谁有关于如何使用 Face Detection Camera 2 API 的资料？

Question

在官方来源上没有找到信息...有很多关于如何使用 Camera API 的示例，但是如何使用 Camera2API 任何东西...在 Stake 上进行了一些讨论等等...是一个与我类似的问题，但我有一个问题没有解决。 ..

链接到同一个问题： Android camera2 face recognition

我以Google's API for Camera 2为例。

这就是我所做的，但我没有检测到人脸：

我添加了事件

    private void createCameraPreviewSession() {
    try {
        SurfaceTexture texture = mTextureView.getSurfaceTexture();
        assert texture != null;

        // We configure the size of default buffer to be the size of camera preview we want.
        texture.setDefaultBufferSize(mPreviewSize.getWidth(), mPreviewSize.getHeight());

        // This is the output Surface we need to start preview.
        Surface surface = new Surface(texture);

        // We set up a CaptureRequest.Builder with the output Surface.
        mPreviewRequestBuilder
                = mCameraDevice.createCaptureRequest(CameraDevice.TEMPLATE_PREVIEW);
        mPreviewRequestBuilder.addTarget(surface);

        // Here, we create a CameraCaptureSession for camera preview.
        mCameraDevice.createCaptureSession(Arrays.asList(surface, mImageReader.getSurface()),
                new CameraCaptureSession.StateCallback() {

                    @Override
                    public void onConfigured(@NonNull CameraCaptureSession cameraCaptureSession) {
                        // The camera is already closed
                        if (null == mCameraDevice) {
                            return;
                        }

                        // When the session is ready, we start displaying the preview.
                        mCaptureSession = cameraCaptureSession;
                        try {



//           ---->>         Установка модуля распознания лица
                            mPreviewRequestBuilder.set(CaptureRequest.STATISTICS_FACE_DETECT_MODE,
                                    CameraMetadata.STATISTICS_FACE_DETECT_MODE_FULL);



                            // Auto focus should be continuous for camera preview.
                            mPreviewRequestBuilder.set(CaptureRequest.CONTROL_AF_MODE,
                                    CaptureRequest.CONTROL_AF_MODE_CONTINUOUS_PICTURE);

                            // Flash is automatically enabled when necessary.
                            setAutoFlash(mPreviewRequestBuilder);

                            // Finally, we start displaying the camera preview.
                            mPreviewRequest = mPreviewRequestBuilder.build();

                            mCaptureSession.setRepeatingRequest(mPreviewRequest,
                                    mCaptureCallback, mBackgroundHandler);
                        } catch (CameraAccessException e) {
                            e.printStackTrace();
                        }
                    }

                    @Override
                    public void onConfigureFailed(
                            @NonNull CameraCaptureSession cameraCaptureSession) {
                        System.out.println("Failed строка 757");
                    }
                }, null
        );
    } catch (CameraAccessException e) {
        e.printStackTrace();
    }
}

private CameraCaptureSession.CaptureCallback mCaptureCallback
        = new CameraCaptureSession.CaptureCallback() {

    @Override
    public void onCaptureProgressed(@NonNull CameraCaptureSession session,
                                    @NonNull CaptureRequest request,
                                    @NonNull CaptureResult partialResult) {
        process(partialResult);
    }

    @Override
    public void onCaptureCompleted(@NonNull CameraCaptureSession session,
                                   @NonNull CaptureRequest request,
                                   @NonNull TotalCaptureResult result) {
        process(result);
    }

    private void process(CaptureResult result) {


--->   //здесь проверяю получает ли он массив лиц или нет + непонятный мод
        Integer mode = result.get(CaptureResult.STATISTICS_FACE_DETECT_MODE);
        Face[] faces = result.get(CaptureResult.STATISTICS_FACES);
        if(faces != null && mode != null)
            System.out.println("tagDDDDDDDDDDDDDDDDDDDDDDDD" + "faces : " +
                    faces.length + " , mode : " + mode);

        switch (mState) {
            case STATE_PREVIEW: {
                // We have nothing to do when the camera preview is working normally.

//                  Here i set Face Detection
                mPreviewRequestBuilder.set(CaptureRequest.STATISTICS_FACE_DETECT_MODE,
                        CameraMetadata.STATISTICS_FACE_DETECT_MODE_FULL);
                break;
            }

我在这里检查相机可以获取的最大面孔数

    private void setUpCameraOutputs(int width, int height) {

    CameraManager manager = (CameraManager) getSystemService(Context.CAMERA_SERVICE);
    try {
        for (String cameraId : manager.getCameraIdList()) {
            CameraCharacteristics characteristics
                    = manager.getCameraCharacteristics(cameraId);

            // We don't use a front facing camera in this sample.
            Integer facing = characteristics.get(CameraCharacteristics.LENS_FACING);
            if (facing != null && facing == CameraCharacteristics.LENS_FACING_FRONT) {
                continue;
            }

            max_count = characteristics.get(
                    CameraCharacteristics.STATISTICS_INFO_MAX_FACE_COUNT);
            modes = characteristics.get(
                    CameraCharacteristics.STATISTICS_INFO_AVAILABLE_FACE_DETECT_MODES);

