def run(self):
while self._running:
try:
self.logger.debug('loading inference model ...')
with CameraInference(face_detection.model()) as inference:
self.logger.debug('running inference ...')
for result in inference.run():
faces = face_detection.get_faces(result)
if faces:
self.logger.debug('found {} faces'.format(
len(faces)))
outgoing_signals = []
for face in faces:
signal_dict = {
'bounding_box': face.bounding_box,
'face_score': face.face_score,
'joy_score': face.joy_score,
}
outgoing_signal = Signal(signal_dict)
outgoing_signals.append(outgoing_signal)
if not self._running:
break
self.notify_signals(outgoing_signals)
except:
self.logger.exception('failed to get inference result!')
self.reset_camera()
self.release_camera()
def facedetect():
with PiCamera() as camera, Leds() as leds:
# Configure camera
camera.resolution = (1640, 922) # Full Frame, 16:9 (Camera v2)
camera.start_preview()
leds.update(Leds.privacy_on())
# Do inference on VisionBonnet
with CameraInference(face_detection.model()) as inference:
for result in inference.run():
if len(face_detection.get_faces(result)) >= 1:
camera.capture(
'faces_' + str(datetime.datetime.now()) + '.jpg')
# print(device.is_active)
print(led.is_active)
# device.on()
# bz.on()
led.on()
print(led.is_active)
# time.sleep(1)
# print(device.is_active)
led.off()
print(led.is_active)
break
# Stop preview
camera.stop_preview()
leds.update(Leds.privacy_on())
def iterator(self):
for inference_result in self._inference.run():
aiy_faces = face_detection.get_faces(inference_result)
if not aiy_faces:
yield None
continue
# inference runs on the vision bonnet, which grabs images from the camera directly
# we need to capture the image separately on the Raspberry in order to use dlib for face rec
image = MyImage.capture(self._camera, use_video_port=True)
inference_size = Size(w=inference_result.width,
h=inference_result.height)
image_size = Size(w=image.width, h=image.height)
yield InputOutput(
image=image,
faces=[
Face(
image_region=_get_image_region(aiy_face.bounding_box,
inference_size,
image_size),
face_score=aiy_face.face_score,
joy_score=aiy_face.joy_score,
person=self._person,
) for aiy_face in aiy_faces
],
)
def run_inference(num_frames, on_loaded):
"""Yields (faces, (frame_width, frame_height)) tuples."""
with CameraInference(face_detection.model()) as inference:
on_loaded()
for result in inference.run(num_frames):
yield face_detection.get_faces(result), (result.width,
result.height)
def detect_face():
with CameraInference(face_detection.model()) as camera_inference:
counter = 1
x_history, y_history, w_history, h_history = [], [], [], []
for result in camera_inference.run():
check_termination_trigger()
faces = face_detection.get_faces(result)
face = select_face(faces)
if face:
x, y, w, h = face.bounding_box
x_err = error_update(x_history, x)
y_err = error_update(y_history, y)
w_err = error_update(w_history, w)
h_err = error_update(h_history, h)
if face_detection_is_stable(x_err,
y_err,
w_err,
h_err,
cutoff=0.03):
face_box = (int(sum(x_history) / len(x_history)),
int(sum(y_history) / len(y_history)),
int(sum(w_history) / len(w_history)),
int(sum(h_history) / len(h_history)))
break
counter += 1
return face_box
def detect(num_frames):
"""Face detection camera inference example"""
# Forced sensor mode, 1640x1232, full FoV. See:
# https://picamera.readthedocs.io/en/release-1.13/fov.html#sensor-modes
# This is the resolution inference run on.
with PiCamera(sensor_mode=4, resolution=(1640, 1232),
framerate=30) as camera:
camera.start_preview()
# Annotator renders in software so use a smaller size and scale results
# for increased performance.
annotator = Annotator(camera, dimensions=(320, 240))
scale_x = 320 / 1640
scale_y = 240 / 1232
with CameraInference(face_detection.model()) as inference:
for result in inference.run(num_frames):
faces = face_detection.get_faces(result)
annotator.clear()
for face in faces:
x, y, width, height = face.bounding_box
annotator.bounding_box(
(scale_x * x, scale_y * y, scale_x *
(x + width), scale_y * (y + height)),
fill=0)
annotator.update()
print('#%05d (%5.2f fps): num_faces=%d, avg_joy_score=%.2f' %
(inference.count, inference.rate, len(faces),
avg_joy_score(faces)))
camera.stop_preview()
def _run_detector(self):
with PiCamera() as camera, PrivacyLED():
# Forced sensor mode, 1640x1232, full FoV. See:
# https://picamera.readthedocs.io/en/release-1.13/fov.html#sensor-modes
# This is the resolution inference run on.
camera.sensor_mode = 4
camera.resolution = (1640, 1232)
camera.framerate = 15
# Blend the preview layer with the alpha value from the flags.
camera.start_preview(alpha=self._preview_alpha)
with CameraInference(face_detection.model()) as inference:
self._play_sound(MODEL_LOAD_SOUND)
self._animator.start()
for i, result in enumerate(inference.run()):
faces = face_detection.get_faces(result)
# Calculate joy score as an average for all detected faces.
joy_score = 0.0
if faces:
joy_score = sum([face.joy_score for face in faces]) / len(faces)
# Append new joy score to the window and calculate mean value.
self._joy_score_window.append(joy_score)
self.joy_score = sum(self._joy_score_window) / len(
self._joy_score_window)
if self._num_frames == i or not self._run_event.is_set():
break
def main():
"""Face detection camera inference example."""
