Merge pull request #28907 from chacha21:more_autobuffer

More use of AutoBuffer #28907

When possible, AutoBuffer should be faster than std::vector<>, and should not be worse if it requires a heap allocation rather than a stack allocation.

### 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
- [X] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [X] 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

modules/features2d/src/blobdetector.cpp

@@ -332,11 +332,13 @@ void SimpleBlobDetectorImpl::findBlobs(InputArray _image, InputArray _binaryImag
 
         //compute blob radius
         {
-            std::vector<double> dists;
-            for (size_t pointIdx = 0; pointIdx < contours[contourIdx].size(); pointIdx++)
+            const std::vector<cv::Point>& contour = contours[contourIdx];
+            const size_t contourSize = contour.size();
+            AutoBuffer<double> dists(contourSize);
+            for (size_t pointIdx = 0; pointIdx < contourSize; pointIdx++)
             {
-                Point2d pt = contours[contourIdx][pointIdx];
-                dists.push_back(norm(center.location - pt));
+                const Point2d& pt = contour[pointIdx];
+                dists[pointIdx] = norm(center.location - pt);
             }
             std::sort(dists.begin(), dists.end());
             center.radius = (dists[(dists.size() - 1) / 2] + dists[dists.size() / 2]) / 2.;

modules/features2d/src/keypoint.cpp

@@ -221,8 +221,8 @@ struct KeyPoint_LessThan
 void KeyPointsFilter::removeDuplicated( std::vector<KeyPoint>& keypoints )
 {
     int i, j, n = (int)keypoints.size();
-    std::vector<int> kpidx(n);
-    std::vector<uchar> mask(n, (uchar)1);
+    AutoBuffer<int> kpidx(n);
+    AutoBuffer<uchar> mask(n, (uchar)1);
 
     for( i = 0; i < n; i++ )
         kpidx[i] = i;

modules/features2d/src/orb.cpp

@@ -839,7 +839,7 @@ static void computeKeyPoints(const Mat& imagePyramid,
 #endif
 
     int i, nkeypoints, level, nlevels = (int)layerInfo.size();
-    std::vector<int> nfeaturesPerLevel(nlevels);
+    AutoBuffer<int> nfeaturesPerLevel(nlevels);
 
     // fill the extractors and descriptors for the corresponding scales
     float factor = (float)(1.0 / scaleFactor);
@@ -877,7 +877,7 @@ static void computeKeyPoints(const Mat& imagePyramid,
 
     allKeypoints.clear();
     std::vector<KeyPoint> keypoints;
-    std::vector<int> counters(nlevels);
+    AutoBuffer<int> counters(nlevels);
     keypoints.reserve(nfeaturesPerLevel[0]*2);
 
     for( level = 0; level < nlevels; level++ )

modules/features2d/src/sift.dispatch.cpp

@@ -225,7 +225,7 @@ void SIFT_Impl::buildGaussianPyramid( const Mat& base, std::vector<Mat>& pyr, in
 {
     CV_TRACE_FUNCTION();
 
-    std::vector<double> sig(nOctaveLayers + 3);
+    AutoBuffer<double> sig(nOctaveLayers + 3);
     pyr.resize(nOctaves*(nOctaveLayers + 3));
 
     // precompute Gaussian sigmas using the following formula: