diff --git a/apps/version/opencv_version.cpp b/apps/version/opencv_version.cpp
index 8034f698c5..795c870fde 100644
--- a/apps/version/opencv_version.cpp
+++ b/apps/version/opencv_version.cpp
@@ -14,6 +14,11 @@
 #include <windows.h>
 #endif
 
+// defined in core/private.hpp
+namespace cv {
+CV_EXPORTS const char* currentParallelFramework();
+}
+
 static void dumpHWFeatures(bool showAll = false)
 {
     std::cout << "OpenCV's HW features list:" << std::endl;
@@ -34,6 +39,16 @@ static void dumpHWFeatures(bool showAll = false)
     std::cout << "Total available: " << count << std::endl;
 }
 
+static void dumpParallelFramework()
+{
+    const char* parallelFramework = cv::currentParallelFramework();
+    if (parallelFramework)
+    {
+        int threads = cv::getNumThreads();
+        std::cout << "Parallel framework: " << parallelFramework << " (nthreads=" << threads << ")" << std::endl;
+    }
+}
+
 int main(int argc, const char** argv)
 {
     CV_TRACE_FUNCTION();
@@ -47,6 +62,7 @@ int main(int argc, const char** argv)
         "{ verbose v      |      | show build configuration log }"
         "{ opencl         |      | show information about OpenCL (available platforms/devices, default selected device) }"
         "{ hw             |      | show detected HW features (see cv::checkHardwareSupport() function). Use --hw=0 to show available features only }"
+        "{ threads        |      | show configured parallel framework and number of active threads }"
     );
 
     if (parser.has("help"))
@@ -73,10 +89,17 @@ int main(int argc, const char** argv)
     {
         dumpHWFeatures(parser.get<bool>("hw"));
     }
+
+    if (parser.has("threads"))
+    {
+        dumpParallelFramework();
+    }
+
 #else
     std::cout << cv::getBuildInformation().c_str() << std::endl;
     cv::dumpOpenCLInformation();
     dumpHWFeatures();
+    dumpParallelFramework();
     MessageBoxA(NULL, "Check console window output", "OpenCV(" CV_VERSION ")", MB_ICONINFORMATION | MB_OK);
 #endif
 
diff --git a/cmake/OpenCVDetectCXXCompiler.cmake b/cmake/OpenCVDetectCXXCompiler.cmake
index cea12ad9c3..2cffad2729 100644
--- a/cmake/OpenCVDetectCXXCompiler.cmake
+++ b/cmake/OpenCVDetectCXXCompiler.cmake
@@ -215,7 +215,13 @@ if(NOT HAVE_CXX11)
   message(FATAL_ERROR "OpenCV 4.x requires C++11")
 endif()
 
-if((HAVE_CXX11
+set(__OPENCV_ENABLE_ATOMIC_LONG_LONG OFF)
+if(HAVE_CXX11 AND (X86 OR X86_64))
+  set(__OPENCV_ENABLE_ATOMIC_LONG_LONG ON)
+endif()
+option(OPENCV_ENABLE_ATOMIC_LONG_LONG "Enable C++ compiler support for atomic<long long>" ${__OPENCV_ENABLE_ATOMIC_LONG_LONG})
+
+if((HAVE_CXX11 AND OPENCV_ENABLE_ATOMIC_LONG_LONG
         AND NOT MSVC
         AND NOT (X86 OR X86_64)
     AND NOT OPENCV_SKIP_LIBATOMIC_COMPILER_CHECK)
@@ -226,9 +232,14 @@ if((HAVE_CXX11
     list(APPEND CMAKE_REQUIRED_LIBRARIES atomic)
     ocv_check_compiler_flag(CXX "" HAVE_CXX_ATOMICS_WITH_LIB "${OpenCV_SOURCE_DIR}/cmake/checks/atomic_check.cpp")
     if(HAVE_CXX_ATOMICS_WITH_LIB)
+      set(HAVE_ATOMIC_LONG_LONG ON)
       list(APPEND OPENCV_LINKER_LIBS atomic)
     else()
-      message(FATAL_ERROR "C++11 compiler must support std::atomic")
+      message(STATUS "Compiler doesn't support std::atomic<long long>")
     endif()
+  else()
+    set(HAVE_ATOMIC_LONG_LONG ON)
   endif()
+else(HAVE_CXX11 AND OPENCV_ENABLE_ATOMIC_LONG_LONG)
+  set(HAVE_ATOMIC_LONG_LONG ${OPENCV_ENABLE_ATOMIC_LONG_LONG})
 endif()
diff --git a/cmake/OpenCVModule.cmake b/cmake/OpenCVModule.cmake
index abb089d060..0ddb3f741e 100644
--- a/cmake/OpenCVModule.cmake
+++ b/cmake/OpenCVModule.cmake
@@ -1115,6 +1115,8 @@ macro(__ocv_parse_test_sources tests_type)
   unset(__currentvar)
 endmacro()
 
