def real_time_lrp(conf):
"""Method to display feature relevance scores in real time.
Args:
conf: Dictionary consisting of configuration parameters.
"""
record_video = conf["playback"]["record_video"]
webcam = Webcam()
lrp = RelevancePropagation(conf)
if record_video:
recorder = VideoRecorder(conf)
while True:
t0 = time.time()
frame = webcam.get_frame()
heatmap = lrp.run(frame)
heatmap = post_processing(frame, heatmap, conf)
cv2.imshow("LRP", heatmap)
if record_video:
recorder.record(heatmap)
t1 = time.time()
fps = 1.0 / (t1 - t0)
print("{:.1f} FPS".format(fps))
if cv2.waitKey(1) % 256 == 27:
print("Escape pressed.")
break
if record_video:
recorder.release()
webcam.turn_off()
cv2.destroyAllWindows()
class VidMag():
def __init__(self):
self.webcam = Webcam()
self.buffer_size = 40
self.fps = 0
self.times = []
self.t0 = time.time()
self.data_buffer = []
#self.vidmag_frames = []
self.frame_out = np.zeros((10, 10, 3), np.uint8)
self.webcam.start()
print("init")
#--------------COLOR MAGNIFICATIONN---------------------#
def build_gaussian_pyramid(self, src, level=3):
s = src.copy()
pyramid = [s]
for i in range(level):
s = cv2.pyrDown(s)
pyramid.append(s)
return pyramid
def gaussian_video(self, video_tensor, levels=3):
for i in range(0, video_tensor.shape[0]):
frame = video_tensor[i]
pyr = self.build_gaussian_pyramid(frame, level=levels)
gaussian_frame = pyr[-1]
if i == 0:
vid_data = np.zeros(
(video_tensor.shape[0], gaussian_frame.shape[0],
gaussian_frame.shape[1], 3))
vid_data[i] = gaussian_frame
return vid_data
def temporal_ideal_filter(self, tensor, low, high, fps, axis=0):
fft = fftpack.fft(tensor, axis=axis)
frequencies = fftpack.fftfreq(tensor.shape[0], d=1.0 / fps)
bound_low = (np.abs(frequencies - low)).argmin()
bound_high = (np.abs(frequencies - high)).argmin()
fft[:bound_low] = 0
fft[bound_high:-bound_high] = 0
fft[-bound_low:] = 0
iff = fftpack.ifft(fft, axis=axis)
return np.abs(iff)
def amplify_video(self, gaussian_vid, amplification=70):
return gaussian_vid * amplification
def reconstract_video(self, amp_video, origin_video, levels=3):
final_video = np.zeros(origin_video.shape)
for i in range(0, amp_video.shape[0]):
img = amp_video[i]
for x in range(levels):
img = cv2.pyrUp(img)
img = img + origin_video[i]
final_video[i] = img
return final_video
def magnify_color(self,
data_buffer,
fps,
low=0.4,
high=2,
levels=3,
amplification=30):
gau_video = self.gaussian_video(data_buffer, levels=levels)
filtered_tensor = self.temporal_ideal_filter(gau_video, low, high, fps)
amplified_video = self.amplify_video(filtered_tensor,
amplification=amplification)
final_video = self.reconstract_video(amplified_video,
data_buffer,
levels=levels)
#print("c")
return final_video
#-------------------------------------------------------------#
#-------------------MOTION MAGNIFICATIONN---------------------#
#build laplacian pyramid for video
def laplacian_video(self, video_tensor, levels=3):
tensor_list = []
for i in range(0, video_tensor.shape[0]):
frame = video_tensor[i]
pyr = self.build_laplacian_pyramid(frame, levels=levels)
if i == 0:
for k in range(levels):
tensor_list.append(
np.zeros((video_tensor.shape[0], pyr[k].shape[0],
pyr[k].shape[1], 3)))
for n in range(levels):
tensor_list[n][i] = pyr[n]
return tensor_list
#Build Laplacian Pyramid
def build_laplacian_pyramid(self, src, levels=3):
gaussianPyramid = self.build_gaussian_pyramid(src, levels)
pyramid = []
for i in range(levels, 0, -1):
GE = cv2.pyrUp(gaussianPyramid[i])
L = cv2.subtract(gaussianPyramid[i - 1], GE)
pyramid.append(L)
return pyramid
#reconstract video from laplacian pyramid
def reconstract_from_tensorlist(self, filter_tensor_list, levels=3):
final = np.zeros(filter_tensor_list[-1].shape)
for i in range(filter_tensor_list[0].shape[0]):
up = filter_tensor_list[0][i]
for n in range(levels - 1):
up = cv2.pyrUp(up) + filter_tensor_list[n + 1][i]
final[i] = up
return final
#butterworth bandpass filter
def butter_bandpass_filter(self, data, lowcut, highcut, fs, order=5):
omega = 0.5 * fs
low = lowcut / omega
high = highcut / omega