parser = argparse.ArgumentParser()
parser.add_argument(
'--num_frames',
'-n',
type=int,
dest='num_frames',
default=-1,
help='Sets the number of frames to run for, otherwise runs forever.')
args = parser.parse_args()
with PiCamera() as camera:
# Forced sensor mode, 1640x1232, full FoV. See:
# https://picamera.readthedocs.io/en/release-1.13/fov.html#sensor-modes
# This is the resolution inference run on.
camera.sensor_mode = 4
# Scaled and cropped resolution. If different from sensor mode implied
# resolution, inference results must be adjusted accordingly. This is
# true in particular when camera.start_recording is used to record an
# encoded h264 video stream as the Pi encoder can't encode all native
# sensor resolutions, or a standard one like 1080p may be desired.
camera.resolution = (1640, 1232)
# Start the camera stream.
camera.framerate = 30
camera.start_preview()
# Annotator renders in software so use a smaller size and scale results
# for increased performace.
annotator = Annotator(camera, dimensions=(320, 240))
scale_x = 320 / 1640
scale_y = 240 / 1232
# Incoming boxes are of the form (x, y, width, height). Scale and
# transform to the form (x1, y1, x2, y2).
def transform(bounding_box):
x, y, width, height = bounding_box
return (scale_x * x, scale_y * y, scale_x * (x + width),
scale_y * (y + height))
with CameraInference(face_detection.model()) as inference:
for i, result in enumerate(inference.run()):
if i == args.num_frames:
break
faces = face_detection.get_faces(result)
annotator.clear()
for face in faces:
annotator.bounding_box(transform(face.bounding_box),
fill=0)
annotator.update()
print('Iteration #%d: num_faces=%d' % (i, len(faces)))
#write to file
F = open('../wwww/check_faces.txt', 'w')
F.write(len(faces))
F.close
camera.stop_preview()
def run(self, num_frames, preview_alpha, image_format, image_folder):
logger.info('Starting...')
leds = Leds()
player = Player(gpio=22, bpm=10)
photographer = Photographer(image_format, image_folder)
animator = Animator(leds, self._done)
try:
# Forced sensor mode, 1640x1232, full FoV. See:
# https://picamera.readthedocs.io/en/release-1.13/fov.html#sensor-modes
# This is the resolution inference run on.
with PiCamera(sensor_mode=4,
resolution=(1640, 1232)) as camera, PrivacyLed(leds):
def take_photo():
logger.info('Button pressed.')
player.play(BEEP_SOUND)
photographer.shoot(camera)
# Blend the preview layer with the alpha value from the flags.
if preview_alpha > 0:
logger.info('Starting preview with alpha %d',
preview_alpha)
camera.start_preview(alpha=preview_alpha)
else:
logger.info('Not starting preview, alpha 0')
button = Button(23)
button.when_pressed = take_photo
joy_score_moving_average = MovingAverage(10)
prev_joy_score = 0.0
with CameraInference(face_detection.model()) as inference:
logger.info('Model loaded.')
player.play(MODEL_LOAD_SOUND)
for i, result in enumerate(inference.run()):
faces = face_detection.get_faces(result)
photographer.update_faces(faces)
joy_score = joy_score_moving_average.next(
average_joy_score(faces))
animator.update_joy_score(joy_score)
if joy_score > JOY_SCORE_PEAK > prev_joy_score:
player.play(JOY_SOUND)
elif joy_score < JOY_SCORE_MIN < prev_joy_score:
player.play(SAD_SOUND)
prev_joy_score = joy_score
if self._done.is_set() or i == num_frames:
break
finally:
player.stop()
photographer.stop()
player.join()
photographer.join()
animator.join()
def main():
"""Face detection camera inference example."""
parser = argparse.ArgumentParser()
parser.add_argument('--num_frames', '-n', type=int, dest='num_frames', default=None,
help='Sets the number of frames to run for, otherwise runs forever.')