+ocv_check_environment_variables(OPENCV_TEST_EXTRA_CXX_FLAGS_Release)
+
 # this is a command for adding OpenCV performance tests to the module
 # ocv_add_perf_tests(<extra_dependencies>)
 function(ocv_add_perf_tests)
@@ -1279,6 +1281,10 @@ function(ocv_add_accuracy_tests)
         _ocv_add_precompiled_headers(${the_target})
       endif()
 
+      if(OPENCV_TEST_EXTRA_CXX_FLAGS_Release)
+        target_compile_options(${the_target} PRIVATE "$<$<CONFIG:Release>:${OPENCV_TEST_EXTRA_CXX_FLAGS_Release}>")
+      endif()
+
       ocv_add_test_from_target("${the_target}" "Accuracy" "${the_target}")
     else(OCV_DEPENDENCIES_FOUND)
       # TODO: warn about unsatisfied dependencies
diff --git a/modules/calib3d/include/opencv2/calib3d.hpp b/modules/calib3d/include/opencv2/calib3d.hpp
index f18f341e3c..c28d40a416 100644
--- a/modules/calib3d/include/opencv2/calib3d.hpp
+++ b/modules/calib3d/include/opencv2/calib3d.hpp
@@ -2138,6 +2138,7 @@ point localization, image resolution, and the image noise.
 @param confidence Parameter used for the RANSAC and LMedS methods only. It specifies a desirable level
 of confidence (probability) that the estimated matrix is correct.
 @param mask
+@param maxIters The maximum number of robust method iterations.
 
 The epipolar geometry is described by the following equation:
 
@@ -2171,6 +2172,11 @@ stereoRectifyUncalibrated to compute the rectification transformation. :
      findFundamentalMat(points1, points2, FM_RANSAC, 3, 0.99);
 @endcode
  */
+CV_EXPORTS_W Mat findFundamentalMat( InputArray points1, InputArray points2,
+                                     int method, double ransacReprojThreshold, double confidence,
+                                     int maxIters, OutputArray mask = noArray() );
+
+/** @overload */
 CV_EXPORTS_W Mat findFundamentalMat( InputArray points1, InputArray points2,
                                      int method = FM_RANSAC,
                                      double ransacReprojThreshold = 3., double confidence = 0.99,
diff --git a/modules/calib3d/src/fundam.cpp b/modules/calib3d/src/fundam.cpp
index 5363e949fd..3f19a8923a 100644
--- a/modules/calib3d/src/fundam.cpp
+++ b/modules/calib3d/src/fundam.cpp
@@ -809,7 +809,7 @@ public:
 
 cv::Mat cv::findFundamentalMat( InputArray _points1, InputArray _points2,
                                 int method, double ransacReprojThreshold, double confidence,
-                                OutputArray _mask )
+                                int maxIters, OutputArray _mask )
 {
     CV_INSTRUMENT_REGION();
 
@@ -861,7 +861,7 @@ cv::Mat cv::findFundamentalMat( InputArray _points1, InputArray _points2,
             confidence = 0.99;
 
         if( (method & ~3) == FM_RANSAC && npoints >= 15 )
-            result = createRANSACPointSetRegistrator(cb, 7, ransacReprojThreshold, confidence)->run(m1, m2, F, _mask);
+            result = createRANSACPointSetRegistrator(cb, 7, ransacReprojThreshold, confidence, maxIters)->run(m1, m2, F, _mask);
         else
             result = createLMeDSPointSetRegistrator(cb, 7, confidence)->run(m1, m2, F, _mask);
     }
@@ -872,11 +872,17 @@ cv::Mat cv::findFundamentalMat( InputArray _points1, InputArray _points2,
     return F;
 }
 