b, a = signal.butter(order, [low, high], btype='band')
y = signal.lfilter(b, a, data, axis=0)
return y
def magnify_motion(self,
video_tensor,
fps,
low=0.4,
high=1.5,
levels=3,
amplification=30):
lap_video_list = self.laplacian_video(video_tensor, levels=levels)
filter_tensor_list = []
for i in range(levels):
filter_tensor = self.butter_bandpass_filter(
lap_video_list[i], low, high, fps)
filter_tensor *= amplification
filter_tensor_list.append(filter_tensor)
recon = self.reconstract_from_tensorlist(filter_tensor_list)
final = video_tensor + recon
return final
#-------------------------------------------------------------#
def buffer_to_tensor(self, buffer):
tensor = np.zeros((len(buffer), 192, 256, 3), dtype="float")
i = 0
for i in range(len(buffer)):
tensor[i] = buffer[i]
return tensor
def run_color(self):
self.times.append(time.time() - self.t0)
L = len(self.data_buffer)
#print(self.data_buffer)
if L > self.buffer_size:
self.data_buffer = self.data_buffer[-self.buffer_size:]
self.times = self.times[-self.buffer_size:]
#self.vidmag_frames = self.vidmag_frames[-self.buffer_size:]
L = self.buffer_size
if len(self.data_buffer) > self.buffer_size - 1:
self.fps = float(L) / (self.times[-1] - self.times[0])
tensor = self.buffer_to_tensor(self.data_buffer)
final_vid = self.magnify_color(data_buffer=tensor, fps=self.fps)
#print(final_vid[0].shape)
#self.vidmag_frames.append(final_vid[-1])
#print(self.fps)
self.frame_out = final_vid[-1]
def run_motion(self):
self.times.append(time.time() - self.t0)
L = len(self.data_buffer)
#print(L)
if L > self.buffer_size:
self.data_buffer = self.data_buffer[-self.buffer_size:]
self.times = self.times[-self.buffer_size:]
#self.vidmag_frames = self.vidmag_frames[-self.buffer_size:]
L = self.buffer_size
if len(self.data_buffer) > self.buffer_size - 1:
self.fps = float(L) / (self.times[-1] - self.times[0])
tensor = self.buffer_to_tensor(self.data_buffer)
final_vid = self.magnify_motion(video_tensor=tensor, fps=self.fps)
#print(self.fps)
#self.vidmag_frames.append(final_vid[-1])
self.frame_out = final_vid[-1]
def key_handler(self):
"""
A plotting or camera frame window must have focus for keypresses to be
detected.
"""
self.pressed = waitKey(1) & 255 # wait for keypress for 10 ms
if self.pressed == 27: # exit program on 'esc'
print("[INFO] Exiting")
self.webcam.stop()
sys.exit()
def mainLoop(self):
frame = self.webcam.get_frame()
f1 = imutils.resize(frame, width=256)
#crop_frame = frame[100:228,200:328]
self.data_buffer.append(f1)
self.run_color()
#print(frame)
#if len(self.vidmag_frames) > 0:
#print(self.vidmag_frames[0])
cv2.putText(frame, "FPS " + str(float("{:.2f}".format(self.fps))),
(20, 420), cv2.FONT_HERSHEY_PLAIN, 1.5, (0, 255, 0), 2)
#frame[100:228,200:328] = cv2.convertScaleAbs(self.vidmag_frames[-1])
cv2.imshow("Original", frame)
#f2 = imutils.resize(cv2.convertScaleAbs(self.vidmag_frames[-1]), width = 640)
f2 = imutils.resize(cv2.convertScaleAbs(self.frame_out), width=640)
cv2.imshow("Color amplification", f2)
self.key_handler() #if not the GUI cant show anything
class Studio(QMainWindow, Ui_MainWindow):
def __init__(self, *args, **kwargs):
super(Studio, self).__init__(*args, **kwargs)
self.setupUi(self)
# Device
self.device_default = 0
self.device = self.device_default
# Webcam
self.webcam = Webcam()
# Image
self.image_dir = 'outputs'
self.image_ext = 'jpg'
self.num_images_max_default = 10
self.num_images_max = self.num_images_max_default
self.num_images = 0
self.saved_width_default = 416 # In pixel
self.saved_height_default = 416
self.saved_width = self.saved_width_default
self.saved_height = self.saved_height_default
self.flip_image = False
self.cb_flip_image.stateChanged.connect(self.change_flip_image)
# Filename prefix
self.filename_prefix = 'class_memo'
# Recording flag
self.is_recording = False
# Timer
self.timer_is_on = False
self.timer_duration = 500 # msec
self.timer = QTimer(self)
self.timer.timeout.connect(self.process_image)
# Plot min/max
self.plot_min = 0.0
self.plot_max = -1.0
# Initialize
self.initialize()
def open_webcam(self):