args = parser.parse_args()
leds = Leds()
leds.reset()
leds.update(Leds.privacy_on())
noCustomerDelay = 0;
with PiCamera(sensor_mode=4, resolution=(1640, 1232)) as camera:
# with PiCamera(sensor_mode=4, resolution=(1640, 1232), framerate=30) as camera:
# with PiCamera() as camera:
camera.start_preview()
with CameraInference(face_detection.model()) as inference:
for result in inference.run():
if len(face_detection.get_faces(result)) >= 1:
noCustomerDelay = 0
leds.update(Leds.rgb_on(GREEN))
# stream = io.BytesIO()
# camera.capture(stream, format='jpeg')
# stream.seek(0)
camera.capture('faces.jpg')
faces = GetFaceId('faces.jpg')
print(faces)
if(len(faces) > 0):
result = GetUserId(faces[0])
print(result)
highestScore = 0
userId = ""
for face in result:
for candidate in face['candidates']:
if(highestScore < candidate['confidence']):
userId = candidate['personId']
InfoVendingMachine("10", userId)
print(userId)
# break
else:
if noCustomerDelay >= 30:
leds.update(Leds.rgb_on(WHITE))
InfoVendingMachine("10", '')
noCustomerDelay = 0;
else:
noCustomerDelay += 1;
camera.stop_preview()
leds.reset()
def main():
"""Face detection camera inference example."""
parser = argparse.ArgumentParser()
parser.add_argument(
'--num_frames',
'-n',
type=int,
dest='num_frames',
default=None,
help='Sets the number of frames to run for, otherwise runs forever.')
args = parser.parse_args()
# pool = [ImageProcessor() for i in range(4)]
# Forced sensor mode, 1640x1232, full FoV. See:
# https://picamera.readthedocs.io/en/release-1.13/fov.html#sensor-modes
# This is the resolution inference run on.
with PiCamera(sensor_mode=4, resolution=(1640, 1232),
framerate=30) as camera:
camera.start_preview()
# time.sleep(2)
# Annotator renders in software so use a smaller size and scale results
# for increased performace.
# annotator = Annotator(camera, dimensions=(320, 240))
scale_x = 320 / 1640
scale_y = 240 / 1232
# Incoming boxes are of the form (x, y, width, height). Scale and
# transform to the form (x1, y1, x2, y2).
def transform(bounding_box):
x, y, width, height = bounding_box
return (scale_x * x, scale_y * y, scale_x * (x + width),
scale_y * (y + height))
with CameraInference(face_detection.model()) as inference:
# camera.capture_sequence(streams(), use_video_port=True)
# print("after capture_sequence")
print(args.num_frames)
for result in inference.run(args.num_frames):
faces = face_detection.get_faces(result)
# annotator.clear()
# for face in faces:
# annotator.bounding_box(transform(face.bounding_box), fill=0)
# annotator.update()
if len(faces) > 0:
# start to identify the person
print("Has Customer")
hasCustomer = True
else:
print("No Customer")
hasCustomer = False
print('#%05d (%5.2f fps): num_faces=%d, avg_joy_score=%.2f' %
(inference.count, inference.rate, len(faces),
avg_joy_score(faces)))
camera.stop_preview()
def test_camera_inference(self):
with PiCamera(sensor_mode=4):
with CameraInference(fd.model()) as inference:
state = inference.engine.get_inference_state()
self.assertEqual(len(state.loaded_models), 1)
self.assertEqual(len(state.processing_models), 1)
results = [fd.get_faces(result) for result in inference.run(10)]
self.assertEqual(len(results), 10)
def run(self, num_frames, preview_alpha, image_format, image_folder, enable_streaming):
logger.info('Starting...')
leds = Leds()
with contextlib.ExitStack() as stack:
player = stack.enter_context(Player(gpio=BUZZER_GPIO, bpm=10))
photographer = stack.enter_context(Photographer(image_format, image_folder))
animator = stack.enter_context(Animator(leds))
# Forced sensor mode, 1640x1232, full FoV. See:
# https://picamera.readthedocs.io/en/release-1.13/fov.html#sensor-modes
# This is the resolution inference run on.
# Use half of that for video streaming (820x616).
camera = stack.enter_context(PiCamera(sensor_mode=4, resolution=(820, 616)))
stack.enter_context(PrivacyLed(leds))
server = None
if enable_streaming:
server = stack.enter_context(StreamingServer(camera))
server.run()
def take_photo():
logger.info('Button pressed.')
player.play(BEEP_SOUND)
photographer.shoot(camera)
if preview_alpha > 0:
camera.start_preview(alpha=preview_alpha)
button = Button(BUTTON_GPIO)
button.when_pressed = take_photo
joy_score_moving_average = MovingAverage(10)
prev_joy_score = 0.0
with CameraInference(face_detection.model()) as inference:
logger.info('Model loaded.')
