0))
lnLen = (barLen * (loopCnt - (time.ticks() - startTick))) // loopCnt
DrawPgsBar(img, barLen, loopCnt, startTick)
for obj in lst:
print(' %s - Confidence %f%%' %
(labels[obj.index()], obj.value()))
rc = obj.rect()
#img.draw_rectangle(rc, color=(255,255,255))
img.draw_rectangle(barLen + 10,
1,
50,
8,
fill=True,
color=(0, 0, 0))
img.draw_string(barLen + 10, 0, labels[obj.index()])
print('algo time cost : %.2f ms' % (tAvg))
def test_color_bars():
sensor.reset()
# Set sensor settings
sensor.set_brightness(0)
sensor.set_saturation(3)
sensor.set_gainceiling(8)
sensor.set_contrast(2)
# Set sensor pixel format
sensor.set_framesize(sensor.QVGA)
sensor.set_pixformat(sensor.RGB565)
# Enable colorbar test mode
sensor.set_colorbar(True)
# Skip a few camera to allow the sensor settle down
for i in range(0, 100):
image = sensor.snapshot()
#color bars thresholds
t = [
lambda r, g, b: r < 70 and g < 70 and b < 70, # Black
lambda r, g, b: r < 70 and g < 70 and b > 200, # Blue
lambda r, g, b: r > 200 and g < 70 and b < 70, # Red
lambda r, g, b: r > 200 and g < 70 and b > 200, # Purple
lambda r, g, b: r < 70 and g > 200 and b < 70, # Green
lambda r, g, b: r < 70 and g > 200 and b > 200, # Aqua
lambda r, g, b: r > 200 and g > 200 and b < 70, # Yellow
lambda r, g, b: r > 200 and g > 200 and b > 200
] # White
# color bars are inverted for OV7725
if (sensor.get_id() == sensor.OV7725):
t = t[::-1]
#320x240 image with 8 color bars each one is approx 40 pixels.
#we start from the center of the frame buffer, and average the
#values of 10 sample pixels from the center of each color bar.
for i in range(0, 8):
avg = (0, 0, 0)
idx = 40 * i + 20 #center of colorbars
for off in range(0, 10): #avg 10 pixels
rgb = image.get_pixel(idx + off, 120)
avg = tuple(map(sum, zip(avg, rgb)))
if not t[i](avg[0] / 10, avg[1] / 10, avg[2] / 10):
raise Exception('COLOR BARS TEST FAILED.'
'BAR#(%d): RGB(%d,%d,%d)' %
(i + 1, avg[0] / 10, avg[1] / 10, avg[2] / 10))
print('COLOR BARS TEST PASSED...')
def init(self, robot_):
self.robot = robot_
if self.robot == self.ROBOT_O: #O_bot
self.thresholds = [
(35, 100, 26, 78, 22, 72), #Ball
(68, 100, -19, 27, 41, 81), #Yellow Goal
(20, 41, -6, 15, -55, -15)
] # Blue Goal
self.window = (59, 18, 184, 181)
elif self.robot == self.ROBOT_P2: #P2_bot
self.thresholds = [
(39, 100, 26, 78, 22, 72), #Ball
(68, 100, -19, 27, 41, 81), #Yellow Goal
(20, 41, -6, 25, -55, -15)
] # Blue Goal
self.window = (71, 4, 193, 191)
# sensor setup
sensor.reset()
sensor.set_pixformat(sensor.RGB565)
sensor.set_framesize(sensor.QVGA) #Resolution
sensor.set_windowing(self.window)
sensor.skip_frames(time=1000)
sensor.set_auto_exposure(False)
sensor.set_auto_whitebal(False)
