def frames2video(frame_dir,
video_file,
file_names,
fps=20,
fourcc='XVID',
show_progress=True):
"""Read the frame images from a directory and join them as a video.
Args:
frame_dir (str): The directory containing video frames.
video_file (str): Output filename.
file_names (list[str]): Image files
fps (float): FPS of the output video.
fourcc (str): Fourcc of the output video, this should be compatible
with the output file type.
show_progress (bool): Whether to show a progress bar.
"""
first_file = os.path.join(frame_dir, file_names[0])
check_file_exist(first_file, 'The start frame not found: ' + first_file)
img = cv2.imread(first_file)
height, width = img.shape[:2]
resolution = (width, height)
vwriter = cv2.VideoWriter(video_file, VideoWriter_fourcc(*fourcc), fps, resolution)
def write_frame(file_idx):
filename = os.path.join(frame_dir, file_names[file_idx])
img = cv2.imread(filename)
vwriter.write(img)
if show_progress:
track_progress(write_frame, range(len(file_names)))
else:
for i in range(len(file_names)):
write_frame(i)
vwriter.release()
def imread(img_or_path, flag='color', channel_order='bgr'):
"""Read an image.
Args:
img_or_path (ndarray or str): Either a numpy array or image path.
If it is a numpy array (loaded image), then it will be returned
as is.
flag (str): Flags specifying the color type of a loaded image,
candidates are `color`, `grayscale` and `unchanged`.
Note that the `turbojpeg` backened does not support `unchanged`.
channel_order (str): Order of channel, candidates are `bgr` and `rgb`.
Returns:
ndarray: Loaded image array.
"""
if isinstance(img_or_path, np.ndarray):
return img_or_path
elif is_str(img_or_path):
check_file_exist(img_or_path,
'img file does not exist: {}'.format(img_or_path))
if imread_backend == 'turbojpeg':
with open(img_or_path, 'rb') as in_file:
img = jpeg.decode(in_file.read(),
_jpegflag(flag, channel_order))
if img.shape[-1] == 1:
img = img[:, :, 0]
return img
else:
flag = imread_flags[flag] if is_str(flag) else flag
img = cv2.imread(img_or_path, flag)
if flag == IMREAD_COLOR and channel_order == 'rgb':
cv2.cvtColor(img, cv2.COLOR_BGR2RGB, img)
return img
else:
raise TypeError('"img" must be a numpy array or a filename')
def imread(img_or_path, flag='color', channel_order='bgr', backend=None):
"""Read an image.
Args:
img_or_path (ndarray or str or Path): Either a numpy array or str or
pathlib.Path. If it is a numpy array (loaded image), then
it will be returned as is.
flag (str): Flags specifying the color type of a loaded image,
candidates are `color`, `grayscale` and `unchanged`.
Note that the `turbojpeg` backened does not support `unchanged`.
channel_order (str): Order of channel, candidates are `bgr` and `rgb`.
backend (str | None): The image decoding backend type. Options are
`cv2`, `pillow`, `turbojpeg`, `tifffile`, `None`.
If backend is None, the global imread_backend specified by
``mmcv.use_backend()`` will be used. Default: None.
Returns:
ndarray: Loaded image array.