player.play(MODEL_LOAD_SOUND)
for i, result in enumerate(inference.run()):
faces = face_detection.get_faces(result)
photographer.update_faces(faces)
joy_score = joy_score_moving_average.next(average_joy_score(faces))
animator.update_joy_score(joy_score)
if server:
data = server_inference_data(result.width, result.height, faces, joy_score)
server.send_inference_data(data)
if joy_score > JOY_SCORE_PEAK > prev_joy_score:
player.play(JOY_SOUND)
elif joy_score < JOY_SCORE_MIN < prev_joy_score:
player.play(SAD_SOUND)
prev_joy_score = joy_score
if self._done.is_set() or i == num_frames:
break
def test_camera_inference(self):
with PiCamera(sensor_mode=4):
with CameraInference(fd.model()) as inference:
state = inference.engine.get_inference_state()
self.assertEqual(len(state.loaded_models), 1)
self.assertEqual(len(state.processing_models), 1)
results = [
fd.get_faces(result) for result in inference.run(10)
]
self.assertEqual(len(results), 10)
def testFaceDetectionWithParams(self):
with TestImage('faces.jpg') as image:
with ImageInference(face_detection.model()) as inference:
params = {'max_face_size': 500}
faces = face_detection.get_faces(inference.run(image, params))
self.assertEqual(1, len(faces))
face0 = faces[0]
self.assertAlmostEqual(face0.face_score, 0.884, delta=0.001)
self.assertAlmostEqual(face0.joy_score, 0.073, delta=0.001)
self.assertEqual((748.0, 1063.0, 496.0, 496.0), face0.bounding_box)
def main():
"""Face detection camera inference example."""
parser = argparse.ArgumentParser()
parser.add_argument(
'--num_frames',
'-n',
type=int,
dest='num_frames',
default=None,
help='Sets the number of frames to run for, otherwise runs forever.')
args = parser.parse_args()
# Forced sensor mode, 1640x1232, full FoV. See:
# https://picamera.readthedocs.io/en/release-1.13/fov.html#sensor-modes
# This is the resolution inference run on.
with PiCamera(sensor_mode=4, resolution=(1640, 1232),
framerate=30) as camera:
camera.start_preview()
# Annotator renders in software so use a smaller size and scale results
# for increased performace.
annotator = Annotator(camera, dimensions=(320, 240))
scale_x = 320 / 1640
scale_y = 240 / 1232
# Incoming boxes are of the form (x, y, width, height). Scale and
# transform to the form (x1, y1, x2, y2).
def transform(bounding_box):
x, y, width, height = bounding_box
return (scale_x * x, scale_y * y, scale_x * (x + width),
scale_y * (y + height))
with CameraInference(face_detection.model()) as inference:
for result in inference.run(args.num_frames):
faces = face_detection.get_faces(result)
print(faces)
annotator.clear()
for index, face in enumerate(faces):
sio.emit('movement', {
'index': index,
'score': face.face_score
})
annotator.bounding_box(transform(face.bounding_box),
fill=0)
annotator.update()
print('#%05d (%5.2f fps): num_faces=%d, avg_joy_score=%.2f' %
(inference.count, inference.rate, len(faces),
avg_joy_score(faces)))
camera.stop_preview()
def main():
with PiCamera() as camera:
camera.resolution = (1640, 922)
camera.start_preview()
with CameraInference(face_detection.model()) as inference:
for result in inference.run():
if len(face_detection.get_faces(result)) >= 1:
camera.capture('faces.jpg')
break
camera.stop_preview()
def main():
parser = argparse.ArgumentParser('Face detection using raspivid.')
parser.add_argument('--num_frames', '-n', type=int, default=None,
help='Sets the number of frames to run for, otherwise runs forever.')
args = parser.parse_args()
with Process(raspivid_cmd(sensor_mode=4)), \
CameraInference(face_detection.model()) as inference:
for result in inference.run(args.num_frames):
faces = face_detection.get_faces(result)
print('#%05d (%5.2f fps): num_faces=%d, avg_joy_score=%.2f' %
(inference.count, inference.rate, len(faces), avg_joy_score(faces)))
def _run(self):
logger.info('Starting...')
leds = Leds()
with contextlib.ExitStack() as stack:
player = stack.enter_context(Player(gpio=BUZZER_GPIO, bpm=10))
photographer = stack.enter_context(
Photographer(self.args.image_format, self.args.image_folder))
animator = stack.enter_context(Animator(leds))
stack.enter_context(PrivacyLed(leds))
server = None
if self.args.enable_streaming:
server = stack.enter_context(StreamingServer(self.camera))
server.run()
def take_photo():
logger.info('Button pressed.')
player.play(BEEP_SOUND)
photographer.shoot(self.camera)
button = Button(BUTTON_GPIO)
button.when_pressed = take_photo
joy_score_moving_average = MovingAverage(10)
prev_joy_score = 0.0
with CameraInference(face_detection.model()) as inference:
logger.info('Model loaded.')
