我怎样才能像“摄像机”那样实时进行人脸检测呢?

我注意到10.0之后就不再推荐AVCaptureStillImageOutput了,所以我改用AVCapturePhotoOutput。但是,我发现我保存下来的用于面部检测的图像不是那么满意吗?有什么想法吗?
更新
在尝试了@提到的。目前,我使用AVCaptureMetadataOutput来检测没有CIFaceDetector的人脸。它如预期的那样工作。然而,当我试图划出脸的界限时,它似乎被错位了。有什么想法吗?

let metaDataOutput = AVCaptureMetadataOutput()
captureSession.sessionPreset = AVCaptureSessionPresetPhoto
let backCamera = AVCaptureDevice.defaultDevice(withDeviceType: .builtInWideAngleCamera, mediaType: AVMediaTypeVideo, position: .back)
do {
let input = try AVCaptureDeviceInput(device: backCamera)
if (captureSession.canAddInput(input)) {
captureSession.addInput(input)
// MetadataOutput instead
if(captureSession.canAddOutput(metaDataOutput)) {
captureSession.addOutput(metaDataOutput)
metaDataOutput.setMetadataObjectsDelegate(self, queue: DispatchQueue.main)
metaDataOutput.metadataObjectTypes = [AVMetadataObjectTypeFace]
previewLayer = AVCaptureVideoPreviewLayer(session: captureSession)
previewLayer?.frame = cameraView.bounds
previewLayer?.videoGravity = AVLayerVideoGravityResizeAspectFill
cameraView.layer.addSublayer(previewLayer!)
captureSession.startRunning()
}
}
} catch {
print(error.localizedDescription)
}和
extension CameraViewController: AVCaptureMetadataOutputObjectsDelegate {
func captureOutput(_ captureOutput: AVCaptureOutput!, didOutputMetadataObjects metadataObjects: [Any]!, from connection: AVCaptureConnection!) {
if findFaceControl {
findFaceControl = false
for metadataObject in metadataObjects {
if (metadataObject as AnyObject).type == AVMetadataObjectTypeFace {
print("")
print(metadataObject)
let bounds = (metadataObject as! AVMetadataFaceObject).bounds
print("origin x: \(bounds.origin.x)")
print("origin y: \(bounds.origin.y)")
print("size width: \(bounds.size.width)")
print("size height: \(bounds.size.height)")
print("cameraView width: \(self.cameraView.frame.width)")
print("cameraView height: \(self.cameraView.frame.height)")
var face = CGRect()
face.origin.x = bounds.origin.x * self.cameraView.frame.width
face.origin.y = bounds.origin.y * self.cameraView.frame.height
face.size.width = bounds.size.width * self.cameraView.frame.width
face.size.height = bounds.size.height * self.cameraView.frame.height
print(face)
showBounds(at: face)
}
}
}
}
}原始
var captureSession = AVCaptureSession()
var photoOutput = AVCapturePhotoOutput()
var previewLayer: AVCaptureVideoPreviewLayer?
override func viewWillAppear(_ animated: Bool) {
super.viewWillAppear(true)
captureSession.sessionPreset = AVCaptureSessionPresetHigh
let backCamera = AVCaptureDevice.defaultDevice(withMediaType: AVMediaTypeVideo)
do {
let input = try AVCaptureDeviceInput(device: backCamera)
if (captureSession.canAddInput(input)) {
captureSession.addInput(input)
if(captureSession.canAddOutput(photoOutput)){
captureSession.addOutput(photoOutput)
captureSession.startRunning()
previewLayer = AVCaptureVideoPreviewLayer(session: captureSession)
previewLayer?.videoGravity = AVLayerVideoGravityResizeAspectFill
previewLayer?.frame = cameraView.bounds
cameraView.layer.addSublayer(previewLayer!)
}
}
} catch {
print(error.localizedDescription)
}
}
func captureImage() {
let settings = AVCapturePhotoSettings()
let previewPixelType = settings.availablePreviewPhotoPixelFormatTypes.first!
let previewFormat = [kCVPixelBufferPixelFormatTypeKey as String: previewPixelType
]
settings.previewPhotoFormat = previewFormat
photoOutput.capturePhoto(with: settings, delegate: self)
}
func capture(_ captureOutput: AVCapturePhotoOutput, didFinishProcessingPhotoSampleBuffer photoSampleBuffer: CMSampleBuffer?, previewPhotoSampleBuffer: CMSampleBuffer?, resolvedSettings: AVCaptureResolvedPhotoSettings, bracketSettings: AVCaptureBracketedStillImageSettings?, error: Error?) {
if let error = error {
print(error.localizedDescription)
}
// Not include previewPhotoSampleBuffer
if let sampleBuffer = photoSampleBuffer,
let dataImage = AVCapturePhotoOutput.jpegPhotoDataRepresentation(forJPEGSampleBuffer: sampleBuffer, previewPhotoSampleBuffer: nil) {
self.imageView.image = UIImage(data: dataImage)
self.imageView.isHidden = false
self.previewLayer?.isHidden = true
self.findFace(img: self.imageView.image!)
}
}findFace适用于正常图像。然而,我通过相机捕捉到的图像将无法工作,有时只能识别一张脸。
法线图像