"""
if backend is None:
backend = imread_backend
if backend not in supported_backends:
raise ValueError(f'backend: {backend} is not supported. Supported '
"backends are 'cv2', 'turbojpeg', 'pillow'")
if isinstance(img_or_path, Path):
img_or_path = str(img_or_path)
if isinstance(img_or_path, np.ndarray):
return img_or_path
elif is_str(img_or_path):
check_file_exist(img_or_path,
f'img file does not exist: {img_or_path}')
if backend == 'turbojpeg':
with open(img_or_path, 'rb') as in_file:
img = jpeg.decode(in_file.read(),
_jpegflag(flag, channel_order))
if img.shape[-1] == 1:
img = img[:, :, 0]
return img
elif backend == 'pillow':
img = Image.open(img_or_path)
img = _pillow2array(img, flag, channel_order)
return img
elif backend == 'tifffile':
img = tifffile.imread(img_or_path)
return img
else:
flag = imread_flags[flag] if is_str(flag) else flag
img = cv2.imread(img_or_path, flag)
if flag == IMREAD_COLOR and channel_order == 'rgb':
cv2.cvtColor(img, cv2.COLOR_BGR2RGB, img)
return img
else:
raise TypeError('"img" must be a numpy array or a str or '
'a pathlib.Path object')
def __init__(self, filename, cache_capacity=10):
check_file_exist(filename, 'Video file not found: ' + filename)
self._vcap = cv2.VideoCapture(filename)
assert cache_capacity > 0
self._cache = Cache(cache_capacity)
self._position = 0
# get basic info
self._width = int(self._vcap.get(CAP_PROP_FRAME_WIDTH))
self._height = int(self._vcap.get(CAP_PROP_FRAME_HEIGHT))
self._fps = self._vcap.get(CAP_PROP_FPS)
self._frame_cnt = int(self._vcap.get(CAP_PROP_FRAME_COUNT))
self._fourcc = self._vcap.get(CAP_PROP_FOURCC)
def __init__(self, filename, cache_capacity=10):
# Check whether the video path is a url
if not filename.startswith(('https://', 'http://')):
check_file_exist(filename, 'Video file not found: ' + filename)
self._vcap = cv2.VideoCapture(filename)
assert cache_capacity > 0
self._cache = Cache(cache_capacity)
self._position = 0
# get basic info
self._width = int(self._vcap.get(CAP_PROP_FRAME_WIDTH))
self._height = int(self._vcap.get(CAP_PROP_FRAME_HEIGHT))
self._fps = self._vcap.get(CAP_PROP_FPS)
self._frame_cnt = int(self._vcap.get(CAP_PROP_FRAME_COUNT))
self._fourcc = self._vcap.get(CAP_PROP_FOURCC)
def frames2video(frame_dir,
video_file,
fps=30,
fourcc='XVID',
filename_tmpl='{:06d}.jpg',
start=0,
end=0,
show_progress=True):
"""Read the frame images from a directory and join them as a video
Args:
frame_dir (str): The directory containing video frames.
video_file (str): Output filename.
fps (float): FPS of the output video.
fourcc (str): Fourcc of the output video, this should be compatible
with the output file type.
filename_tmpl (str): Filename template with the index as the variable.
start (int): Starting frame index.
end (int): Ending frame index.
show_progress (bool): Whether to show a progress bar.
"""
if end == 0:
ext = filename_tmpl.split('.')[-1]
end = len([name for name in scandir(frame_dir, ext)])
first_file = osp.join(frame_dir, filename_tmpl.format(start))
check_file_exist(first_file, 'The start frame not found: ' + first_file)
img = cv2.imread(first_file)
height, width = img.shape[:2]
resolution = (width, height)
vwriter = cv2.VideoWriter(video_file, VideoWriter_fourcc(*fourcc), fps,
resolution)
def write_frame(file_idx):
filename = osp.join(frame_dir, filename_tmpl.format(file_idx))
img = cv2.imread(filename)
vwriter.write(img)
if show_progress:
track_progress(write_frame, range(start, end))
else:
for i in range(start, end):
filename = osp.join(frame_dir, filename_tmpl.format(i))
img = cv2.imread(filename)
vwriter.write(img)
vwriter.release()
def imread(img_or_path, flag='color'):
"""Read an image.
Args:
img_or_path (ndarray or str): Either a numpy array or image path.
If it is a numpy array (loaded image), then it will be returned
as is.
flag (str): Flags specifying the color type of a loaded image,
candidates are `color`, `grayscale` and `unchanged`.
Returns:
ndarray: Loaded image array.
"""
if isinstance(img_or_path, np.ndarray):
return img_or_path
elif is_str(img_or_path):
flag = imread_flags[flag] if is_str(flag) else flag
check_file_exist(img_or_path,
'img file does not exist: {}'.format(img_or_path))
return cv2.imread(img_or_path, flag)
else:
raise TypeError('"img" must be a numpy array or a filename')