player.play(MODEL_LOAD_SOUND)
for i, result in enumerate(inference.run()):
faces = face_detection.get_faces(result)
photographer.update_faces(faces)
avg_joy_score = average_joy_score(faces)
joy_score = joy_score_moving_average.next(avg_joy_score)
animator.update_joy_score(joy_score)
if server:
data = server_inference_data(result.width,
result.height, faces,
joy_score)
server.send_inference_data(data)
if avg_joy_score > JOY_SCORE_MIN:
photographer.shoot(self.camera)
# if joy_score > JOY_SCORE_PEAK > prev_joy_score:
# player.play(JOY_SOUND)
# elif joy_score < JOY_SCORE_MIN < prev_joy_score:
# player.play(SAD_SOUND)
prev_joy_score = joy_score
if self._done.is_set() or i == self.args.num_frames:
break
def testFaceDetection(self):
with TestImage('faces.jpg') as image:
with ImageInference(face_detection.model()) as inference:
faces = face_detection.get_faces(inference.run(image))
self.assertEqual(2, len(faces))
face0 = faces[0]
self.assertAlmostEqual(face0.face_score, 1.0, delta=0.001)
self.assertAlmostEqual(face0.joy_score, 0.969, delta=0.001)
self.assertEqual((812.0, 44.0, 1000.0, 1000.0), face0.bounding_box)
face1 = faces[1]
self.assertAlmostEqual(face1.face_score, 0.884, delta=0.001)
self.assertAlmostEqual(face1.joy_score, 0.073, delta=0.001)
self.assertEqual((748.0, 1063.0, 496.0, 496.0), face1.bounding_box)
def main():
with PiCamera() as camera:
# Configure camera
camera.resolution = (1640, 922) # Full Frame, 16:9 (Camera v2)
camera.start_preview()
# Do inference on VisionBonnet
with CameraInference(face_detection.model()) as inference:
for result in inference.run():
if len(face_detection.get_faces(result)) >= 1:
camera.capture('faces.jpg')
break
# Stop preview
camera.stop_preview()
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--input', '-i', dest='input', required=True)
parser.add_argument('--output', '-o', dest='output')
args = parser.parse_args()
with ImageInference(face_detection.model()) as inference:
image = Image.open(args.input)
draw = ImageDraw.Draw(image)
for i, face in enumerate(face_detection.get_faces(inference.run(image))):
print('Face #%d: %s' % (i, str(face)))
x, y, width, height = face.bounding_box
draw.rectangle((x, y, x + width, y + height), outline='red')
if args.output:
image.save(args.output)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--input', '-i', dest='input', required=True)
parser.add_argument('--output', '-o', dest='output')
args = parser.parse_args()
with ImageInference(face_detection.model()) as inference:
image = Image.open(args.input)
draw = ImageDraw.Draw(image)
faces = face_detection.get_faces(inference.run(image))
for i, face in enumerate(faces):
print('Face #%d: %s' % (i, face))
x, y, width, height = face.bounding_box
draw.rectangle((x, y, x + width, y + height), outline='red')
if args.output:
image.save(args.output)
def loop(inference, robot, annotator, leds):
for inference_result in inference.run(None):
# Get all the faces.
faces = face_detection.get_faces(inference_result)
# Get the stronger face.
stronger_face = selectFaceWithHigherScore(faces)
if stronger_face is None:
print("No face detected")
continue
# Angular difference between the face and the center of the camera.
face_x_center = stronger_face.bounding_box[
0] + stronger_face.bounding_box[2] / 2
face_y_center = stronger_face.bounding_box[
1] + stronger_face.bounding_box[3] / 2
face_x_normalized = face_x_center / CAMERA_WIDTH
face_y_normalized = face_y_center / CAMERA_HEIGHT
face_x_angle = (face_x_normalized * 2 - 1) * (CAMERA_FOV_WIDTH / 2)
# The screen and motor axis are reversed.
face_y_angle = -(face_y_normalized * 2 - 1) * (CAMERA_FOV_HEIGHT / 2)
print("Face delta: %s %s" % (face_x_angle, face_y_angle))
robot.deltaYaw(controller(face_x_angle))
robot.deltaPitch(controller(face_y_angle))
leds.update(
Leds.rgb_on((255 * (1 - stronger_face.joy_score),
255 * stronger_face.joy_score, 0)))
if SLEEP > 0:
sleep(SLEEP)
if PRINT_LOGS:
for face_idx, face in enumerate(faces):
print("Face %i -> %s" % (face_idx, face))
if ENABLE_DISPLAY:
annotator.clear()
for face in faces:
annotator.bounding_box(transform_annotator(face.bounding_box),
fill=0)
annotator.update()
def main():
parser = argparse.ArgumentParser('Face detection using raspivid.')
parser.add_argument(
'--num_frames',
'-n',
type=int,
default=None,
help='Sets the number of frames to run for, otherwise runs forever.')
args = parser.parse_args()
with Process(raspivid_cmd(sensor_mode=4)), \
CameraInference(face_detection.model()) as inference:
for result in inference.run(args.num_frames):
faces = face_detection.get_faces(result)
print('#%05d (%5.2f fps): num_faces=%d, avg_joy_score=%.2f' %
(inference.count, inference.rate, len(faces),
avg_joy_score(faces)))
def facedetector():
"""Face detection camera inference example."""
