检测到随机圆圈
我正在尝试检测圆圈,但检测到的圆圈根本不存在。我的代码如下。任何人都知道如何修改 DetectCircle() 方法以使检测更准确,请谢谢
void detectCircle( IplImage * img )
{
int edge_thresh = 1;
IplImage *gray = cvCreateImage( cvSize(img->width,img->height), 8, 1);
IplImage *edge = cvCreateImage( cvSize(img->width,img->height), 8, 1);
cvCvtColor(img, gray, CV_BGR2GRAY);
gray->origin = 1;
// color threshold
cvThreshold(gray,gray,100,255,CV_THRESH_BINARY);
// smooths out image
cvSmooth(gray, gray, CV_GAUSSIAN, 11, 11);
// get edges
cvCanny(gray, edge, (float)edge_thresh, (float)edge_thresh*3, 5);
// detects circle
CvSeq* circle = cvHoughCircles(edge, cstorage, CV_HOUGH_GRADIENT, 1,
edge->height/50, 5, 35);
// draws circle and its centerpoint
float* p = (float*)cvGetSeqElem( circle, 0 );
if( p==null ){ return;}
cvCircle( img, cvPoint(cvRound(p[0]),cvRound(p[1])), 3, CV_RGB(255,0,0), -1, 8, 0 );
cvCircle( img, cvPoint(cvRound(p[0]),cvRound(p[1])), cvRound(p[2]), CV_RGB(200,0,0), 1, 8, 0 );
cvShowImage ("Snooker", img );
}
I'm trying to detect circles but I am detecting circles that aren't even there. My code is below. Anyone know how to modify the DetectCircle() method to make the detection more accurate , please and thanks
void detectCircle( IplImage * img )
{
int edge_thresh = 1;
IplImage *gray = cvCreateImage( cvSize(img->width,img->height), 8, 1);
IplImage *edge = cvCreateImage( cvSize(img->width,img->height), 8, 1);
cvCvtColor(img, gray, CV_BGR2GRAY);
gray->origin = 1;
// color threshold
cvThreshold(gray,gray,100,255,CV_THRESH_BINARY);
// smooths out image
cvSmooth(gray, gray, CV_GAUSSIAN, 11, 11);
// get edges
cvCanny(gray, edge, (float)edge_thresh, (float)edge_thresh*3, 5);
// detects circle
CvSeq* circle = cvHoughCircles(edge, cstorage, CV_HOUGH_GRADIENT, 1,
edge->height/50, 5, 35);
// draws circle and its centerpoint
float* p = (float*)cvGetSeqElem( circle, 0 );
if( p==null ){ return;}
cvCircle( img, cvPoint(cvRound(p[0]),cvRound(p[1])), 3, CV_RGB(255,0,0), -1, 8, 0 );
cvCircle( img, cvPoint(cvRound(p[0]),cvRound(p[1])), cvRound(p[2]), CV_RGB(200,0,0), 1, 8, 0 );
cvShowImage ("Snooker", img );
}
如果你对这篇内容有疑问,欢迎到本站社区发帖提问 参与讨论,获取更多帮助,或者扫码二维码加入 Web 技术交流群。
绑定邮箱获取回复消息
由于您还没有绑定你的真实邮箱,如果其他用户或者作者回复了您的评论,将不能在第一时间通知您!
发布评论
评论(1)
cvHoughCircles 检测对我们来说不明显的圆圈。如果您知道斯诺克球的像素大小,您可以根据球的半径对其进行过滤。尝试在 cvHoughCircles 函数中设置 min_radius 和 max_radius 参数。
顺便说一句,一旦获得圆圈,您可以根据颜色对其进行过滤。如果圆圈主要是一种颜色,则它很可能是一个球,如果不是,则可能是误报。
编辑:“圆圈的颜色”是指圆圈边界内的像素
cvHoughCircles detects circles that arent obvious to us. If you know the pixel size of snooker balls you can filter them based on their radius. Try setting the min_radius and max_radius parameters in your cvHoughCircles function.
On a side note, once you get the circles, you can filter them based on color. If the circle is mostly one color, it has a good chance of being a ball, if it doenst its probably a false positive.
edit: by "circle's color" i mean the pixels inside the circle boundary