捕获图像

func findFace(img: UIImage) {
guard let faceImage = CIImage(image: img) else { return }
let accuracy = [CIDetectorAccuracy: CIDetectorAccuracyHigh]
let faceDetector = CIDetector(ofType: CIDetectorTypeFace, context: nil, options: accuracy)
// For converting the Core Image Coordinates to UIView Coordinates
let detectedImageSize = faceImage.extent.size
var transform = CGAffineTransform(scaleX: 1, y: -1)
transform = transform.translatedBy(x: 0, y: -detectedImageSize.height)
if let faces = faceDetector?.features(in: faceImage, options: [CIDetectorSmile: true, CIDetectorEyeBlink: true]) {
for face in faces as! [CIFaceFeature] {
// Apply the transform to convert the coordinates
var faceViewBounds = face.bounds.applying(transform)
// Calculate the actual position and size of the rectangle in the image view
let viewSize = imageView.bounds.size
let scale = min(viewSize.width / detectedImageSize.width,
viewSize.height / detectedImageSize.height)
let offsetX = (viewSize.width - detectedImageSize.width * scale) / 2
let offsetY = (viewSize.height - detectedImageSize.height * scale) / 2
faceViewBounds = faceViewBounds.applying(CGAffineTransform(scaleX: scale, y: scale))
print("faceBounds = \(faceViewBounds)")
faceViewBounds.origin.x += offsetX
faceViewBounds.origin.y += offsetY
showBounds(at: faceViewBounds)
}
if faces.count != 0 {
print("Number of faces: \(faces.count)")
} else {
print("No faces ")
}
}
}
func showBounds(at bounds: CGRect) {
let indicator = UIView(frame: bounds)
indicator.frame = bounds
indicator.layer.borderWidth = 3
indicator.layer.borderColor = UIColor.red.cgColor
indicator.backgroundColor = .clear
self.imageView.addSubview(indicator)
faceBoxes.append(indicator)
}发布于 2017-01-24 13:39:25
检测人脸的方法有两种: CIFaceDetector和AVCaptureMetadataOutput。根据您的需求,选择与您相关的内容。
CIFaceDetector有更多的功能,它给你眼睛和嘴巴的位置,一个微笑探测器等等。
另一方面,在帧上计算AVCaptureMetadataOutput,跟踪检测到的人脸,不需要添加额外的代码。我发现这是因为追踪。在此过程中,人脸检测更加可靠。这样做的缺点是,你只会检测到面孔,而不是眼睛或嘴巴的位置。此方法的另一个优点是,定位问题较小,因为您可以在设备方向发生变化时使用videoOrientation,而面向的方向将相对于该方向。
在我的例子中,我的应用程序使用YUV420作为所需的格式,因此实时使用CIDetector (与RGB一起工作)是不可行的。由于连续跟踪,使用AVCaptureMetadataOutput节省了大量的精力,并且执行得更可靠。
一旦我有了包围框的脸,我编码额外的特征,如皮肤检测,并将其应用于静止图像。
注意:当您捕获静态图像时,脸框信息将与元数据一起添加,因此不会出现同步问题。
您也可以使用两者的组合,以获得更好的结果。
根据您的应用程序探索和评估利弊。
人脸矩形是wrt图像的原点。所以,对于屏幕来说,它可能是不同的。使用:
for (AVMetadataFaceObject *faceFeatures in metadataObjects) {
CGRect face = faceFeatures.bounds;
CGRect facePreviewBounds = CGRectMake(face.origin.y * previewLayerRect.size.width,
face.origin.x * previewLayerRect.size.height,
face.size.width * previewLayerRect.size.height,
face.size.height * previewLayerRect.size.width);
/* Draw rectangle facePreviewBounds on screen */
}发布于 2017-03-06 08:06:07
要在iOS上执行人脸检测,可以使用CIDetector (苹果)或移动视觉 (Google)。
IMO,提供了更好的性能。
如果你感兴趣,这是你可以玩的项目。(iOS 10.2,Swift 3)
在2017年WWDC之后,苹果在iOS 11中引入了iOS。Vision框架使人脸检测更加准确:)
我做了一个演示项目。包含VisionV.S. CIDetector.同时,它还包含了人脸地标的实时检测。
发布于 2018-06-17 12:02:01
有点晚了,但这里是坐标问题的解决方案。可以在预览层上调用一种方法将元数据对象转换为您的坐标系:transformedMetadataObject(for:metadataObject)。
guard let transformedObject = previewLayer.transformedMetadataObject(for: metadataObject) else {
continue
}
let bounds = transformedObject.bounds
showBounds(at: bounds)顺便说一句,如果您使用Swift 4 (或将项目升级到Swift 4),AVCaptureMetadataOutputsObject的委托方法已经更改为:
func metadataOutput(_ output: AVCaptureMetadataOutput, didOutput metadataObjects: [AVMetadataObject], from connection: AVCaptureConnection)亲切的问候
https://stackoverflow.com/questions/41354698
复制相似问题