global currentState
# Forced sensor mode, 1640x1232, full FoV. See:
# https://picamera.readthedocs.io/en/release-1.13/fov.html#sensor-modes
# This is the resolution inference run on.
with PiCamera(sensor_mode=4, resolution=(1640, 1232),
framerate=30) as camera:
# Annotator renders in software so use a smaller size and scale results
# for increased performace.
scale_x = 320 / 1640
scale_y = 240 / 1232
# Incoming boxes are of the form (x, y, width, height). Scale and
# transform to the form (x1, y1, x2, y2).
def transform(bounding_box):
x, y, width, height = bounding_box
return (scale_x * x, scale_y * y, scale_x * (width),
scale_y * (height))
def checkSquat(bounding_box):
x, y, width, height = bounding_box
# calc average y position
avgHeight = y + height / 2
#print("AvgHeight: ", avgHeight)
if avgHeight > THRESHOLD_Y:
return 2
else:
return 1
with CameraInference(face_detection.model()) as inference:
for result in inference.run(None):
faces = face_detection.get_faces(result)
checkedFaces = []
for face in faces:
checkedFaces.append(
checkSquat(transform(face.bounding_box)))
if len(checkedFaces) == 0:
currentState = 1
elif (2 in checkedFaces):
currentState = 2
else:
currentState = 0
def main():
with PiCamera(resolution=(1640, 922)) as camera:
with CameraInference(face_detection.model()) as inference:
for result in inference.run():
if len(face_detection.get_faces(result)) >= 1:
print("face detected!")
h264_file_path = generate_filename(datetime.datetime.now())
leds = Leds()
with PrivacyLed(leds):
camera.start_recording(h264_file_path, format='h264')
sleep(5)
camera.stop_recording()
leds.reset()
output_file_path = h264_to_mp4(h264_file_path)
upload_video_to_slack(output_file_path, SLACK_TOKEN,
SLACK_CHANNEL_ID)
def main():
global lastSaveTime
with PiCamera() as camera:
# Configure camera
camera.resolution = (1640, 922) # Full Frame, 16:9 (Camera v2)
camera.start_preview()
# Do inference on VisionBonnet
with CameraInference(face_detection.model()) as inference:
for result in inference.run():
if len(face_detection.get_faces(
result)) >= 1 and time.time() - lastSaveTime > 60:
print('yay, we got an image')
camera.capture('image.jpg')
discordcode.send_image('image.jpg')
lastSaveTime = time.time()
# Stop preview
camera.stop_preview()
def main():
"""Face detection camera inference example."""
parser = argparse.ArgumentParser()
parser.add_argument('--num_frames', '-n', type=int, dest='num_frames', default=None,
help='Sets the number of frames to run for, otherwise runs forever.')
args = parser.parse_args()
# Forced sensor mode, 1640x1232, full FoV. See:
# https://picamera.readthedocs.io/en/release-1.13/fov.html#sensor-modes
# This is the resolution inference run on.
with PiCamera(sensor_mode=4, resolution=(1640, 1232), framerate=30) as camera:
camera.start_preview()
# Annotator renders in software so use a smaller size and scale results
# for increased performace.
annotator = Annotator(camera, dimensions=(320, 240))
scale_x = 320 / 1640
scale_y = 240 / 1232
# Incoming boxes are of the form (x, y, width, height). Scale and
# transform to the form (x1, y1, x2, y2).
def transform(bounding_box):
x, y, width, height = bounding_box
return (scale_x * x, scale_y * y, scale_x * (x + width),
scale_y * (y + height))
with CameraInference(face_detection.model()) as inference:
for result in inference.run(args.num_frames):
faces = face_detection.get_faces(result)
annotator.clear()
for face in faces:
annotator.bounding_box(transform(face.bounding_box), fill=0)
annotator.update()
print('#%05d (%5.2f fps): num_faces=%d, avg_joy_score=%.2f' %
(inference.count, inference.rate, len(faces), avg_joy_score(faces)))
camera.stop_preview()
def run(self, num_frames, preview_alpha, image_format, image_folder):
logger.info('Starting...')
leds = Leds()
player = Player(gpio=22, bpm=10)
photographer = Photographer(image_format, image_folder)
animator = Animator(leds, self._done)
try:
# Forced sensor mode, 1640x1232, full FoV. See:
# https://picamera.readthedocs.io/en/release-1.13/fov.html#sensor-modes
# This is the resolution inference run on.
with PiCamera(sensor_mode=4,
resolution=(1640, 1232)) as camera, PrivacyLed(leds):
def take_photo():
logger.info('Button pressed.')
player.play(BEEP_SOUND)
photographer.shoot(camera)
# Blend the preview layer with the alpha value from the flags.
if preview_alpha > 0:
logger.info('Starting preview with alpha %d',
preview_alpha)
camera.start_preview(alpha=preview_alpha)
else:
logger.info('Not starting preview, alpha 0')
button = Button(23)
button.when_pressed = take_photo
joy_score_moving_average = MovingAverage(10)
prev_joy_score = 0.0
#fb.delete('/', 'joy')
time_interval = 1
camera_id = 1
t_ref = time.localtime()
with CameraInference(face_detection.model()) as inference:
logger.info('Model loaded.')
