一.Android摄像头预览

Android OpenCV开发过程中，我们有3种可选方式去实现Android摄像头预览功能：

• 使用Android系统Camera API
• 使用CameraX（JetPack组件）
• 使用OpenCV SDK辅助类（JavaCameraView、JavaCamera2View等）

利用Android OpenCV SDK实现相机预览

1.申明权限

  <uses-permission android:name="android.permission.CAMERA" />
  <uses-feature
        android:name="android.hardware.camera"
        android:required="false" />
    <uses-feature
        android:name="android.hardware.camera.autofocus"
        android:required="false" />
    <uses-feature
        android:name="android.hardware.camera.front"
        android:required="false" />
    <uses-feature
        android:name="android.hardware.camera.front.autofocus"
        android:required="false" />

2.布局添加JavaCameraView或者JavaCamera2View至布局

<?xml version="1.0" encoding="utf-8"?>
<androidx.constraintlayout.widget.ConstraintLayout xmlns:android="http://schemas.android.com/apk/res/android"
    xmlns:app="http://schemas.android.com/apk/res-auto"
    xmlns:tools="http://schemas.android.com/tools"
    android:layout_width="match_parent"
    android:layout_height="match_parent"
    tools:context=".MainActivity">

    <org.opencv.android.JavaCamera2View
        android:id="@+id/camera_view"
        app:layout_constraintTop_toTopOf="parent"
        app:layout_constraintLeft_toLeftOf="parent"
        android:layout_width="match_parent"
        android:layout_height="match_parent">

    </org.opencv.android.JavaCamera2View>
    <ImageView
        android:id="@+id/image_view"
        android:layout_width="match_parent"
        android:layout_height="match_parent">

    </ImageView>

</androidx.constraintlayout.widget.ConstraintLayout>

3.Activity继承CameraActivity，实现CameraBridgeViewBase.CvCameraViewListener或者CameraBridgeViewBase.CvCameraViewListener2接口，两个接口的差异主要集中在onCameraFrame回调。

  @Override
    public void onCameraViewStarted(int width, int height) {

    }

    @Override
    public void onCameraViewStopped() {

    }

    @Override
    public Mat onCameraFrame(CameraBridgeViewBase.CvCameraViewFrame inputFrame) {
        // 获取相机中的图像
        Mat rgba = inputFrame.rgba();
        Core.rotate(rgba, rgba, Core.ROTATE_90_CLOCKWISE);
        Bitmap bitmap = Bitmap.createBitmap(rgba.cols(), rgba.rows(), Bitmap.Config.ARGB_8888);
        Utils.matToBitmap(rgba, bitmap);
        Bitmap location = location(bitmap);
        if (location==null){
            return null;
        }
        runOnUiThread(() -> image_view.setImageBitmap(location));
        return null;
    }

4.复写方法getCameraViewList

 @Override
    protected List<? extends CameraBridgeViewBase> getCameraViewList() {
        return Arrays.asList(mCVCamera);
    }

二.物体检测

1.在onCameraFrame回调中拿到图像后做一次滤镜去除干扰再进行边缘检测，这时候边缘可能并不是连通的所以我们再对图像做一次膨胀操作。最后进行轮廓检测将检测到的轮廓绘制到原图上。

  private Bitmap location(Bitmap bmp) {
        Mat originMat=new Mat();
        Utils.bitmapToMat(bmp,originMat);
        Mat resultG = new Mat();
        Mat result = new Mat();
        Imgproc.GaussianBlur(originMat, resultG, new Size(3.0, 3.0), 0);
        Imgproc.Canny(resultG, result, 100.0, 220.0, 3);
        // 膨胀，连接边缘
        Imgproc.dilate(result, result, new Mat(), new Point(-1,-1), 4, 1, new Scalar(1));
//        Bitmap Bmp = Bitmap.createBitmap(result.cols(), result.rows(), Bitmap.Config.ARGB_8888);
//        Utils.matToBitmap(result,Bmp);

        List<MatOfPoint> contours  = new ArrayList<>();
        Mat hierarchy = new Mat();
        Imgproc.findContours(result, contours, hierarchy, Imgproc.RETR_EXTERNAL, Imgproc.CHAIN_APPROX_SIMPLE);
        //有了轮廓之后，为了方便我们先将轮廓给画出来，这里的resultMat其实就是srcMat，为了区分用了Mat resultMat = srcMat.clone();，
        // 下面代码的意思是，把contours轮廓列表中的所有轮廓(-1表示所有轮廓)在，resultMat上画用黑色(new Scalar(0, 0, 0))粗细为10的线条画出来。
        if (contours.isEmpty()){
            return null;
        }
        Mat resultMat = resultG.clone();

        double arcLength=0;
        int index=0;
        for (int i = 0; i < contours.size(); i++) {
            MatOfPoint2f source = new MatOfPoint2f();
            source.fromList(contours.get(i).toList());
            if (Imgproc.arcLength(source, true)>arcLength){
                arcLength=Imgproc.arcLength(source, true);
                index=i;
            }

        }
        MatOfPoint matOfPoint = contours.get(index);
        MatOfPoint2f tempMat=new MatOfPoint2f();
        Imgproc.approxPolyDP(new MatOfPoint2f(matOfPoint.toArray()), tempMat, Imgproc.arcLength(new MatOfPoint2f(matOfPoint.toArray()), true)*0.04, true);
        Point[] points = tempMat.toArray();
        if (points.length!=4){
            return null;
        }
        List<MatOfPoint> matOfPoints  = new ArrayList<>();
        matOfPoints.add(new MatOfPoint(tempMat.toArray()));

        Imgproc.drawContours(resultMat, matOfPoints, -1, new Scalar(0, 0, 255), 4);

        Bitmap resultBmp = Bitmap.createBitmap(resultMat.cols(), resultMat.rows(), Bitmap.Config.ARGB_8888);
        Utils.matToBitmap(resultMat,resultBmp);

        return resultBmp;

    }

三.效果

没办法传视频。https://github.com/jzqCode/OpenCvDemo

111.jpg