            System.out.println("!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! max_count " + max_count + " modes " + modes);

** 输出为：**

I/System.out: !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! max_count 16 modes [I@3e2907e8

** 这就是日志打印的内容 **

    03-08 18:34:07.018 7405-7438/com.example.android.camera2basic I/System.out: tagDDDDDDDDDDDDDDDDDDDDDDDDfaces : 0 , mode : 1
03-08 18:34:07.048 7405-7438/com.example.android.camera2basic I/System.out: tagDDDDDDDDDDDDDDDDDDDDDDDDfaces : 0 , mode : 1
03-08 18:34:07.078 7405-7438/com.example.android.camera2basic I/System.out: tagDDDDDDDDDDDDDDDDDDDDDDDDfaces : 0 , mode : 1
03-08 18:34:07.118 7405-7438/com.example.android.camera2basic I/System.out: tagDDDDDDDDDDDDDDDDDDDDDDDDfaces : 0 , mode : 1
03-08 18:34:07.148 7405-7438/com.example.android.camera2basic I/System.out: tagDDDDDDDDDDDDDDDDDDDDDDDDfaces : 0 , mode : 1
03-08 18:34:07.178 7405-7438/com.example.android.camera2basic I/System.out: tagDDDDDDDDDDDDDDDDDDDDDDDDfaces : 0 , mode : 1
03-08 18:34:07.218 7405-7438/com.example.android.camera2basic I/System.out: tagDDDDDDDDDDDDDDDDDDDDDDDDfaces : 0 , mode : 1
03-08 18:34:07.258 7405-7438/com.example.android.camera2basic I/System.out: tagDDDDDDDDDDDDDDDDDDDDDDDDfaces : 0 , mode : 1
03-08 18:34:07.288 7405-7438/com.example.android.camera2basic I/System.out: tagDDDDDDDDDDDDDDDDDDDDDDDDfaces : 0 , mode : 1
03-08 18:34:07.308 7405-7438/com.example.android.camera2basic I/System.out: tagDDDDDDDDDDDDDDDDDDDDDDDDfaces : 0 , mode : 1
03-08 18:34:07.348 7405-7438/com.example.android.camera2basic I/System.out: tagDDDDDDDDDDDDDDDDDDDDDDDDfaces : 0 , mode : 1

为什么它不是reterning face？如果有人有正确的工作示例，请提供链接。我如何使用 camera2API 进行人脸检测。整个星期，我都无法理解（（

Answer 1

阿列克谢，

您的 RequestBuilder 看起来是正确的，但我认为问题在于您如何选择要使用的相机设备。我有和你一样的设置，它正在工作。

private boolean setUpCameraOutputs() {
    Activity activity = getActivity();
    CameraManager manager = (CameraManager) activity.getSystemService(Context.CAMERA_SERVICE);
    if (manager == null) {
        ErrorDialog.buildErrorDialog("This device doesn't support the Camera2 API.").
            show(getFragmentManager(), "dialog");
        return false;
    }
    try {
        // Find a CameraDevice that supports Face recognition, and configure state.
        for (String cameraId : manager.getCameraIdList()) {
            CameraCharacteristics characteristics
                    = manager.getCameraCharacteristics(cameraId);

            // We only use a camera that supports Faces.
            if (!contains(characteristics.get(
                            CameraCharacteristics.STATISTICS_INFO_AVAILABLE_FACE_DETECT_MODES),
                    CameraCharacteristics.STATISTICS_FACE_DETECT_MODE_SIMPLE)) {
                continue;
            }

            StreamConfigurationMap map = characteristics.get(
                    CameraCharacteristics.SCALER_STREAM_CONFIGURATION_MAP);

            synchronized (mCameraStateLock) {
                mCharacteristics = characteristics;
                mCameraId = cameraId;
            }
            return true;
        }
    } catch (CameraAccessException e) {
        e.printStackTrace();
    }

    // If we found no suitable cameras for capturing Faces, warn the user.
    ErrorDialog.buildErrorDialog("This device doesn't support Face detection").
            show(getFragmentManager(), "dialog");
    return false;
}

希望以上代码至少可以帮助您确定问题出在您的设备上还是出在您访问相机的方式上。

Answer 2

在 Play services 8.3 中，Google 引入了 Mobile Vision API。它包括一个易于使用的 API，称为人脸 API，可检测图像和视频中的人脸。不要将此与人脸识别混淆，因为人脸 API 目前仅支持检测。

检测人脸

当 API 检测到人脸时，它会作为 Face 对象返回。 Face 对象提供人脸的空间数据，因此您可以 例如，在面部周围绘制边界矩形，或者，如果您使用 脸上的地标，你可以在正确的地方为人脸添加特征 地方，比如给一个人一顶新帽子。

它还带有很酷的方法，例如用户是在微笑 :) 还是在眨眼 ;) 等等。

查看文档和参考以了解更多信息。

1. Mobile Vision: Find objects in photos and video, using real-time on-device vision technology.
2. Face API- Google Developers
3. Mobile Vision- Youtube
4. Android developers- Face detection API

希望这会有所帮助:)