Reputation: 843
I'm trying to figure out how motion detection work in opencv.
I can see there the video analysis reference but I don't find enough information about how this is used.
I've also seen some people using absdiff I tried it like this, but It gives me an exception at memore errors
OpenCV Error: Sizes of input arguments do not match (The operation is neither 'a rray op array' (where arrays have the same size and the same number of channels) , nor 'array op scalar', nor 'scalar op array') in cv::arithm_op, file C:\builds \2_4_PackSlave-win32-vc12-shared\opencv\modules\core\src\arithm.cpp, line 1287
the code is
#include <iostream>
#include <sstream>
#include <string>
#include <opencv2/core/core.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <opencv2/highgui/highgui.hpp>
using namespace cv;
using namespace std;
int main()
{
//create matrix for storage
Mat image;
Mat image2;
Mat image3;
Mat image4;
//initialize capture
VideoCapture cap;
cap.open(0);
//create window to show image
namedWindow("window", 1);
while (1){
//copy webcam stream to image
cap >> image;
cap >> image2;
absdiff(image, image2, image3);
threshold(image3, image4, 128, 255, THRESH_BINARY);
//print image to screen
if (!image.empty()) {
imshow("window", image3);
}
//delay33ms
waitKey(10);
//
}
}
im obviously not using it right
Upvotes: 0
Views: 1646
Reputation: 2660
You need to confirm the VideoCapture was successful before using the images. Also, you want to test if the image was captured successfully before using it. Try this:
VideoCapture cap(0);
if(!cap.isOpened()) {
std::cerr << "Failed to open video capture" << std::endl;
return -1;
}
namedWindow("window");
while(true) {
cap >> image;
cap >> image2;
if(image.empty() || image2.empty()) {
std::cerr << "failed to capture images\n";
return -1;
}
absdiff(image, image2, image3);
threshold(image3, image4, 128, 255, THRESH_BINARY);
imshow("window", image);
int k = waitKey(30) & 0xff;
if('q' == k || 27 == k)
break;
}
Upvotes: 1