player.play(MODEL_LOAD_SOUND)
for i, result in enumerate(inference.run()):
t_begin = datetime.now()
faces = face_detection.get_faces(result)
num_faces = len(faces)
print("face num" + str(num_faces))
# for face in faces:
# print(face.joy_score)
photographer.update_faces(faces)
joy_score = joy_score_moving_average.next(
average_joy_score(faces))
animator.update_joy_score(joy_score)
print(joy_score)
t0 = time.localtime()
time_stamp = str(t0.tm_hour) + ":" + str(
t0.tm_min) + ":" + str(t0.tm_sec) + " | " + str(
t0.tm_mon) + "/" + str(t0.tm_mday) + "/" + str(
t0.tm_year)
time_up = time_stamp = str(t0.tm_hour) + ":" + str(
t0.tm_min) + ":" + str(t0.tm_sec)
elapsed_time = int(t0.tm_sec) - int(t_ref.tm_sec)
# print("Elapsed time: " + str(elapsed_time_milli))
if elapsed_time < 0:
elapsed_time += 60
if elapsed_time >= time_interval:
if joy_score != 0:
fb.put(
'/joy_data/' + str(t0.tm_year) + "/" +
str(t0.tm_mon) + "/" + str(t0.tm_mday) +
"/" + str(t0.tm_hour) + "/" +
str(t0.tm_min) + "/", time.ctime(), {
'time': time_stamp,
'cam_id': camera_id,
'num_faces': num_faces,
'joy_score': joy_score
})
t_ref = t0
print(time_stamp)
#if joy_score > JOY_SCORE_PEAK > prev_joy_score:
# player.play(JOY_SOUND)
#elif joy_score < JOY_SCORE_MIN < prev_joy_score:
# player.play(SAD_SOUND)
prev_joy_score = joy_score
t_end = datetime.now()
ellapsed_milli = t_end - t_begin
print("Elapsed time: ")
print(int(ellapsed_milli.total_seconds() * 1000))
if self._done.is_set() or i == num_frames:
break
finally:
player.stop()
photographer.stop()
player.join()
photographer.join()
animator.join()
def main():
"""Face detection camera inference example."""
parser = argparse.ArgumentParser()
parser.add_argument(
'--label',
'-lbl',
type=str,
dest='label',
required=True,
help='Specifies the class (label) of training images (e.g. no_hangs).')
parser.add_argument('--num_images',
'-nimg',
type=int,
dest='num_images',
default=10,
help='Sets the number of training images to make.')
args = parser.parse_args()
with PiCamera() as camera:
# Forced sensor mode, 1640x1232, full FoV. See:
# https://picamera.readthedocs.io/en/release-1.13/fov.html#sensor-modes
# This is the resolution inference run on.
camera.sensor_mode = 4
# Scaled and cropped resolution. If different from sensor mode implied
# resolution, inference results must be adjusted accordingly. This is
# true in particular when camera.start_recording is used to record an
# encoded h264 video stream as the Pi encoder can't encode all native
# sensor resolutions, or a standard one like 1080p may be desired.
camera.resolution = (1640, 1232)
# Start the camera stream.
camera.framerate = 30
camera.start_preview()
# Stage #1: Capture and store raw images
# Create foler to store raw images
path_to_raw_img_folder = path_to_training_folder + 'raw/'
if not os.path.exists(path_to_raw_img_folder):
os.makedirs(path_to_raw_img_folder)
time.sleep(2)
# Create list to store hand boxes location for each image
hand_boxes_locations = []
with CameraInference(face_detection.model()) as inference:
leds.update(Leds.rgb_on(RED))
time.sleep(3)
counter = 1
start = time.time()
for result in inference.run():
faces = face_detection.get_faces(result)
face = select_face(faces)
if face:
if counter > args.num_images:
break
face_box = transform(face.bounding_box)
hands = hand_box(face_box)
# Capture raw image
img_name = path_to_raw_img_folder + 'img' + str(
counter) + '.jpg'
camera.capture(img_name)
time.sleep(0.2)
# Record position of hands
hand_boxes_locations.append([counter, hands])
print('Captured ', str(counter), " out of ",
str(args.num_images))
counter += 1
print('Stage #1: It took', str(round(time.time() - start, 1)),
'sec to record', str(args.num_images), 'raw images')
camera.stop_preview()
# Stage #2: Crop training images from the raw ones and store them in class (label) subfolder
leds.update(Leds.rgb_on(BLUE))
start = time.time()
for i, entry in enumerate(hand_boxes_locations):
img_number = entry[0]
hands = entry[1]
raw_img_name = path_to_raw_img_folder + 'img' + str(
img_number) + '.jpg'
if os.path.isfile(raw_img_name):
raw_image = Image.open(raw_img_name)
crop_and_store_images(args.label, hands, raw_image)
raw_image.close()
time.sleep(0.5)
os.remove(raw_img_name)
print('Processed ', str(i + 1), " out of ", str(args.num_images))
print('Stage #2: It took ', str(round(time.time() - start, 1)),
'sec to process', str(args.num_images), 'images')
time.sleep(3)
# Delete empty folder for raw images
if os.listdir(path_to_raw_img_folder) == []:
os.rmdir(path_to_raw_img_folder)
leds.update(Leds.rgb_off())
def test_image_inference_jpeg(self):
with ImageInference(
fd.model()) as inference, TestImageFile('faces.jpg') as f:
fd.get_faces(inference.run(f.read()))
def test_image_inference_raw(self):
with ImageInference(
fd.model()) as inference, TestImage('faces.jpg') as image:
fd.get_faces(inference.run(image))
def main():
#### Setup stepper motor ####
# create a default object, no changes to I2C address or frequency
mh = Adafruit_MotorHAT(addr=0x60)