# Need to let the above settings get in...
sensor.skip_frames(time=250)
# === GAIN ===
curr_gain = sensor.get_gain_db()
sensor.set_auto_gain(False, gain_db=curr_gain)
# === EXPOSURE ===
curr_exposure = sensor.get_exposure_us()
sensor.set_auto_exposure(False, exposure_us=int(curr_exposure * 0.5))
# === WHITE BAL ===
sensor.set_auto_whitebal(
False, rgb_gain_db=(-6.02073, -3.762909,
3.33901)) #Must remain false for blob tracking
sensor.set_brightness(2)
sensor.set_contrast(2)
sensor.set_saturation(2)
sensor.skip_frames(time=500)
def face_detect(init_start, calc_time):
print("~~~~~~~~~~~~~~~~FACE_DETECT~~~~~~~~~~~~~~~~~~~~~~")
gc.collect()
while pyb.elapsed_millis(init_start) < calc_time:
RED_LED_PIN = 1
BLUE_LED_PIN = 3
sensor.reset()
sensor.set_contrast(3)
sensor.set_gainceiling(16)
sensor.set_pixformat(sensor.GRAYSCALE)
sensor.set_framesize(sensor.HQVGA)
sensor.skip_frames(time=2000)
face_cascade = image.HaarCascade("frontalface", stages=25)
uos.chdir("/")
pyb.LED(RED_LED_PIN).on()
print("About to start detecting faces...")
sensor.skip_frames(time=2000)
pyb.LED(RED_LED_PIN).off()
print("Now detecting faces!")
pyb.LED(BLUE_LED_PIN).on()
diff = 10
try:
while (diff):
img = sensor.snapshot()
sensor.alloc_extra_fb(img.width(), img.height(),
sensor.GRAYSCALE)
faces = img.find_features(face_cascade,
threshold=0.5,
scale_factor=1.5)
sensor.dealloc_extra_fb()
if faces:
diff -= 1
for r in faces:
img.draw_rectangle(r)
elif (pyb.elapsed_millis(init_start)) > calc_time:
raise Exception
pyb.LED(BLUE_LED_PIN).off()
print("Face detected! Saving image...")
pic_name = "snapshot-person.pgm"
sensor.snapshot().save(pic_name)
pyb.delay(100)
gc.collect()
return pic_name
except Exception as go:
print("exception - time expired")
pyb.LED(BLUE_LED_PIN).off()
gc.collect()
def init(is_debug,delay_time):
uart.deinit()
sensor.reset()
sensor.set_pixformat(sensor.GRAYSCALE)
sensor.set_framesize(sensor.QVGA)
sensor.set_contrast(3)
sensor.set_brightness(-3)
sensor.set_auto_exposure(True)
sensor.skip_frames(time = delay_time)
sensor.set_auto_whitebal(False)
uart.init(115200,timeout_char=1000)
lcd.init()
global CompetitionScene
if is_debug==True:
CompetitionScene=0
else:
CompetitionScene=1
def test_color_bars():
sensor.reset()
# Set sensor settings
sensor.set_brightness(0)
sensor.set_saturation(0)
sensor.set_gainceiling(8)
sensor.set_contrast(2)
# Set sensor pixel format
sensor.set_framesize(sensor.QVGA)
sensor.set_pixformat(sensor.RGB565)
# Enable colorbar test mode
sensor.set_colorbar(True)
# Skip a few frames to allow the sensor settle down
# Note: This takes more time when exec from the IDE.
for i in range(0, 100):
image = sensor.snapshot()
