如何在CameraX中获得实时预览并检测用户是否使用Firebase的人脸检测来眨眼？

问题描述

我正在尝试使用CameraX API和Firebase MLkit人脸检测来检测用户是否眨眼。我对这两个API都是新手，而且我很难使用CameraX，因为大多数教程和文档都是Kotlin（我对Kotlin的知识为零）。我想发生的是我希望CameraX进行实时预览，然后Firebase的人脸检测将确定用户是否眨眼。我遇到的所有CameraX教程都是通过按钮实现的，但我想在闪烁后触发move to dashboard。下面是我的代码：

public class FaceDetectionActivity extends AppCompatActivity {

    private Executor executor = Executors.newSingleThreadExecutor();
    private int REQUEST_CODE_PERMISSIONS = 1001;
    private final String[] required_PERMISSIONS = new String[]{"android.permission.CAMERA","android.permission.WRITE_EXTERNAL_STORAGE"};

    private PreviewView mPreviewView;
    private FaceDetector detector;

    @Override
    protected void onCreate(Bundle savedInstanceState) {
        super.onCreate(savedInstanceState);
        setContentView(R.layout.activity_face_detection);

        mPreviewView = findViewById(R.id.camera);

        if(allPermissionsGranted()){
            startCamera(); //start camera if permission has been granted by user
        } else{
            ActivityCompat.requestPermissions(this,required_PERMISSIONS,REQUEST_CODE_PERMISSIONS);
        }

        FaceDetectorOptions highAccuracyOpts =
                new FaceDetectorOptions.Builder()
                        .setPerformanceMode(FaceDetectorOptions.PERFORMANCE_MODE_ACCURATE)
                        .setLandmarkMode(FaceDetectorOptions.LANDMARK_MODE_ALL)
                        .setContourMode(FaceDetectorOptions.CONTOUR_MODE_ALL)
                        .setClassificationMode(FaceDetectorOptions.CLASSIFICATION_MODE_ALL)
                        .enableTracking()
                        .build();

        detector = FaceDetection.getClient(highAccuracyOpts);
    }

    private void startCamera() {
        ListenableFuture<ProcessCameraProvider> cameraProviderFuture = ProcessCameraProvider.getInstance(this);
        cameraProviderFuture.addListener(new Runnable() {
            @Override
            public void run() {
                try {
                    ProcessCameraProvider cameraProvider = cameraProviderFuture.get();
                    bindPreview(cameraProvider);
                } catch (ExecutionException | InterruptedException e) {
                    // No errors need to be handled for this Future.
                    // This should never be reached.
                }
            }
        },ContextCompat.getMainExecutor(this));
    }

    private void bindPreview(@NonNull ProcessCameraProvider cameraProvider) {
        Preview preview = new Preview.Builder().build();
        CameraSelector cameraSelector = new CameraSelector.Builder()
                .requireLensFacing(CameraSelector.LENS_FACING_FRONT)
                .build();

        ImageAnalysis imageAnalysis = new ImageAnalysis.Builder().build();
        ImageCapture.Builder builder = new ImageCapture.Builder();

        final ImageCapture imageCapture = builder
                .setTargetRotation(this.getwindowManager().getDefaultdisplay().getRotation())
                .build();
        preview.setSurfaceProvider(mPreviewView.createSurfaceProvider());
        cameraProvider.bindToLifecycle(this,cameraSelector,preview,imageAnalysis,imageCapture);

        //Detect here first if the user blink
        imageCapture.takePicture(executor,new ImageCapture.OnImageCapturedCallback() {
            @Override
            public void onCaptureSuccess(@NonNull ImageProxy image) {
                Bitmap bitmap = getBitmap(image);
                Inputimage inputimage = Inputimage.fromBitmap(bitmap,image.getimageInfo().getRotationdegrees());
                Task<List<Face>> result = detector.process(inputimage)
                        .addOnSuccessListener(faces -> {
                            for (Face face : faces) {
                                if (face.getLeftEyeOpenProbability() < 0.4 && face.getRightEyeOpenProbability() < 0.4) {
                                    Log.d("lifeFaceDetection","Blinked");
                                    
                                    //Move to dashboard here
                                } else {
                                    Log.d("lifeFaceDetection","Didn't");
                                }
                            }
                        })
                        .addOnFailureListener(e -> Log.e("life",e.toString()));
                result.addOnCompleteListener(task -> {
                    if (task.isSuccessful()){
                        Toast.makeText(FaceDetectionActivity.this,"Image Saved successfully",Toast.LENGTH_SHORT).show();
                    }
                });
                super.onCaptureSuccess(image);
            }

            @Override
            public void onError(@NonNull ImageCaptureException exception) {
                super.onError(exception);
            }
        });
    }

这也是行不通的，您能告诉我另一种实现闪烁检测的方法吗？

编辑： 我遵循了this教程，但仍然无法将kotlin代码转换为Java。

解决方法

暂无找到可以解决该程序问题的有效方法，小编努力寻找整理中！

如果你已经找到好的解决方法，欢迎将解决方案带上本链接一起发送给小编。

小编邮箱:dio#foxmail.com (将#修改为@）