def _process_image(self, img_file_path: str) -> tuple:
"""
Extract all faces in given image file and
compute corresponding description vectors.
:param img_file_path: str - Path to image file.
:return: (list, list) - List of data
points and another list of
corresponding metadata structures.
Return empty lists in case no
description vectors could be retrieved.
"""
# Read specified image file.
img_bgr = image.read_image_from_file(img_file_path)
if img_bgr.size < 1:
# Error: image file could not be
# read, therefore return empty lists
# to indicate that no description
# vectors could be retrieved.
return list(), list()
# Convert retrieved image to RGB color encoding.
img_rgb = image.swap_color_encoding(img_bgr)
# Get description vector and
# bounding box coordinates of all
# detected faces in current image.
face_descriptions = self._get_face_descriptions(img_rgb)
# Create empty list to store description vectors.
vector_list = list()
# Create empty list to store metadata structures.
metadata_list = list()
# Fill both lists with corresponding data of detected faces.
for face_data_tuple in face_descriptions:
# Extract and store description vector of current face.
vector = face_data_tuple[0]
vector_list.append(vector)
# Extract and store metadata of current face.
top_left = face_data_tuple[1]
bottom_right = face_data_tuple[2]
# Create metadata structure for current
# face in image file. In this case, this
# is a tuple containing file name and top
# left / bottom right bounding box corners.
img_metadata = DataSet.create_metadata(
os.path.basename(img_file_path), top_left, bottom_right)
metadata_list.append(img_metadata)
return vector_list, metadata_list
def _process_video(self, video_file_path: str,
num_skipped_frames: int) -> tuple:
"""
Extract all faces in given video file and
compute corresponding description vectors.
:param video_file_path: str - Path to video file.
:param num_skipped_frames: int - Number of skipped
frames between two consecutive samples.
:return: (list, list) - List of data
points and another list of
corresponding metadata structures.
Return empty lists in case no
description vectors could be retrieved.
"""
# Open video file.
cap = cv2.VideoCapture(video_file_path)
# Adjust given number of frames between
# two samples to indicate the number of
# necessary forward steps in video file.
num_skipped_frames += 1
# Create empty list to store description vectors.
vector_list = list()
# Create empty list to store metadata structures.
metadata_list = list()
# Create list to store description vectors
# of last sample. Should be used as cache
# to avoid multiple insertions of description
# vectors corresponding to the same person.
vectors_in_last_sample = list()
# Read frames with specified sample rate.
next_frame_index = 0
ret = True
while ret:
# Jump to next frame index.
cap.set(cv2.CAP_PROP_POS_FRAMES, next_frame_index)
# Read frame.
ret, frame_bgr = cap.read()
# Check if retrieved pixel data is valid.
if frame_bgr is None:
# Error: current frame is invalid,
# therefore skip it and continue
# with next sample (if possible).
continue
# Convert retrieved frame to RGB color encoding.
frame_rgb = image.swap_color_encoding(frame_bgr)
# Get current frame number and convert
# it to corresponding frame index.
frame_number = int(cap.get(cv2.CAP_PROP_POS_FRAMES))
frame_index = frame_number - 1
# Get description vector of all
# detected faces in current frame.
face_descriptions = self._get_face_descriptions(frame_rgb)
# Fill description vector and metadata lists
# with corresponding data of detected faces.
for face_tuple in face_descriptions:
# Extract description vector of current face.
vector = face_tuple[0]
# Compare current vector to those detected in last
# frame. When its distance exceeds a certain threshold,
# assume a new face which needs to be stored.
present_in_last_sample = False
for last_vector in vectors_in_last_sample:
distance = calculation.get_distance(last_vector, vector)
if numpy.less_equal(
distance, settings.DISTANCE_THRESHOLD_RECOGNITION):
present_in_last_sample = True
break
if not present_in_last_sample:
# Store description vector of current face.
vector_list.append(vector)
# Extract and store corresponding metadata.
top_left = face_tuple[1]
bottom_right = face_tuple[2]
# Create metadata structure for current face in
# specified video file frame. In this case, this
# is a tuple containing file name, frame index
# and top left / bottom right bounding box corners.
video_metadata = DataSet.create_metadata(
os.path.basename(video_file_path), frame_index,
top_left, bottom_right)
metadata_list.append(video_metadata)
# Update description vectors of last
# frame to those currently retrieved.
vectors_in_last_sample.clear()
for vector, _top_left, _bottom_right in face_descriptions:
vectors_in_last_sample.append(vector)
# Update frame index.
next_frame_index += num_skipped_frames
# Close video file.
cap.release()
return vector_list, metadata_list