# Color bars thresholds
t = [lambda r, g, b: r < 50 and g < 50 and b < 50, # Black
lambda r, g, b: r < 50 and g < 50 and b > 200, # Blue
lambda r, g, b: r > 200 and g < 50 and b < 50, # Red
lambda r, g, b: r > 200 and g < 50 and b > 200, # Purple
lambda r, g, b: r < 50 and g > 200 and b < 50, # Green
lambda r, g, b: r < 50 and g > 200 and b > 200, # Aqua
lambda r, g, b: r > 200 and g > 200 and b < 50, # Yellow
lambda r, g, b: r > 200 and g > 200 and b > 200] # White
# 320x240 image with 8 color bars each one is approx 40 pixels.
# we start from the center of the frame buffer, and average the
# values of 10 sample pixels from the center of each color bar.
for i in range(0, 8):
avg = (0, 0, 0)
idx = 40*i+20 # center of colorbars
for off in range(0, 10): # avg 10 pixels
rgb = image.get_pixel(idx+off, 120)
avg = tuple(map(sum, zip(avg, rgb)))
if not t[i](avg[0]/10, avg[1]/10, avg[2]/10):
raise Exception("COLOR BARS TEST FAILED. "
"BAR#(%d): RGB(%d,%d,%d)"%(i+1, avg[0]/10, avg[1]/10, avg[2]/10))
print("COLOR BARS TEST PASSED...")
def LENETTest(loopCnt=1200, barLen=60):
sensor.reset() # Reset and initialize the sensor.
sensor.set_contrast(3)
sensor.set_pixformat(
sensor.GRAYSCALE) # Set pixel format to RGB565 (or GRAYSCALE)
sensor.set_framesize(sensor.VGA) # Set frame size to QVGA (320x240)
sensor.set_windowing((84, 84)) # Set 128x128 window.
sensor.skip_frames(time=1400) # Wait for settings take effect.
sensor.set_auto_gain(False)
sensor.set_framerate(2 << 2)
#sensor.set_auto_whitebal(False)
#sensor.set_auto_exposure(False)
net = nn.load('/lenet.network')
labels = ['0', '1', '2', '3', '4', '5', '6', '7', '8', '9']
clock = time.clock()
avg = 0.0
pyb.LED(1).on()
startTick = time.ticks()
while (True):
if time.ticks() - startTick > loopCnt:
break
clock.tick()
img = sensor.snapshot()
img.draw_string(3, 8, 'recg 0-9', color=(0, 0, 0))
t1 = time.ticks()
tmp_img = img.copy().binary([(120, 255)], invert=True)
lst = net.search(tmp_img, threshold=0.8, min_scale=1, scale_mul=0.8, \
x_overlap=-1, y_overlap=-1, contrast_threshold=0.5, softmax=False)
t2 = time.ticks() - t1
avg = avg * 0.95 + t2 * 0.05
lnLen = (barLen * (loopCnt - (time.ticks() - startTick))) // loopCnt
img.draw_rectangle(0, 2, barLen + 1, 3)
img.draw_rectangle(0, 3, lnLen, 1, fill=True)
for obj in lst:
print('Detected %s - Confidence %f%%' %
(labels[obj.index()], obj.value()))
img.draw_rectangle(obj.rect())
img.draw_string(barLen + 8,
2,
labels[obj.index()],
color=(0, 0, 0))
# print(clock.fps())
print('algo time cost : %.2f ms' % (avg))
def FaceTest(loopCnt=220, barLen=120):
sensor.reset()
# Sensor settings
sensor.set_contrast(1)
#sensor.set_gainceiling(16)
# HQVGA and GRAYSCALE are the best for face tracking.
#sensor.set_framesize(sensor.VGA)
#sensor.set_windowing((320,240))
sensor.set_framesize(sensor.VGA)
sensor.set_windowing((320, 240))
sensor.set_pixformat(sensor.GRAYSCALE)
#sensor.set_auto_gain(False)
