一种基于圆形的特殊标记识别

由于项目需要，我之前做了一个基于圆形图案的标记识别，其目的是实现单目相机对标记物的识别和定位。标记如下所示：

这个东西有四个圆形组成，打印出来后，测量其尺寸，就可以通过识别其图像位置，再使用P4P解算，就可以得到该平面相对于相机的三维方向和倾角。

首先是识别：

		ima = ardrone.getImage();
	SimpleBlobDetector::Params params;
	params.minThreshold = 40;
	params.maxThreshold = 160;
	params.thresholdStep = 5;
	params.minArea = 100;
	params.minConvexity = 0.7f;
	params.minInertiaRatio = 0.8f;
	params.maxArea = 8000;

	params.filterByCircularity = true;
	params.minCircularity = 0.5;
	params.maxCircularity = 1.5;
	params.maxInertiaRatio = 1;
	params.maxConvexity = 1;

	cv::Ptr<cv::SimpleBlobDetector> detector = cv::SimpleBlobDetector::create(params);
	cvtColor(ima, gray, CV_BGR2GRAY); // smooth it, otherwise a lot of false circles may be detected 
		//normalize(gray, gray, 0, 255, 32);
		//cout << gray.rows <<' '<<gray.cols<< endl;
		std::vector<KeyPoint> keypoints;

if (keypoints.size() != pointnum)continue;

		int fail = 0;
		for (int i = 1; i < pointnum; i++)
		{
			if (abs(keypoints[0].size - keypoints[i].size) / keypoints[0].size > 0.3)fail = 1;
		}
		if (fail == 1)continue;
		vector<vector<int>>dis;
		for (int i = 0; i < pointnum; i++)
		{
			vector<int> temp;
			for (int j = 0; j < pointnum; j++)
			{
				if (j == i)continue;
				temp.push_back(GetDis(keypoints[i].pt, keypoints[j].pt));
			}
			dis.push_back(temp);
		}
		int pa = -1, pb = -1, pc = -1, pd = -1;
		for (int i = 0; i < pointnum; i++)
		{
			int a = dis[i][0] - dis[i][1];
			int b = dis[i][2] - dis[i][1];
			int c = dis[i][0] - dis[i][2];
			if ((float)abs(a) / (float)dis[i][0] < 0.2 && (float)abs(c) / (float)dis[i][0] < 0.2)
				pa = i;
			else if ((float)abs(a) / (float)dis[i][0] <0.2 && (float)abs(c) / (float)dis[i][0] >0.5&&c<0)
				pb = i;
			else if ((float)abs(c) / (float)dis[i][0] <0.2 && (float)abs(a) / (float)dis[i][0] >0.5&&a<0)
				pb = i;
			else if ((float)abs(c) / (float)dis[i][0] > 0.5 && (float)abs(a) / (float)dis[i][0] > 0.5 && (float)abs(a) / (float)dis[i][1] < 0.2)
				pb = i;
			else if ((float)dis[i][1] / (float)dis[i][0] <0.8 && (float)dis[i][2] / (float)dis[i][0] <0.8 && (float)abs(b) / (float)dis[i][1] <0.2)
				pb = i;
		}
		if (pa < 0 || pb < 0)continue;
		drawArrow(ima, keypoints[pa].pt, keypoints[pb].pt, 10, 60, Scalar(0, 0, 255));
		putText(ima, "0", keypoints[pa].pt, 0, 1.0f, CV_RGB(255, 0, 0), 2);
		putText(ima, "1", keypoints[pb].pt, 0, 1.0f, CV_RGB(255, 0, 0), 2);

detector->detect(gray, keypoints);

这里使用了OPRENCV自带的斑点检测法进行检验，设定参数后，得到比较准确的斑点。

然后对斑点的相对位置进行检验，得到点的相对位置和整个图案的指向方向。

if (keypoints.size() != pointnum)continue;