# recommended for auto-disabling motors on shutdown!
def turnOffMotors():
mh.getMotor(1).run(Adafruit_MotorHAT.RELEASE)
mh.getMotor(2).run(Adafruit_MotorHAT.RELEASE)
mh.getMotor(3).run(Adafruit_MotorHAT.RELEASE)
mh.getMotor(4).run(Adafruit_MotorHAT.RELEASE)
atexit.register(turnOffMotors)
mh = Adafruit_MotorHAT(addr=0x60)
myStepper = mh.getStepper(200, 1) # 200 steps/rev, motor port #1
myStepper.setSpeed(30) # 30 RPM
#### setup camera ####
"""Face detection camera inference example."""
parser = argparse.ArgumentParser()
parser.add_argument(
'--num_frames',
'-n',
type=int,
dest='num_frames',
default=-1,
help='Sets the number of frames to run for, otherwise runs forever.')
args = parser.parse_args()
with PiCamera() as camera:
# Forced sensor mode, 1640x1232, full FoV. See:
# https://picamera.readthedocs.io/en/release-1.13/fov.html#sensor-modes
# This is the resolution inference run on.
camera.sensor_mode = 4
# Scaled and cropped resolution. If different from sensor mode implied
# resolution, inference results must be adjusted accordingly. This is
# true in particular when camera.start_recording is used to record an
# encoded h264 video stream as the Pi encoder can't encode all native
# sensor resolutions, or a standard one like 1080p may be desired.
camera.resolution = (1640, 1232)
# Start the camera stream.
camera.framerate = 30
# Tempolary disable camera preview so that I can see the log on Terminal
camera.start_preview()
# Annotator renders in software so use a smaller size and scale results
# for increased performace.
annotator = Annotator(camera, dimensions=(320, 240))
scale_x = 320 / 1640
scale_y = 240 / 1232
# Incoming boxes are of the form (x, y, width, height). Scale and
# transform to the form (x1, y1, x2, y2).
def transform(bounding_box):
x, y, width, height = bounding_box
return (scale_x * x, scale_y * y, scale_x * (x + width),
scale_y * (y + height))
with CameraInference(face_detection.model()) as inference:
for i, result in enumerate(inference.run()):
if i == args.num_frames:
break
faces = face_detection.get_faces(result)
annotator.clear()
for face in faces:
annotator.bounding_box(transform(face.bounding_box),
fill=0)
# Print the (x, y) location of face
print('X = %d, Y = %d' %
(face.bounding_box[0], face.bounding_box[1]))
# Move stepper motor
if face.bounding_box[0] > 1640 / 2 and abs(
face.bounding_box[0] - 1640 / 2) > 200:
print("Double coil step - right")
myStepper.step(10, Adafruit_MotorHAT.FORWARD,
Adafruit_MotorHAT.DOUBLE)
elif face.bounding_box[0] < 1640 / 2 and abs(
face.bounding_box[0] - 1640 / 2) > 300:
print("Double coil step - left")
myStepper.step(10, Adafruit_MotorHAT.BACKWARD,
Adafruit_MotorHAT.DOUBLE)
annotator.update()
# print('Iteration #%d: num_faces=%d' % (i, len(faces)))
camera.stop_preview()
def test_image_inference_raw(self):
with ImageInference(fd.model()) as inference, TestImage('faces.jpg') as image:
fd.get_faces(inference.run(image))
def test_image_inference_jpeg(self):
with ImageInference(fd.model()) as inference, TestImageFile('faces.jpg') as f:
fd.get_faces(inference.run(f.read()))
def run_inference(num_frames, on_loaded):
"""Yields (faces, (frame_width, frame_height)) tuples."""
with CameraInference(face_detection.model()) as inference:
on_loaded()
for result in inference.run(num_frames):
yield face_detection.get_faces(result), (result.width, result.height)