#sensor.set_auto_whitebal(True) # must be turned off for color tracking
# Load Haar Cascade
# By default this will use all stages, lower satges is faster but less accurate.
face_cascade = image.HaarCascade("frontalface", stages=25)
print(face_cascade)
clock = time.clock()
avg = 0.0
startTick = time.ticks()
while (True):
if time.ticks() - startTick > loopCnt:
break
clock.tick()
img = sensor.snapshot()
img.draw_string(4, 4, 'Face Detect', color=(0, 0, 0))
t0 = time.ticks()
objects = img.find_features(face_cascade,
threshold=0.75,
scale_factor=1.25)
t1 = time.ticks() - t0
avg = avg * 0.90 + t1 * 0.10
fID = 0
lnLen = (barLen * (loopCnt - (time.ticks() - startTick))) // loopCnt
DrawPgsBar(img, barLen, loopCnt, startTick)
for r in objects:
img.draw_rectangle(r, thickness=3)
img.draw_rectangle(r[0], r[1], 48, 10, fill=True)
fID += 1
s = 'face %d' % (fID)
img.draw_string(r[0], r[1], s, color=(0, 0, 0))
print('algo time cost : %.2f ms' % (avg))
def init(is_debug, pixformat, delay_time):
uart.deinit()
sensor.reset()
if pixformat == "GRAY":
sensor.set_pixformat(sensor.GRAYSCALE)
elif pixformat == "RGB":
sensor.set_pixformat(sensor.RGB565)
sensor.set_framesize(sensor.QQVGA)
sensor.set_gainceiling(128)
sensor.set_contrast(3)
sensor.set_brightness(0)
sensor.set_saturation(3)
sensor.set_auto_exposure(True)
sensor.skip_frames(time=delay_time)
sensor.set_auto_gain(False)
sensor.set_auto_whitebal(False)
uart.init(115200, timeout_char=1000)
global CompetitionScene
if is_debug == True:
CompetitionScene = 0
else:
CompetitionScene = 1
def LENetTest(loopCnt=600, isFull=False, barLen=80):
sensor.reset() # Reset and initialize the sensor.
sensor.set_contrast(3)
sensor.set_pixformat(
sensor.GRAYSCALE) # Set pixel format to RGB565 (or GRAYSCALE)
sensor.set_framesize(sensor.CIF) # Set frame size to QVGA (320x240)
sensor.set_windowing((96, 96)) # Set 128x128 window.
sensor.set_auto_gain(True)
sensor.set_auto_whitebal(False)
sensor.set_auto_exposure(False)
sensor.skip_frames(time=400) # Wait for settings take effect.
net = nn.load('/lenet.network')
labels = ['0', '1', '2', '3', '4', '5', '6', '7', '8', '9']
clock = time.clock()
tAvg = 0.0
startTick = time.ticks()
while (True):
if time.ticks() - startTick > loopCnt:
break
clock.tick()
img = sensor.snapshot()
t0 = time.ticks()
tmp_img = img.copy().binary([(120, 255)], invert=True)
lst = net.search(tmp_img, threshold=0.8, min_scale=1.0, scale_mul=0.8, \
x_overlap=-1, y_overlap=-1, contrast_threshold=0.5, softmax=False)
t1 = time.ticks() - t0
tAvg = tAvg * 0.9 + t1 * 0.1
img.draw_string(4, 8, 'LENET', color=(0, 0, 0))
lnLen = (barLen * (loopCnt - (time.ticks() - startTick))) // loopCnt
DrawPgsBar(img, barLen, loopCnt, startTick)
for obj in lst:
print('Detected %s - Confidence %f%%' %
(labels[obj.index()], obj.value()))
