WinRT Extract frames from video stream

Question

I'm decoding barcodes using the built in camera, I do this with the capElement.Source.CapturePhotoToStreamAsync to capture photos from the preview. it works, but freezes the app for a brief moment, which feels very clumsy and buggy.

So I'd like to this in background while at least leaving a responsive UI while processing the photos.

So far I came up with this to capture the video stream:

 private async void ScanInBackground()
        {
            bool failedScan = true;

            var stream = new InMemoryRandomAccessStream();

            await  capElement.Source.StartRecordToStreamAsync(MediaEncodingProfile.CreateWmv(VideoEncodingQuality.HD1080p), stream);

            while(failedScan)
            {
                Byte[] bytes = await GetBytesFromStream(stream);
                //How to split the bytes into frames?

                Task.Delay(50);
            }

            Dispatcher.RunAsync(CoreDispatcherPriority.Low,() => StopCap()); 
        }

and this method to get the bytes from the stream:

public static async Task<byte[]> GetBytesFromStream(IRandomAccessStream randomStream)
        {
            var reader = new DataReader(randomStream.GetInputStreamAt(0));
            var bytes = new byte[randomStream.Size];
            try
            {
                await reader.LoadAsync((uint)randomStream.Size); reader.ReadBytes(bytes);
            }
            catch(Exception ex)
            {
                Logger.LogExceptionAsync(ex, "GetBytesFromStream");
            }
            return bytes;
        }

From the comment at the ScanInBackground, you can see that I have no clue how to split the stream into photos/frames.

Answer 1

There is a sample on the Microsoft github page that is relevant, although they target Windows 10. You may be interested in migrating your project to get this functionality.

GetPreviewFrame: This sample will capture preview frames as opposed to full-blown photos. Once it has a preview frame, it can read and edit the pixels on it.

Here is the relevant part:

private async Task GetPreviewFrameAsSoftwareBitmapAsync()
{
    // Get information about the preview
    var previewProperties = _mediaCapture.VideoDeviceController.GetMediaStreamProperties(MediaStreamType.VideoPreview) as VideoEncodingProperties;

    // Create the video frame to request a SoftwareBitmap preview frame
    var videoFrame = new VideoFrame(BitmapPixelFormat.Bgra8, (int)previewProperties.Width, (int)previewProperties.Height);

    // Capture the preview frame
    using (var currentFrame = await _mediaCapture.GetPreviewFrameAsync(videoFrame))
    {
        // Collect the resulting frame
        SoftwareBitmap previewFrame = currentFrame.SoftwareBitmap;

        // Add a simple green filter effect to the SoftwareBitmap
        EditPixels(previewFrame);
    }
}

private unsafe void EditPixels(SoftwareBitmap bitmap)
{
    // Effect is hard-coded to operate on BGRA8 format only
    if (bitmap.BitmapPixelFormat == BitmapPixelFormat.Bgra8)
    {
        // In BGRA8 format, each pixel is defined by 4 bytes
        const int BYTES_PER_PIXEL = 4;

        using (var buffer = bitmap.LockBuffer(BitmapBufferAccessMode.ReadWrite))
        using (var reference = buffer.CreateReference())
        {
            // Get a pointer to the pixel buffer
            byte* data;
            uint capacity;
            ((IMemoryBufferByteAccess)reference).GetBuffer(out data, out capacity);

            // Get information about the BitmapBuffer
            var desc = buffer.GetPlaneDescription(0);

            // Iterate over all pixels
            for (uint row = 0; row < desc.Height; row++)
            {
                for (uint col = 0; col < desc.Width; col++)
                {
                    // Index of the current pixel in the buffer (defined by the next 4 bytes, BGRA8)
                    var currPixel = desc.StartIndex + desc.Stride * row + BYTES_PER_PIXEL * col;

                    // Read the current pixel information into b,g,r channels (leave out alpha channel)
                    var b = data[currPixel + 0]; // Blue
                    var g = data[currPixel + 1]; // Green
                    var r = data[currPixel + 2]; // Red

                    // Boost the green channel, leave the other two untouched
                    data[currPixel + 0] = b;
                    data[currPixel + 1] = (byte)Math.Min(g + 80, 255);
                    data[currPixel + 2] = r;
                }
            }
        }
    }
}

And declare this outside your class:

[ComImport]
[Guid("5b0d3235-4dba-4d44-865e-8f1d0e4fd04d")]
[InterfaceType(ComInterfaceType.InterfaceIsIUnknown)]
unsafe interface IMemoryBufferByteAccess
{
    void GetBuffer(out byte* buffer, out uint capacity);
}

And of course, your project will have to allow unsafe code for all of this to work.

