potok/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2026-07-30 07:43:03 +04:00
Code Packages Releases Wiki Activity

Merge pull request #27952 from DDmytro:ecc/template-mask-rework

Browse Source 
Add optional template mask for findTransformECC #27952

Supersedes #22997

**Summary**
Add optional template mask support to findTransformECC so that only pixels valid in both the template and the image are used in ECC. Backward compatibility is preserved (existing signatures unchanged; one new overload adds templateMask).

**Motivation**

- Real-world frames often contain moving foreground artifacts (e.g., a football over a static field). Masking the object in one frame only is insufficient because its position changes independently of the background. Since we don’t know the warp a priori, we can’t back-project a single mask across frames. The correct approach is to supply both masks and take their intersection.
- Templates may include uninformative/low-texture or noisy regions, or partial overlaps with other objects. Excluding such regions from the alignment improves robustness and convergence.

This PR completes and replaces https://github.com/opencv/opencv/pull/22997

### Pull Request Readiness Checklist
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [ ] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [ ] The feature is well documented and sample code can be built with the project CMake
This commit is contained in:
Dmytro Dadyka
2025-11-21 10:50:29 +02:00
committed by GitHub
parent 2cc5b69fd1
commit 6231b080ff
3 changed files with 137 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/video/src/ecc.cpp
+72 -25
View File
@@ -333,8 +333,15 @@ double cv::computeECC(InputArray templateImage, InputArray inputImage, InputArra
return templateImage_zeromean.dot(inputImage_zeromean) / (templateImagenorm * inputImagenorm);
}
double cv::findTransformECC(InputArray templateImage, InputArray inputImage, InputOutputArray warpMatrix,
int motionType, TermCriteria criteria, InputArray inputMask, int gaussFiltSize) {
double cv::findTransformECCWithMask( InputArray templateImage,
InputArray inputImage,
InputArray templateMask,
InputArray inputMask,
InputOutputArray warpMatrix,
int motionType,
TermCriteria criteria,
int gaussFiltSize) {
Mat src = templateImage.getMat(); // template image
Mat dst = inputImage.getMat(); // input image (to be warped)
Mat map = warpMatrix.getMat(); // warp (transformation)
@@ -416,7 +423,7 @@ double cv::findTransformECC(InputArray templateImage, InputArray inputImage, Inp
Ycoord.release();
const int channels = src.channels();
int type = CV_MAKETYPE(CV_32F, channels); // используем отдельно, если нужно явно
int type = CV_MAKETYPE(CV_32F, channels);
std::vector<cv::Mat> XgridCh(channels, Xgrid);
cv::merge(XgridCh, Xgrid);
@@ -430,27 +437,10 @@ double cv::findTransformECC(InputArray templateImage, InputArray inputImage, Inp
Mat imageWarped = Mat(hs, ws, type); // to store the warped zero-mean input image
Mat imageMask = Mat(hs, ws, CV_8U); // to store the final mask
Mat inputMaskMat = inputMask.getMat();
// to use it for mask warping
Mat preMask;
if (inputMask.empty())
preMask = Mat::ones(hd, wd, CV_8U);
else
threshold(inputMask, preMask, 0, 1, THRESH_BINARY);
// Gaussian filtering is optional
src.convertTo(templateFloat, templateFloat.type());
GaussianBlur(templateFloat, templateFloat, Size(gaussFiltSize, gaussFiltSize), 0, 0);
Mat preMaskFloat;
preMask.convertTo(preMaskFloat, type);
GaussianBlur(preMaskFloat, preMaskFloat, Size(gaussFiltSize, gaussFiltSize), 0, 0);
// Change threshold.
preMaskFloat *= (0.5 / 0.95);
// Rounding conversion.
preMaskFloat.convertTo(preMask, preMask.type());
preMask.convertTo(preMaskFloat, preMaskFloat.type());
dst.convertTo(imageFloat, imageFloat.type());
GaussianBlur(imageFloat, imageFloat, Size(gaussFiltSize, gaussFiltSize), 0, 0);
@@ -466,12 +456,48 @@ double cv::findTransformECC(InputArray templateImage, InputArray inputImage, Inp
filter2D(imageFloat, gradientX, -1, dx);
filter2D(imageFloat, gradientY, -1, dx.t());
cv::Mat preMaskFloatNCh;
std::vector<cv::Mat> maskChannels(gradientX.channels(), preMaskFloat);
cv::merge(maskChannels, preMaskFloatNCh);
// To use in mask warping
Mat templtMask;
if(templateMask.empty())
{
templtMask = Mat::ones(hs, ws, CV_8U);
}
else
{
threshold(templateMask, templtMask, 0, 1, THRESH_BINARY);
templtMask.convertTo(templtMask, CV_32F);
GaussianBlur(templtMask, templtMask, Size(gaussFiltSize, gaussFiltSize), 0, 0);
templtMask *= (0.5/0.95);
templtMask.convertTo(templtMask, CV_8U);
}
gradientX = gradientX.mul(preMaskFloatNCh);
gradientY = gradientY.mul(preMaskFloatNCh);
//to use it for mask warping
Mat preMask;
if(inputMask.empty())
{
preMask = Mat::ones(hd, wd, CV_8U);
}
else
{
Mat preMaskFloat;
threshold(inputMask, preMask, 0, 1, THRESH_BINARY);
preMask.convertTo(preMaskFloat, CV_32F);
GaussianBlur(preMaskFloat, preMaskFloat, Size(gaussFiltSize, gaussFiltSize), 0, 0);
// Change threshold.
preMaskFloat *= (0.5/0.95);
// Rounding conversion.
preMaskFloat.convertTo(preMask, CV_8U);
// If there's no template mask, we can apply image masks to gradients only once.
// Otherwise, we'll need to combine the template and image masks at each iteration.
if (templateMask.empty())
{
cv::Mat zeroMask = (preMask == 0);
gradientX.setTo(0, zeroMask);
gradientY.setTo(0, zeroMask);
}
}
// matrices needed for solving linear equation system for maximizing ECC
Mat jacobian = Mat(hs, ws * numberOfParameters, type);
@@ -505,6 +531,15 @@ double cv::findTransformECC(InputArray templateImage, InputArray inputImage, Inp
warpPerspective(preMask, imageMask, map, imageMask.size(), maskFlags);
}
if (!templateMask.empty())
{
cv::bitwise_and(imageMask, templtMask, imageMask);
cv::Mat zeroMask = (imageMask == 0);
gradientXWarped.setTo(0, zeroMask);
gradientYWarped.setTo(0, zeroMask);
}
Scalar imgMean, imgStd, tmpMean, tmpStd;
meanStdDev(imageWarped, imgMean, imgStd, imageMask);
meanStdDev(templateFloat, tmpMean, tmpStd, imageMask);
@@ -576,6 +611,18 @@ double cv::findTransformECC(InputArray templateImage, InputArray inputImage, Inp
return rho;
}
double cv::findTransformECC(InputArray templateImage,
InputArray inputImage,
InputOutputArray warpMatrix,
int motionType,
TermCriteria criteria,
InputArray inputMask,
int gaussFiltSize
) {
return findTransformECCWithMask(templateImage, inputImage, noArray(), inputMask,
warpMatrix, motionType, criteria, gaussFiltSize);
}
double cv::findTransformECC(InputArray templateImage, InputArray inputImage, InputOutputArray warpMatrix,
int motionType, TermCriteria criteria, InputArray inputMask) {
// Use default value of 5 for gaussFiltSize to maintain backward compatibility.