img.draw_rectangle(obj.rect(), color=(255, 255, 255))
img.draw_string(4, 4, labels[obj.index()])
print('algo time cost : %.2f ms' % (tAvg))
import sensor
sensor.set_contrast(1)
sensor.set_gainceiling(8)
sensor.set_framesize(sensor.QQVGA)
sensor.set_pixformat(sensor.RGB565)
image = sensor.snapshot()
image.save("/test.ppm")
#求x的平方的和
def Square_Sum(data,datalen):
i = 0
z = 0
for i in range(datalen):
z = z + data[i]*data[i]
return z
#设置摄像头相关参数
sensor.reset()
sensor.set_pixformat(sensor.RGB565) #设置图片格式（彩色/灰度图）
sensor.set_framesize(sensor.QVGA) #设置图像大小
sensor.skip_frames(10) #等待设置生效
sensor.set_auto_whitebal(False) #关闭白平衡
sensor.set_auto_gain(False) #关闭自动亮度调节
sensor.set_contrast(0) #对比度 -3~3 7个调节
sensor.set_brightness(0) #亮度
sensor.set_saturation(0) #饱和度
uart = UART(3,115200) #设置串口
led = pyb.LED(3) #提示灯
clock = time.clock() #初始化时钟
#颜色识别区域的中心坐标
x_distance = y_distance = 0
#路径识别参数
ROIS = [ # [ROI, weight]
#(0, 110, 160, 10),
#(0, 100, 160, 10),
(0, 090, 160, 10),
# Importe de librerias
import sensor, image, lcd, time, utime
import KPU as kpu
# Configuración inicial de la pantalla LCD y la camara OV2640
lcd.init() # Inicializa la pantalla
sensor.reset() # Inicializa la camara
sensor.set_pixformat(sensor.RGB565) # Define el formato de color de la imagen
sensor.set_framesize(
sensor.QVGA) # Establece la captura de imagen como QVGA (320x240)
sensor.set_windowing(
(224, 224)) # Establece el tamaño de imagen con el que se entreno la red
sensor.set_vflip(1) # Rotación vertical de la imagen
sensor.set_saturation(-3) # Saturacion
sensor.set_brightness(-3) # brightness
sensor.set_contrast(-3) # contrast
lcd.clear() # Limpia la pantalla y la deja en negro
# Descripción y carga del modelo
labels = ['Acaro', 'Bueno',
'Manchado'] # Etiquetas de la ultima capa de la red
task = kpu.load(
'/sd/3clases.kmodel') # Acá va al ubicación del archivo .kmodel (CARGA)
kpu.set_outputs(task, 0, 1, 1,
3) # Aqúi van las dimensiones de la ultima capa de la red
while (True):
tick1 = utime.ticks_ms()
# Ejecucion del modelo en tiempo real
from pyb import UART
import math
# 初始化摄像头
clock = time.clock()
sensor.reset() # 初始化光感元件
if sensor.get_id() == sensor.OV7725:
sensor.set_hmirror(True) # 水平方向翻转
sensor.set_vflip(True) # 垂直方向翻转
sensor.set_pixformat(sensor.RGB565) # 设置为rgb
sensor.set_framesize(sensor.QVGA) # 设置图像大小
sensor.skip_frames(20) # 跳过前20帧
sensor.set_auto_exposure(1)
sensor.set_auto_whitebal(False) # 关闭自动白平衡
sensor.set_auto_gain(False) # 关闭自动增益
sensor.set_contrast(+3)
clock = time.clock() # 跟踪FPS帧率
uart = UART(3, 19200) #初始化串口三
def find_ball():
#引入和声明数据
global fps
global img
target_ball = 0
target_ball_size = 0
#先查找色块
img = sensor.snapshot().lens_corr(strength=1.1, zoom=1.0)
blobs = img.find_blobs([ball_threshold], roi=area, pixels_threshold=20)
