C++ 视差图opencv
我正在尝试制作视差图。我看到了opencv'stereo_match.cpp'提供的示例代码,并编写了以下代码。但当我在校正和重新映射后显示左右图像时,图像是黑色的。谁能告诉我哪里做错了C++ 视差图opencv,c++,opencv,stereo-3d,C++,Opencv,Stereo 3d,我正在尝试制作视差图。我看到了opencv'stereo_match.cpp'提供的示例代码,并编写了以下代码。但当我在校正和重新映射后显示左右图像时,图像是黑色的。谁能告诉我哪里做错了 int main(int argc, char* argv[]) { Mat img1, img2, g1, g2; Mat disp, disp8; char* method ="SGBM"; float scale = 1.f; // don't know why /
int main(int argc, char* argv[])
{
Mat img1, img2, g1, g2;
Mat disp, disp8;
char* method ="SGBM";
float scale = 1.f; // don't know why
//img1 = imread(argv[1]);
//img2 = imread(argv[2]);
img1=imread("l1.jpg");
img2=imread("r1.jpg");
cvtColor(img1, g1, CV_BGR2GRAY);
cvtColor(img2, g2, CV_BGR2GRAY);
Size img_size = img1.size();
Rect roi1, roi2;
Mat Q;
/*reading parameters of ectrinssic & intrinssic file*/
const char* intrinsic_filename="intrinsics";
Mat img1r, img2r;
if( intrinsic_filename )
{
FileStorage fs("intrinsics.yml", cv::FileStorage::READ);
if(!fs.isOpened())
{
printf("Failed to open file %s\n");
return -1;
}
Mat M1, D1, M2, D2;
fs["M1"] >> M1;
fs["D1"] >> D1;
fs["M2"] >> M2;
fs["D2"] >> D2;
M1 *= scale;
M2 *= scale;
fs.open("extrinsics.yml", cv::FileStorage::READ);
if(!fs.isOpened())
{
printf("Failed to open file %s\n");
return -1;
}
Mat R, T, R1, P1, R2, P2;
fs["R"] >> R;
fs["T"] >> T;
stereoRectify( M1, D1, M2, D2, img_size, R, T, R1, R2, P1, P2, Q, CALIB_ZERO_DISPARITY, -1, img_size, &roi1, &roi2 );
Mat map11, map12, map21, map22;
initUndistortRectifyMap(M1, D1, R1, P1, img_size, CV_16SC2, map11, map12);
initUndistortRectifyMap(M2, D2, R2, P2, img_size, CV_16SC2, map21, map22);
remap(img1, img1r, map11, map12, INTER_LINEAR);
remap(img2, img2r, map21, map22, INTER_LINEAR);
// img1 = img1r;
// img2 = img2r;
imshow("left1", img1r);
imshow("left2", img2r);
}
}
}!![原始左图][3]您没有在以下位置切换cvtColor(…)上的输入/输出参数: g1和g2似乎是输入图像的灰度版本,但它们从未在下面的代码中使用。 你为什么不换个方向试试呢
g1=imread("l1.jpg");
g2=imread("r1.jpg");
cvtColor(g1, img1, CV_BGR2GRAY);
cvtColor(g2, img2, CV_BGR2GRAY);
OpenCV中的视差贴图比例在8位显示器上没有显示太多对比度。您需要重新映射图像范围以增加对比度 为了改进这个答案,以下是我在Python中使用的代码:
disp = cv2.normalize(sgbm.compute(ri_l, ri_r), alpha=0, beta=255, \
norm_type=cv2.NORM_MINMAX, dtype=cv2.CV_8U)
sgmb.compute()是视差贴图生成函数。如果“重新映射”仅创建灰色图像,则表示您的内在/外在值不正确
您必须返回到校准阶段,然后再次执行此操作,直到您从stereoCalibrate中发现错误<1。谢谢您的回答。但这没有任何改变。输出相同:(
disp = cv2.normalize(sgbm.compute(ri_l, ri_r), alpha=0, beta=255, \
norm_type=cv2.NORM_MINMAX, dtype=cv2.CV_8U)