Skip to content

feat(video): add height_width for webcam caps #494

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
hanxiao merged 1 commit into from
Aug 19, 2022
Merged

feat(video): add height_width for webcam caps #494

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 21 additions & 4 deletions docarray/document/mixins/video.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,11 +1,21 @@
import threading
import time
from typing import Union, BinaryIO, TYPE_CHECKING, Generator, Type, Dict, Optional
from typing import (
Union,
BinaryIO,
TYPE_CHECKING,
Generator,
Type,
Dict,
Optional,
Tuple,
)

import numpy as np

if TYPE_CHECKING:
from docarray.typing import T
from docarray import Document


class VideoDataMixin:
Expand All @@ -14,6 +24,7 @@ class VideoDataMixin:
@classmethod
def generator_from_webcam(
cls: Type['T'],
height_width: Optional[Tuple[int, int]] = None,
show_window: bool = True,
window_title: str = 'webcam',
fps: int = 30,
Expand All @@ -26,6 +37,8 @@ def generator_from_webcam(

This feature requires the `opencv-python` package.

:param height_width: the shape of the video frame, if not provided, the shape will be determined from the first frame.
Note that this is restricted by the hardware of the camera.
:param show_window: if to show preview window of the webcam video
:param window_title: the window title of the preview window
:param fps: expected frames per second, note that this is not guaranteed, as the actual fps depends on the hardware limit
Expand All @@ -46,7 +59,11 @@ def generator_from_webcam(
try:
while not exit_event.is_set():
rval, frame = vc.read()
yield cls(tensor=frame, tags=tags)
d = cls(tensor=frame, tags=tags) # type: Document
if height_width:
d.set_image_tensor_shape(height_width)

yield d

key = cv2.waitKey(1000 // (fps + fps - actual_fps))

Expand All @@ -60,7 +77,7 @@ def generator_from_webcam(

# putting the FPS count on the frame
cv2.putText(
frame,
d.tensor,
f'FPS {actual_fps:0.0f}/{fps}',
(7, 70),
cv2.FONT_HERSHEY_SIMPLEX,
Expand All @@ -71,7 +88,7 @@ def generator_from_webcam(
)

# displaying the frame with fps
cv2.imshow(window_title, frame)
cv2.imshow(window_title, d.tensor)

if key == exit_key or not rval:
break
Expand Down