# Color Tracking Thresholds (L Min, L Max, A Min, A Max, B Min, B Max)
# The below thresholds track in general red/green things. You may wish to tune them...
# generic_red_thresholds -> index is 0 so code == (1 << 0)
# generic_green_thresholds -> index is 1 so code == (1 << 1)
# Codes are or'ed together when "merge=True" for "find_blobs".
sensor.reset()
sensor.set_pixformat(sensor.RGB565)
sensor.set_framesize(sensor.QVGA)
sensor.skip_frames(time=2000)
sensor.set_auto_exposure(False, 5000)
sensor.set_auto_gain(False, 0, 0) # must be turned off for color tracking
sensor.set_auto_whitebal(False,
(0, 0, 0)) # must be turned off for color tracking
sensor.set_saturation(+3)
sensor.set_contrast(-3)
clock = time.clock()
# _
# | \
# | |\
# | | \
# Goal/ _____| _| \
# Hole | | \
# | | \
# | | \
# | | \
# | | \
# | | \
# Goal _ | | \ <---- upward_distance
# Hight | | \
#get the gains and exposure
gain_db = sensor.get_gain_db()
exposure_us = sensor.get_exposure_us()
rgb_gain_db = sensor.get_rgb_gain_db()
print("gain_db is " + str(gain_db))
print("exposure is " + str(exposure_us))
print("rgb_gain_db is " + str(rgb_gain_db))
# Set the gain and exposure as fixed (not concerned about the values)
sensor.set_auto_gain(False, gain_db)
sensor.set_auto_exposure(False, exposure_us)
sensor.set_auto_whitebal(False, rgb_gain_db)
# Setup contrast, brightness and saturation
sensor.set_contrast(0) # range -3 to +3
sensor.set_brightness(0) # range -3 to +3
sensor.set_saturation(0) # range -3 to +3
# Disable night mode (auto frame rate) and black level calibration (BLC)
sensor.__write_reg(0x0E, 0b00000000) # Disable night mode
sensor.__write_reg(0x3E, 0b00000000) # Disable BLC
sensor.__write_reg(0x13, 0b00000000) # disable automated gain
gain_db = sensor.get_gain_db()
exposure_us = sensor.get_exposure_us()
rgb_gain_db = sensor.get_rgb_gain_db()
print("gain_db is " + str(gain_db))
print("exposure is " + str(exposure_us))
print("rgb_gain_db is " + str(rgb_gain_db))
# Iris Detection 2 Example
#
# This example shows how to find the eye gaze (pupil detection) after finding
# the eyes in an image. This script uses the find_eyes function which determines
# the center point of roi that should contain a pupil. It does this by basically
# finding the center of the darkest area in the eye roi which is the pupil center.
#
# Note: This script does not detect a face first, use it with the telephoto lens.
import sensor, time, image
# Reset sensor
sensor.reset()
# Sensor settings
sensor.set_contrast(3)
sensor.set_gainceiling(16)
# Set resolution to VGA.
sensor.set_framesize(sensor.VGA)
# Bin/Crop image to 200x100, which gives more details with less data to process
sensor.set_windowing((220, 190, 200, 100))
sensor.set_pixformat(sensor.GRAYSCALE)
# Load Haar Cascade
# By default this will use all stages, lower stages is faster but less accurate.
eyes_cascade = image.HaarCascade("eye", stages=24)
print(eyes_cascade)
# 用于匿名的openmv，串口通信程序
import sensor, image, time, math, struct
from pyb import UART, LED, Timer
#初始化镜头
sensor.reset() #初始化摄像头，reset()是sensor模块里面的函数
sensor.set_pixformat(sensor.GRAYSCALE) #设置图像色彩格式，有RGB565色彩图和GRAYSCALE灰度图两种
sensor.set_framesize(sensor.QQVGA) #图像质量 分辨率为120*160
sensor.skip_frames(30)
sensor.set_auto_gain(True) #自动增益
sensor.set_auto_whitebal(True) #打开白平衡
sensor.set_contrast(3) #对比度
blue_led = LED(3)
clock = time.clock() #初始化时钟
uart = UART(3, 500000) #初始化串口 波特率 500000
thresholds = [0, 100] #自定义灰度阈值
fthresholds = [100, 256] #自定义灰度阈值
class Dot(object):
x = 0
y = 0
pixels = 0
num = 0
ok = 0
flag = 0
class singleline_check():
BG_UPDATE_FRAMES = 15 #50
BG_UPDATE_BLEND = 0 #128
# fire up servo board
i2c = I2C(sda=Pin('P5'), scl=Pin('P4'))
servo = Servos(i2c,
address=0x40,
freq=50,
min_us=650,
max_us=2800,
degrees=180)
sensor.reset()
# Sensor settings
sensor.set_contrast(3) #1
sensor.set_gainceiling(16)
sensor.set_auto_whitebal(False)