-cv::Mat cv::findFundamentalMat( InputArray _points1, InputArray _points2,
-                               OutputArray _mask, int method,
-                               double ransacReprojThreshold , double confidence)
+cv::Mat cv::findFundamentalMat( cv::InputArray points1, cv::InputArray points2,
+                                     int method, double ransacReprojThreshold, double confidence,
+                                     cv::OutputArray mask )
+{
+    return cv::findFundamentalMat(points1, points2, method, ransacReprojThreshold, confidence, 1000, mask);
+}
+
+cv::Mat cv::findFundamentalMat( cv::InputArray points1, cv::InputArray points2, cv::OutputArray mask,
+                                int method, double ransacReprojThreshold, double confidence )
 {
-    return cv::findFundamentalMat(_points1, _points2, method, ransacReprojThreshold, confidence, _mask);
+    return cv::findFundamentalMat(points1, points2, method, ransacReprojThreshold, confidence, 1000, mask);
 }
 
 
diff --git a/modules/core/CMakeLists.txt b/modules/core/CMakeLists.txt
index e4a63d9c2b..ee2c4b4b43 100644
--- a/modules/core/CMakeLists.txt
+++ b/modules/core/CMakeLists.txt
@@ -81,6 +81,23 @@ if(HAVE_MEMALIGN)
   ocv_append_source_file_compile_definitions(${CMAKE_CURRENT_SOURCE_DIR}/src/alloc.cpp "HAVE_MEMALIGN=1")
 endif()
 
+option(OPENCV_ENABLE_ALLOCATOR_STATS "Enable Allocator metrics" ON)
+
+if(NOT OPENCV_ENABLE_ALLOCATOR_STATS)
+  add_definitions(-DOPENCV_DISABLE_ALLOCATOR_STATS=1)
+else()
+  if(NOT DEFINED OPENCV_ALLOCATOR_STATS_COUNTER_TYPE)
+    if(HAVE_ATOMIC_LONG_LONG AND OPENCV_ENABLE_ATOMIC_LONG_LONG)
+      set(OPENCV_ALLOCATOR_STATS_COUNTER_TYPE "long long")
+    else()
+      set(OPENCV_ALLOCATOR_STATS_COUNTER_TYPE "int")
+    endif()
+  endif()
+  message(STATUS "Allocator metrics storage type: '${OPENCV_ALLOCATOR_STATS_COUNTER_TYPE}'")
+  add_definitions("-DOPENCV_ALLOCATOR_STATS_COUNTER_TYPE=${OPENCV_ALLOCATOR_STATS_COUNTER_TYPE}")
+endif()
+
+
 ocv_create_module(${extra_libs})
 
 ocv_target_link_libraries(${the_module} PRIVATE
diff --git a/modules/core/include/opencv2/core/hal/intrin_vsx.hpp b/modules/core/include/opencv2/core/hal/intrin_vsx.hpp
index 6e8b439182..e0f6cbf635 100644
--- a/modules/core/include/opencv2/core/hal/intrin_vsx.hpp
+++ b/modules/core/include/opencv2/core/hal/intrin_vsx.hpp
@@ -1564,81 +1564,10 @@ OPENCV_HAL_IMPL_VSX_TRANSPOSE4x4(v_uint32x4, vec_uint4)
 OPENCV_HAL_IMPL_VSX_TRANSPOSE4x4(v_int32x4, vec_int4)
 OPENCV_HAL_IMPL_VSX_TRANSPOSE4x4(v_float32x4, vec_float4)
 
-template<int i>
-inline v_int8x16 v_broadcast_element(v_int8x16 v)
-{
-    return v_int8x16(vec_perm(v.val, v.val, vec_splats((unsigned char)i)));
-}
-
-template<int i>
-inline v_uint8x16 v_broadcast_element(v_uint8x16 v)
-{
-    return v_uint8x16(vec_perm(v.val, v.val, vec_splats((unsigned char)i)));
-}
-
-template<int i>
-inline v_int16x8 v_broadcast_element(v_int16x8 v)
-{
-    unsigned char t0 = 2*i, t1 = 2*i + 1;
-    vec_uchar16 p = {t0, t1, t0, t1, t0, t1, t0, t1, t0, t1, t0, t1, t0, t1, t0, t1};
-    return v_int16x8(vec_perm(v.val, v.val, p));
-}
-
-template<int i>
-inline v_uint16x8 v_broadcast_element(v_uint16x8 v)
-{
-    unsigned char t0 = 2*i, t1 = 2*i + 1;
-    vec_uchar16 p = {t0, t1, t0, t1, t0, t1, t0, t1, t0, t1, t0, t1, t0, t1, t0, t1};
-    return v_uint16x8(vec_perm(v.val, v.val, p));
-}
-
-template<int i>
-inline v_int32x4 v_broadcast_element(v_int32x4 v)
-{
-    unsigned char t0 = 4*i, t1 = 4*i + 1, t2 = 4*i + 2, t3 = 4*i + 3;
-    vec_uchar16 p = {t0, t1, t2, t3, t0, t1, t2, t3, t0, t1, t2, t3, t0, t1, t2, t3};
-    return v_int32x4(vec_perm(v.val, v.val, p));
-}
+template<int i, typename Tvec>
+inline Tvec v_broadcast_element(const Tvec& v)
+{ return Tvec(vec_splat(v.val, i)); }
 