Have a closer look at the sample to see how to get all the details. Or, to have a walkthrough, you can watch the camera session from the recent //build/ conference, which includes a little bit of a walkthrough through some camera samples.

Answer 2

I believe that showing the media preview and handling the different possible exceptions is necessary, here a simple example of how to do that,

let say you have the following UI, with a CaptureElement to show the preview and an Image control to show the captured pic,

 mc:Ignorable="d" Loaded="MainPage_OnLoaded">

<Grid Background="{StaticResource ApplicationPageBackgroundThemeBrush}" VerticalAlignment="Stretch" HorizontalAlignment="Stretch">
    <Grid.ColumnDefinitions>
        <ColumnDefinition Width="auto"/>
        <ColumnDefinition Width="auto"/>
    </Grid.ColumnDefinitions>
    <Grid.RowDefinitions>
        <RowDefinition Height="auto"/>
        <RowDefinition Height="auto"/>
    </Grid.RowDefinitions>
    <CaptureElement x:Name="PreviewElement" Width="400" Height="400" Grid.Column="0" Grid.Row="0"/>
    <Image x:Name="ImageElement"  Width="400"   Height="400" Grid.Column="1" Grid.Row="0"/>
    <Button Click="TakePhoto_Click"  Content="Take Photo" Grid.Column="0" Grid.Row="1" Grid.ColumnSpan="2" HorizontalAlignment="Stretch" />                                    
</Grid>

On the code behind declare a mediaCapture field,

private MediaCapture _mediaCapture;  

then in the page loaded event handler you need to

• start the media capture device,
• set the several possible exceptions handlers,

• and start the cam preview

   private async void MainPage_OnLoaded(object sender, RoutedEventArgs e)
  {
      //Start the device 
      try
      {
          _mediaCapture = new MediaCapture();
          _mediaCapture.RecordLimitationExceeded += MediaCapture_RecordLimitationExceeded;
          _mediaCapture.Failed += MediaCapture_Failed;
          await _mediaCapture.InitializeAsync();
      }
      catch (UnauthorizedAccessException ex)
      {
          (new MessageDialog("Set the permission to use the webcam")).ShowAsync();                
      }
      catch (Exception ex)
      {
          (new MessageDialog("Can't initialize the webcam !")).ShowAsync();                
      }
  
      //Start the preview 
      if (_mediaCapture != null)
      {
          try
          {
              PreviewElement.Source = _mediaCapture;
              await _mediaCapture.StartPreviewAsync();
          }
          catch (Exception ex)
          {
              (new MessageDialog("Something went wrong !")).ShowAsync();
          }
      }
  }
  private async void MediaCapture_Failed(MediaCapture sender, MediaCaptureFailedEventArgs errorEventArgs)
  {
      await Dispatcher.RunAsync(Windows.UI.Core.CoreDispatcherPriority.Normal, () => (new MessageDialog("Media capture failed")).ShowAsync());
  }
  private async void MediaCapture_RecordLimitationExceeded(MediaCapture sender)
  {
      await _mediaCapture.StopRecordAsync();
      await Dispatcher.RunAsync(Windows.UI.Core.CoreDispatcherPriority.Normal, () => (new MessageDialog("Record limitation exceeded")).ShowAsync());
  }
  

And finally here how to properly take a shot, every thing is async so no lag or whatsoever

 private async void TakePhoto_Click(object sender, RoutedEventArgs e)
    {
        if (_mediaCapture != null)
        {
            try
            {
                ImageEncodingProperties encodingProperties = ImageEncodingProperties.CreateJpeg();
                WriteableBitmap bitmap = new WriteableBitmap((int)ImageElement.Width, (int)ImageElement.Height);
                using (var imageStream = new InMemoryRandomAccessStream())
                {
                    await this._mediaCapture.CapturePhotoToStreamAsync(encodingProperties, imageStream);
                    await imageStream.FlushAsync();
                    imageStream.Seek(0);
                    bitmap.SetSource(imageStream);
                    await Dispatcher.RunAsync(Windows.UI.Core.CoreDispatcherPriority.Normal,
                                    () =>
                                    {
                                        ImageElement.Source = bitmap;
                                    });
                }
            }
            catch (Exception ex)
            {
                (new MessageDialog("Something went wrong !")).ShowAsync();
            }
        }
    }