# HQVGA and GRAYSCALE are the best for face tracking.
sensor.set_framesize(sensor.HQVGA)
sensor.set_pixformat(sensor.GRAYSCALE)
sensor.skip_frames(time=2000)
# Load Haar Cascade
# By default this will use all stages, lower satges (25)is faster but less accurate.
face_cascade = image.HaarCascade("frontalface", stages=20)
print(face_cascade)
# BG subtraction setup
extra_fb = sensor.alloc_extra_fb(sensor.width(), sensor.height(),
sensor.GRAYSCALE)
#************************************ (C) COPYRIGHT 2019 ANO ***********************************#
import sensor, image, time, math, struct, lcd
import json
from pyb import LED, Timer
from struct import pack, unpack
#初始化镜头
sensor.reset()
sensor.set_pixformat(sensor.RGB565) #设置相机模块的像素模式
sensor.set_framesize(sensor.QVGA) #设置相机分辨率160*120
sensor.skip_frames(time=3000) #时钟
sensor.set_auto_whitebal(False) #若想追踪颜色则关闭白平衡
clock = time.clock() #初始化时钟
sensor.set_contrast(1) #设置相机图像对比度。-3至+3
sensor.set_gainceiling(16) #设置相机图像增益上限。2, 4, 8, 16, 32, 64, 128。
#lcd.init()
#主循环
class Recognition(object):
flag = 0
color = 0
cx = 0
cy = 0
Recognition = Recognition()
# 红色阈值
red_threshold = (40, 91, 34, 127, -60, 96)
# 绿色阈值
green_threshold = (42, 100, -84, -26, -2, 108)
import sensor, image, time, math #引入摄像头、图像、时间模块
from pid import PID #引入PID模块
from pyb import UART #引入UART串口通信模块
sensor.reset() #初始化摄像头
sensor.set_pixformat(sensor.RGB565) #设置RGB图像格式
sensor.set_framesize(sensor.QQVGA) #设置图像分辨率
sensor.skip_frames(10, 1000) #跳过10帧
sensor.set_contrast(1) #设置对比度
sensor.set_auto_whitebal(False) #关闭白平衡
#sensor.set_auto_gain(False) #关闭自动增益
time.sleep(2000) #等待2S
white_thresholds = (62, 98, 1, 9, -15, 10) #设置白色阈值
red_thresholds = (41, 83, 24, 83, -18, 60) #设置红色阈值
green_thresholds = (47, 93, -69, -24, 26, 83) #设置绿色阈值
threshold_change = red_thresholds #颜色阈值变量
size_threshold1 = 2500 #设置色块大小
size_threshold2 = 4000 #设置色块大小
x_pid = PID(p=4.9, i=0.5, imax=100) #初始化P、I参数
h_pid = PID(p=0.12, i=0.019, imax=50) #初始化P、I参数
uart = UART(3, 115200) #设置通信串口P4、P5
K = 500 #计算距离系数
logo = [
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0
] #判断距离大小是否趋于稳定的标识符
import sensor, time
sensor.reset()
# Set sensor settings
sensor.set_brightness(0)
sensor.set_saturation(0)
sensor.set_gainceiling(8)
sensor.set_contrast(2)
# Set sensor pixel format
sensor.set_framesize(sensor.QVGA)
sensor.set_pixformat(sensor.RGB565)
# Enable colorbar test mode
sensor.set_colorbar(True)
# Skip a few frames to allow the sensor settle down
for i in range(0, 30):
image = sensor.snapshot()
#color bars thresholds
t = [lambda r, g, b: r < 50 and g < 50 and b < 50, # Black
lambda r, g, b: r < 50 and g < 50 and b > 200, # Blue
lambda r, g, b: r > 200 and g < 50 and b < 50, # Red
lambda r, g, b: r > 200 and g < 50 and b > 200, # Purple
lambda r, g, b: r < 50 and g > 200 and b < 50, # Green
lambda r, g, b: r < 50 and g > 200 and b > 200, # Aqua
lambda r, g, b: r > 200 and g > 200 and b < 50, # Yellow
lambda r, g, b: r > 200 and g > 200 and b > 200] # White
#320x240 image with 8 color bars each one is approx 40 pixels.
