树莓派opencv实时摄像头传输

https://www.pyimagesearch.com/2015/03/30/accessing-the-raspberry-pi-camera-with-opencv-and-python/

Step 6: Accessing the video stream of your Raspberry Pi using Python and OpenCV.

Alright, so we’ve learned how to grab a single image from the Raspberry Pi camera. But what about a video stream?

You might guess that we are going to use the cv2.VideoCapture  function here — but I actually recommend against this. Getting cv2.VideoCapture  to play nice with your Raspberry Pi is not a nice experience (you’ll need to install extra drivers) and something you should generally avoid.

And besides, why would we use the cv2.VideoCapture  function when we can easily access the raw video stream using the picamera  module?

Let’s go ahead and take a look on how we can access the video stream. Open up a new file, name it test_video.py , and insert the following code:

Accessing the Raspberry Pi Camera with OpenCV and Python

Python

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31

# import the necessary packages from picamera . array import PiRGBArray from picamera import PiCamera import time import cv2   # initialize the camera and grab a reference to the raw camera capture camera = PiCamera ( ) camera . resolution = ( 640 , 480 ) camera . framerate = 32 rawCapture = PiRGBArray ( camera , size = ( 640 , 480 ) )   # allow the camera to warmup time . sleep ( 0.1 )   # capture frames from the camera for frame in camera . capture_continuous ( rawCapture , format = "bgr" , use_video_port = True ) : # grab the raw NumPy array representing the image, then initialize the timestamp # and occupied/unoccupied text image = frame . array   # show the frame cv2 . imshow ( "Frame" , image ) key = cv2 . waitKey ( 1 ) & 0xFF   # clear the stream in preparation for the next frame rawCapture . truncate ( 0 )   # if the `q` key was pressed, break from the loop if key == ord ( "q" ) : break

This example starts off similarly to the previous one. We start off by importing our necessary packages on Lines 2-5.

And from there we construct our camera  object on Line 8 which allows us to interface with the Raspberry Pi camera. However, we also take the time to set the resolution of our camera (640 x 480 pixels) on Line 9 and the frame rate (i.e. frames per second, or simply FPS) on Line 10. We also initialize our PiRGBArray  object on Line 11, but we also take care to specify the same resolution as on Line 9.

Accessing the actual video stream is handled on Line 17 by making a call to thecapture_continuous  method of our camera  object.

This method returns a frame  from the video stream. The frame then has an array  property, which corresponds to the frame  in NumPy array format — all the hard work is done for us on Lines 17 and 20!

We then take the frame of the video and display on screen on Lines 23 and 24.

An important line to pay attention to is Line 27: You must clear the current frame before you move on to the next one!

If you fail to clear the frame, your Python script will throw an error — so be sure to pay close attention to this when implementing your own applications!

Finally, if the user presses the q  key, we break form the loop and exit the program.

To execute our script, just open a terminal (making sure you are in the cv  virtual environment, of course) and issue the following command:

Accessing the Raspberry Pi Camera with OpenCV and Python

Shell

1	$ python test_video .py

Below follows an example of me executing the above command:

As you can see, the Raspberry Pi camera’s video stream is being read by OpenCV and then displayed on screen! Furthermore, the Raspberry Pi camera shows no lag when accessing frames at 32 FPS. Granted, we are not doing any processing on the individual frames, but as I’ll show in future blog posts, the Pi 2 can easily keep up 24-32 FPS even when processing each frame.