视频JavaCV中的人脸识别

Question

我正在学习JavaCV，并找到了用于人脸再殖民化的示例代码。这是代码

import java.io.File;

import org.bytedeco.javacpp.IntPointer;
import org.bytedeco.javacpp.DoublePointer;

import org.bytedeco.javacv.Frame;
import org.bytedeco.javacv.FrameGrabber.Exception;
import org.bytedeco.javacv.OpenCVFrameConverter;
import org.bytedeco.javacv.OpenCVFrameGrabber;

import static org.bytedeco.javacpp.opencv_core.*;
import static org.bytedeco.javacpp.opencv_face.*;
import static org.bytedeco.javacpp.opencv_highgui.*;
import static org.bytedeco.javacpp.opencv_imgproc.*;
import static org.bytedeco.javacpp.opencv_objdetect.*;

/**
 * This is an example how to detect face in a video file with javacv
 * @author Vincent He (chinadragon0515@gmail.com)
 *
 */
public class FaceRecognizerInVideo {

    public static void main(String[] args) throws Exception {

        OpenCVFrameConverter.ToMat converterToMat = new OpenCVFrameConverter.ToMat();

        /**if (args.length < 2) {
            System.out.println("Two parameters are required to run this program, first parameter is the analized video and second parameter is the trained result for fisher faces.");
        } */

        String videoFileName = "myvideo.mp4";
        String trainedResult = "myfacedir";

        CascadeClassifier face_cascade = new CascadeClassifier(
                "data\\haarcascade_frontalface_default.xml");
        FaceRecognizer lbphFaceRecognizer = LBPHFaceRecognizer.create();
        lbphFaceRecognizer.read(trainedResult);

        File f = new File(videoFileName);

        OpenCVFrameGrabber grabber = null;
        try {
            grabber = OpenCVFrameGrabber.createDefault(f);
            grabber.start();
        } catch (Exception e) {
            System.err.println("Failed start the grabber.");
        }

        Frame videoFrame = null;
        Mat videoMat = new Mat();
        while (true) {
            videoFrame = grabber.grab();
            videoMat = converterToMat.convert(videoFrame);
            Mat videoMatGray = new Mat();
            // Convert the current frame to grayscale:
            cvtColor(videoMat, videoMatGray, COLOR_BGRA2GRAY);
            equalizeHist(videoMatGray, videoMatGray);

            Point p = new Point();
            RectVector faces = new RectVector();
            // Find the faces in the frame:
            face_cascade.detectMultiScale(videoMatGray, faces);

            // At this point you have the position of the faces in
            // faces. Now we'll get the faces, make a prediction and
            // annotate it in the video. Cool or what?
            for (int i = 0; i < faces.size(); i++) {
                Rect face_i = faces.get(i);

                Mat face = new Mat(videoMatGray, face_i);
                // If fisher face recognizer is used, the face need to be
                // resized.
                // resize(face, face_resized, new Size(im_width, im_height),
                // 1.0, 1.0, INTER_CUBIC);

                // Now perform the prediction, see how easy that is:
                IntPointer label = new IntPointer(1);
                DoublePointer confidence = new DoublePointer(1);
                lbphFaceRecognizer.predict(face, label, confidence);
                int prediction = label.get(0);

                // And finally write all we've found out to the original image!
                // First of all draw a green rectangle around the detected face:
                rectangle(videoMat, face_i, new Scalar(0, 255, 0, 1));

                // Create the text we will annotate the box with:
                String box_text = "Prediction = " + prediction;
                // Calculate the position for annotated text (make sure we don't
                // put illegal values in there):
                int pos_x = Math.max(face_i.tl().x() - 10, 0);
                int pos_y = Math.max(face_i.tl().y() - 10, 0);
                // And now put it into the image:
                putText(videoMat, box_text, new Point(pos_x, pos_y),
                        FONT_HERSHEY_PLAIN, 1.0, new Scalar(0, 255, 0, 2.0));
            }
            // Show the result:
            imshow("face_recognizer", videoMat);

            char key = (char) waitKey(20);
            // Exit this loop on escape:
            if (key == 27) {
                destroyAllWindows();
                break;
            }
        }
    }

}

我在String videoFileName中传递了一个示例视频，并且还将面部目录添加到String trainedResult中。但是它不能正常工作。我每次都遇到错误

Exception in thread "main" java.lang.RuntimeException: OpenCV(3.4.2) /home/travis/build/javacpp-presets/opencv/cppbuild/linux-x86_64/opencv-3.4.2/modules/core/src/persistence_c.cpp:388: error: (-49:Unknown error code -49) Input file is empty in function 'cvOpenFileStorage'

    at org.bytedeco.javacpp.opencv_face$FaceRecognizer.read(Native Method)
    at facerec.FaceRecognizerInVideo.main(FaceRecognizerInVideo.java:44)

代码有什么问题？ 代码在这里：https://github.com/bytedeco/javacv/blob/master/samples/FaceRecognizerInVideo.java