# Set the maximum Frames Per Second for the main loop (fps)
MAX_FPS = 2.0
# Reset and initialize the sensor.
sensor.reset()
# Set pixel format to RGB565 (or GRAYSCALE)
sensor.set_pixformat(sensor.RGB565)
# Set frame size to 64x64 pixels
sensor.set_framesize(sensor.B64X64)
# Disable automatic exposure and gain
sensor.set_auto_exposure(False)
sensor.set_auto_gain(False)
sensor.set_contrast(0)
sensor.set_brightness(0)
# Wait two seconds for settings take effect.
sensor.skip_frames(time=2000)
# Create a clock object to track the FPS.
clock = time.clock()
# Load the Tensorflow Lite model
model = tf.load('whattolabel_resnet9.tflite')
def setLED(color='none'):
"""Function to set LED to a color (red, green, blue, none)
"""
# This threshold is used when extracting keypoints, the lower
# the threshold the higher the number of keypoints extracted.
KEYPOINTS_THRESH=30
# Keypoint-level threshold, range from 0 to 100.
# This threshold is used when matching two keypoint descriptors, it's the
# percentage of the distance between two descriptors to the max distance.
# In other words, the minimum matching percentage between 2 keypoints.
MATCHING_THRESH=70
#greenled = pyb.LED(1)
#blueled = pyb.LED(2)
# Reset sensor
sensor.reset()
# Sensor settings
sensor.set_contrast(1)
sensor.set_gainceiling(16)
sensor.set_framesize(sensor.HQVGA)
sensor.set_pixformat(sensor.GRAYSCALE)
# Skip a few frames to allow the sensor settle down
# Note: This takes more time when exec from the IDE.
#for i in range(0, 10):
# img = sensor.snapshot()
# img.draw_string(0, 0, "Please wait...")
# Load Haar Cascade
# By default this will use all stages, lower satges is faster but less accurate.
face_cascade = image.HaarCascade("frontalface", stages=25)
print(face_cascade)
user_exposure_time = 500 #camera exposure time, feel free to change. 900 is default value for tested setup
sensor.reset() # Initialize the camera sensor
sensor.set_pixformat(
sensor.GRAYSCALE
) # set camera format to grayscale (color not important in this example)
sensor.set_framesize(sensor.QVGA) # set camera resolution to QVGA 320 x 240
sensor.set_auto_whitebal(False) # Turn off white balance
sensor.set_auto_exposure(
False, exposure_us=user_exposure_time
) # set exposure time, user changable (user_exposure_time variable)
#these setting are manually set in order to prevent camera to change it during use (no automatic setting in machine vision!)
sensor.set_brightness(0) #set camera brightness
sensor.set_contrast(2) #set camera contrast
sensor.set_saturation(0) #set camera saturation
# Print out the initial gain for comparison.
print("Initial gain == %f db" % sensor.get_gain_db())
sensor.skip_frames(
time=2000) #small 2 seconds pause, so camera can update its settings
# calculating sensor gain
# user can change GAIN_SCALE factor in order to obtain more bright image
current_gain_in_decibels = sensor.get_gain_db() #current sensor gain
print("Current Gain == %f db" %
current_gain_in_decibels) #reporting current gain
sensor.set_auto_gain(False,
gain_db=current_gain_in_decibels * GAIN_SCALE) #new gain
print("New gain == %f db" % sensor.get_gain_db()) #reporting new sensor gain