		int fail = 0;
		for (int i = 1; i < pointnum; i++)
		{
			if (abs(keypoints[0].size - keypoints[i].size) / keypoints[0].size > 0.3)fail = 1;
		}
		if (fail == 1)continue;
		vector<vector<int>>dis;
		for (int i = 0; i < pointnum; i++)
		{
			vector<int> temp;
			for (int j = 0; j < pointnum; j++)
			{
				if (j == i)continue;
				temp.push_back(GetDis(keypoints[i].pt, keypoints[j].pt));
			}
			dis.push_back(temp);
		}
		int pa = -1, pb = -1, pc = -1, pd = -1;
		for (int i = 0; i < pointnum; i++)
		{
			int a = dis[i][0] - dis[i][1];
			int b = dis[i][2] - dis[i][1];
			int c = dis[i][0] - dis[i][2];
			if ((float)abs(a) / (float)dis[i][0] < 0.2 && (float)abs(c) / (float)dis[i][0] < 0.2)
				pa = i;
			else if ((float)abs(a) / (float)dis[i][0] <0.2 && (float)abs(c) / (float)dis[i][0] >0.5&&c<0)
				pb = i;
			else if ((float)abs(c) / (float)dis[i][0] <0.2 && (float)abs(a) / (float)dis[i][0] >0.5&&a<0)
				pb = i;
			else if ((float)abs(c) / (float)dis[i][0] > 0.5 && (float)abs(a) / (float)dis[i][0] > 0.5 && (float)abs(a) / (float)dis[i][1] < 0.2)
				pb = i;
			else if ((float)dis[i][1] / (float)dis[i][0] <0.8 && (float)dis[i][2] / (float)dis[i][0] <0.8 && (float)abs(b) / (float)dis[i][1] <0.2)
				pb = i;
		}
		if (pa < 0 || pb < 0)continue;
		drawArrow(ima, keypoints[pa].pt, keypoints[pb].pt, 10, 60, Scalar(0, 0, 255));
		putText(ima, "0", keypoints[pa].pt, 0, 1.0f, CV_RGB(255, 0, 0), 2);
		putText(ima, "1", keypoints[pb].pt, 0, 1.0f, CV_RGB(255, 0, 0), 2);

然后就是计算距离了，先构造四个点的相机坐标系坐标，然后在图上找到四个点的像素坐标，然后带入solvePnP计算，就可以得到一个平移和旋转矩阵，从平移和旋转矩阵中就可以计算出该平面相对与相机的位置了。代码如下：

	if (DIS)
		{
			for (int i = 0; i < pointnum; i++)
			{
				if (i != pa&&i != pb)
					if (LinePoint(keypoints[pa].pt, keypoints[pb].pt, keypoints[i].pt) > 0)
						pc = i;
					else pd = i;
			}
			if (pc < 0 || pd < 0)continue;
			putText(ima, "2", keypoints[pc].pt, 0, 1.0f, CV_RGB(255, 0, 0), 2);
			putText(ima, "3", keypoints[pd].pt, 0, 1.0f, CV_RGB(255, 0, 0), 2);
			vector<Point2f> centers;
			centers.push_back(keypoints[pa].pt);
			centers.push_back(keypoints[pb].pt);
			centers.push_back(keypoints[pc].pt);
			centers.push_back(keypoints[pd].pt);
			vector<Point2f> tempshape;
			tempshape.push_back(keypoints[pa].pt);
			tempshape.push_back(keypoints[pc].pt);
			tempshape.push_back(keypoints[pb].pt);
			tempshape.push_back(keypoints[pd].pt);
			double matchresult = matchShapes(myshape, tempshape, 1, 0);
			if (matchresult > 0.5)
			{
				cout << "Shape not match:" << matchresult << endl;
				continue;
			}
			solvePnP(realpos, centers, cameraMatrix, distCoeffs, rvecs, tvecs);
			Rodrigues(rvecs, R);
			Ang_X = asin(R.at<double>(1, 0) / cos(asin(-R.at<double>(2, 0)))) / pi * 180;
			Ang_Y = asin(-R.at<double>(2, 0)) / pi * 180;
			Ang_Z = asin(R.at<double>(2, 1) / cos(asin(-R.at<double>(2, 0)))) / pi * 180;

			X = R.at<double>(0, 0) *realpos[0].x + R.at<double>(0, 1)  * realpos[0].y + R.at<double>(0, 2)  * realpos[0].z + tvecs.at<double>(0, 0);
			Y = R.at<double>(1, 0) *realpos[0].x + R.at<double>(1, 1)  * realpos[0].y + R.at<double>(1, 2)  * realpos[0].z + tvecs.at<double>(1, 0);
			Z = R.at<double>(2, 0) *realpos[0].x + R.at<double>(2, 1)  * realpos[0].y + R.at<double>(2, 2)  * realpos[0].z + tvecs.at<double>(2, 0);
			putText(ima, "X:" + to_string(X), { 1, 50 }, 0, 1.0f, CV_RGB(255, 0, 0), 2);
			putText(ima, "Y:" + to_string(Y), { 1, 150 }, 0, 1.0f, CV_RGB(0, 255, 0), 2);
			putText(ima, "Z:" + to_string(Z), { 1, 250 }, 0, 1.0f, CV_RGB(0, 0, 255), 2);
			putText(ima, "Ang_X:" + to_string(Ang_X), { 300, 50 }, 0, 1.0f, CV_RGB(255, 0, 0), 2);
			putText(ima, "Ang_Y:" + to_string(Ang_Y), { 300, 150 }, 0, 1.0f, CV_RGB(0, 255, 0), 2);
			putText(ima, "Ang_Z:" + to_string(Ang_Z), { 300, 250 }, 0, 1.0f, CV_RGB(0, 0, 255), 2);
		}

这个代码是应用在了一个无人机上，所以图像获取部分等其他代码就不放了，但是核心原理都在上面了。

再放一下识别结果：