I am working on a hand gesture recognition problem, when I try to extract the foreground bu subtraction of the still background the object appears to be transparent. Why? Please help and suggest any better approach to detection of foreground. Thank you.
I slightly changed the code i've found from some website that i do not remember anymore.
#include <opencv2/opencv.hpp>
#include <iostream>
#include <vector>
int main ()
{
cv::Mat frame;
cv::Mat back;
cv::Mat fore;
cv::VideoCapture cap (0);
cv::BackgroundSubtractorMOG2 bg;
bg.set ("nmixtures", 3);
bg.setBool("detectShadows", false);
std::vector < std::vector < cv::Point > >contours;
cv::namedWindow("Frame");
cv::namedWindow("Background");
for(;;)
{
cap >> frame;
bg.operator ()(frame,fore);
bg.getBackgroundImage(back);
cv::erode(fore,fore,cv::Mat());
cv::dilate(fore,fore,cv::Mat());
cv::findContours(fore,contours,CV_RETR_EXTERNAL,CV_CHAIN_APPROX_NONE);
cv::drawContours(frame,contours,-1,cv::Scalar(0,0,255),2);
cv::imshow("Frame",frame);
cv::imshow("Background",back);
if(cv::waitKey(30) >= 0) break;
}
return 0;
}
Asked: 2014-04-08 05:44:21 -0600
Seen: 416 times
Last updated: Aug 08 '14
>>> bgs = cv2.BackgroundSubtractorMOG2()
>>> help(bgs)
Are you using findContours or Canny? When you say transparent, do you mean nothing there or a ghostly set of lines?