# Release the resource which had been used.
if self.webcam.is_open():
self.webcam.release()
self.webcam.open(self.device)
self.process_image()
# Show message
self.show_message('webcam is opened.')
# Start the timer
if not self.timer_is_on:
self.start_timer()
def start_timer(self):
self.timer_is_on = True
self.timer.start(self.timer_duration)
def stop_timer(self):
self.timer_is_on = False
self.timer.stop()
def change_flip_image(self):
if self.cb_flip_image.isChecked():
self.flip_image = True
else:
self.flip_image = False
def start_recording(self):
self.is_recording = True
self.num_images = 0
self.show_message('recording frames.')
def finish_recording(self):
self.is_recording = False
self.show_message('recording is finished.')
def show_message(self, msg):
text = 'Status: ' + msg
self.lb_status.setText(text)
def show_num_images(self):
text = '{}/{}'.format(self.num_images, self.num_images_max)
self.lb_num_images.setText(text)
def get_image_path(self, n):
str_num = to_str_digits(n, num_digits=5)
filename = self.filename_prefix + '_' + str_num + '.' + self.image_ext
path = os.path.join(self.image_dir, filename)
return path
def save_image(self):
# Save the image.
self.num_images += 1
if self.num_images <= self.num_images_max:
image_path = self.get_image_path(self.num_images)
frame = self.webcam.get_frame()
image = Image.fromarray(frame)
size = (self.saved_width, self.saved_height)
image = make_square(image)
image = image.resize(size)
image.save(image_path)
else:
self.num_images = self.num_images_max
self.finish_recording()
# Show the number of images
self.show_num_images()
def process_image(self):
if self.webcam.is_open():
# Show frame
frame = self.webcam.read()
image = QImage(frame.data, frame.shape[1], frame.shape[0],
QImage.Format_RGB888)
# Flip the image horizontally
image_flipped = image.mirrored(True, False)
if self.flip_image:
pixmap = QPixmap.fromImage(image_flipped)
else:
pixmap = QPixmap.fromImage(image)
self.lb_image.setPixmap(pixmap)
# Record frame
if self.is_recording:
self.save_image()
def initialize(self):
# Connect the signal and slot
self.cb_device.activated[str].connect(self.set_device)
self.edit_num_images_max.textChanged.connect(self.set_num_images_max)
self.edit_saved_width.textChanged.connect(self.set_saved_width)
self.edit_saved_height.textChanged.connect(self.set_saved_height)
self.edit_filename_prefix.textChanged.connect(self.set_filename_prefix)
self.btn_open.clicked.connect(self.open_webcam)
self.btn_record.clicked.connect(self.start_recording)
# UI
text = str(self.num_images_max)
self.edit_num_images_max.setText(text)
text = str(self.saved_width)
self.edit_saved_width.setText(text)
text = str(self.saved_height)
self.edit_saved_height.setText(text)
text = str(self.filename_prefix)
self.edit_filename_prefix.setText(text)
def set_device(self):
value = self.cb_device.currentIndex()
try:
value = int(value)
except:
value = self.device_default
self.device = value
def set_num_images_max(self):
value = self.edit_num_images_max.text()
try:
value = int(value)
except:
value = self.num_images_max_default
self.num_images_max = value
def set_saved_width(self):
value = self.edit_saved_width.text()
try:
value = int(value)
except:
value = self.saved_width_default
self.saved_width = value
def set_saved_height(self):
value = self.edit_saved_height.text()
try:
value = int(value)
except:
value = self.edit_saved_height_default
self.saved_height = value
def set_filename_prefix(self):
value = self.edit_filename_prefix.text()
self.filename_prefix = value
def add_widget(self, widget):
widget.setParent(self.central_widget)
self.view_layout.addWidget(widget)
def remove_widget(self, widget):
self.view_layout.removeWidget(widget)
widget.setParent(None)
def refresh_view(self):
text = 'Remianing time: {} (sec)'.format(self.num_images)
self.lb_num_images.setText(text)
def closeEvent(self, event):
self.webcam.release()