Swift - AVCaptureSession, how to captureOutput

Question

I am new to Swift and trying to implement a text recognition for a live camera feed, which I have created with AVCaptureSession.

The live view is being displayed as a sublayer of an UIView. For the last hours I have been struggling to capture its output into a CMSampleBuffer. I have already surfed the internet but this topic seems to be rare.

Correct me if I am wrong, but I think captureOutput would be the function to go here - unfortunately, I am not aware how to fill it.

My CameraViewController:

import UIKit
import AVFoundation

class CameraViewController: UIViewController, AVCaptureVideoDataOutputSampleBufferDelegate {

    @IBOutlet weak var toolbar: UIToolbar!
    @IBOutlet weak var cameraView: UIView!
    var session: AVCaptureSession?
    var device: AVCaptureDevice?
    var input: AVCaptureDeviceInput?
    var output: AVCaptureMetadataOutput?
    var prevLayer: AVCaptureVideoPreviewLayer?
    var videoOutput: AVCaptureVideoDataOutput?

    override func viewDidLoad() {
        super.viewDidLoad()
        prevLayer?.frame.size = cameraView.frame.size
        createSession()
        self.toolbar.setBackgroundImage(UIImage(),
                                        forToolbarPosition: .any,
                                        barMetrics: .default)
        self.toolbar.setShadowImage(UIImage(), forToolbarPosition: .any)
    }

    @IBAction func goBack(_ sender: Any) {
        performSegue(withIdentifier: "goBackToAdd", sender: self)
    }


    func createSession() {
        session = AVCaptureSession()
        device = AVCaptureDevice.default(for: AVMediaType.video)

        do{
            input = try AVCaptureDeviceInput(device: device!)
        }
        catch{
            print(error)
        }

        if let input = input{
            session?.addInput(input)
        }

        prevLayer = AVCaptureVideoPreviewLayer(session: session!)
        prevLayer?.frame.size = cameraView.frame.size
        prevLayer?.videoGravity = AVLayerVideoGravity.resizeAspectFill

        prevLayer?.connection?.videoOrientation = transformOrientation(orientation: UIInterfaceOrientation(rawValue: UIApplication.shared.statusBarOrientation.rawValue)!)

        cameraView.layer.addSublayer(prevLayer!)

        session?.startRunning()
    }

    func cameraWithPosition(position: AVCaptureDevice.Position) -> AVCaptureDevice? {
        let deviceDiscoverySession = AVCaptureDevice.DiscoverySession(deviceTypes: [.builtInDualCamera, .builtInTelephotoCamera, .builtInTrueDepthCamera, .builtInWideAngleCamera, ], mediaType: .video, position: position)

        if let device = deviceDiscoverySession.devices.first {
            return device
        }
        return nil
    }

    override func viewWillTransition(to size: CGSize, with coordinator: UIViewControllerTransitionCoordinator) {
        coordinator.animate(alongsideTransition: { (context) -> Void in
            self.prevLayer?.connection?.videoOrientation = self.transformOrientation(orientation: UIInterfaceOrientation(rawValue: UIApplication.shared.statusBarOrientation.rawValue)!)
            self.prevLayer?.frame.size = self.cameraView.frame.size
        }, completion: { (context) -> Void in

        })
        super.viewWillTransition(to: size, with: coordinator)
    }

    func transformOrientation(orientation: UIInterfaceOrientation) -> AVCaptureVideoOrientation {
        switch orientation {
        case .landscapeLeft:
            return .landscapeLeft
        case .landscapeRight:
            return .landscapeRight
        case .portraitUpsideDown:
            return .portraitUpsideDown
        default:
            return .portrait
        }
    }

    func captureOutput(_ output: AVCaptureOutput, didOutput sampleBuffer: CMSampleBuffer, from connection: AVCaptureConnection) {
        <#code#>
    }

}

Answer 1

It's pretty easy, first you need to make AVCaptureOutput and set the delegate to an object which it's class conformed to AVCaptureVideoDataOutputSampleBufferDelegate. For that class, just implement the method

func captureOutput(_ output: AVCaptureOutput, didOutput sampleBuffer: CMSampleBuffer, from connection: AVCaptureConnection) {
    guard let imageBuffer = CMSampleBufferGetImageBuffer(sampleBuffer) else {
        return
    }
    let image = CIImage(cvImageBuffer: imageBuffer)
    // ... render the image to a custom layer or write to a AVAsset as you want
}

Answer 2

Get UIImage in captureOutput.

    func captureOutput(_ output: AVCaptureOutput, didOutput sampleBuffer: CMSampleBuffer, from connection: AVCaptureConnection) {
      UIImage *image = [self imageFromSampleBuffer:sampleBuffer];
      dispatch_async(dispatch_get_main_queue(), ^{
       //< Add your code here that uses the image >
     }
}

// Create a UIImage from sample buffer data
- (UIImage *) imageFromSampleBuffer:(CMSampleBufferRef) sampleBuffer 
{
    NSLog(@"imageFromSampleBuffer: called");
    // Get a CMSampleBuffer's Core Video image buffer for the media data
    CVImageBufferRef imageBuffer = CMSampleBufferGetImageBuffer(sampleBuffer); 
    // Lock the base address of the pixel buffer
    CVPixelBufferLockBaseAddress(imageBuffer, 0); 

    // Get the number of bytes per row for the pixel buffer
    void *baseAddress = CVPixelBufferGetBaseAddress(imageBuffer); 

    // Get the number of bytes per row for the pixel buffer
    size_t bytesPerRow = CVPixelBufferGetBytesPerRow(imageBuffer); 
    // Get the pixel buffer width and height
    size_t width = CVPixelBufferGetWidth(imageBuffer); 
    size_t height = CVPixelBufferGetHeight(imageBuffer); 

    // Create a device-dependent RGB color space
    CGColorSpaceRef colorSpace = CGColorSpaceCreateDeviceRGB(); 

    // Create a bitmap graphics context with the sample buffer data
    CGContextRef context = CGBitmapContextCreate(baseAddress, width, height, 8, 
                                             bytesPerRow, colorSpace, kCGBitmapByteOrder32Little | kCGImageAlphaPremultipliedFirst); 
    // Create a Quartz image from the pixel data in the bitmap graphics context
    CGImageRef quartzImage = CGBitmapContextCreateImage(context); 
    // Unlock the pixel buffer
    CVPixelBufferUnlockBaseAddress(imageBuffer,0);


    // Free up the context and color space
    CGContextRelease(context); 
    CGColorSpaceRelease(colorSpace);

    // Create an image object from the Quartz image
    UIImage *image = [UIImage imageWithCGImage:quartzImage];

    // Release the Quartz image
    CGImageRelease(quartzImage);

    return (image);
}