-template<int i>
-inline v_uint32x4 v_broadcast_element(v_uint32x4 v)
-{
-    unsigned char t0 = 4*i, t1 = 4*i + 1, t2 = 4*i + 2, t3 = 4*i + 3;
-    vec_uchar16 p = {t0, t1, t2, t3, t0, t1, t2, t3, t0, t1, t2, t3, t0, t1, t2, t3};
-    return v_uint32x4(vec_perm(v.val, v.val, p));
-}
-
-template<int i>
-inline v_int64x2 v_broadcast_element(v_int64x2 v)
-{
-    unsigned char t0 = 8*i, t1 = 8*i + 1, t2 = 8*i + 2, t3 = 8*i + 3, t4 = 8*i + 4, t5 = 8*i + 5, t6 = 8*i + 6, t7 = 8*i + 7;
-    vec_uchar16 p = {t0, t1, t2, t3, t4, t5, t6, t7, t0, t1, t2, t3, t4, t5, t6, t7};
-    return v_int64x2(vec_perm(v.val, v.val, p));
-}
-
-template<int i>
-inline v_uint64x2 v_broadcast_element(v_uint64x2 v)
-{
-    unsigned char t0 = 8*i, t1 = 8*i + 1, t2 = 8*i + 2, t3 = 8*i + 3, t4 = 8*i + 4, t5 = 8*i + 5, t6 = 8*i + 6, t7 = 8*i + 7;
-    vec_uchar16 p = {t0, t1, t2, t3, t4, t5, t6, t7, t0, t1, t2, t3, t4, t5, t6, t7};
-    return v_uint64x2(vec_perm(v.val, v.val, p));
-}
-
-template<int i>
-inline v_float32x4 v_broadcast_element(v_float32x4 v)
-{
-    unsigned char t0 = 4*i, t1 = 4*i + 1, t2 = 4*i + 2, t3 = 4*i + 3;
-    vec_uchar16 p = {t0, t1, t2, t3, t0, t1, t2, t3, t0, t1, t2, t3, t0, t1, t2, t3};
-    return v_float32x4(vec_perm(v.val, v.val, p));
-}
-
-template<int i>
-inline v_float64x2 v_broadcast_element(v_float64x2 v)
-{
-    unsigned char t0 = 8*i, t1 = 8*i + 1, t2 = 8*i + 2, t3 = 8*i + 3, t4 = 8*i + 4, t5 = 8*i + 5, t6 = 8*i + 6, t7 = 8*i + 7;
-    vec_uchar16 p = {t0, t1, t2, t3, t4, t5, t6, t7, t0, t1, t2, t3, t4, t5, t6, t7};
-    return v_float64x2(vec_perm(v.val, v.val, p));
-}
 
 CV_CPU_OPTIMIZATION_HAL_NAMESPACE_END
 
diff --git a/modules/core/include/opencv2/core/utils/allocator_stats.impl.hpp b/modules/core/include/opencv2/core/utils/allocator_stats.impl.hpp
index b77493d010..61fcf15977 100644
--- a/modules/core/include/opencv2/core/utils/allocator_stats.impl.hpp
+++ b/modules/core/include/opencv2/core/utils/allocator_stats.impl.hpp
@@ -11,32 +11,55 @@
 #include <atomic>
 #endif
 
+//#define OPENCV_DISABLE_ALLOCATOR_STATS
+
 namespace cv { namespace utils {
 
+#ifndef OPENCV_ALLOCATOR_STATS_COUNTER_TYPE
+#if defined(__GNUC__) && (\
+        (defined(__SIZEOF_POINTER__) && __SIZEOF_POINTER__ == 4) || \
+        (defined(__GCC_HAVE_SYNC_COMPARE_AND_SWAP_4) && !defined(__GCC_HAVE_SYNC_COMPARE_AND_SWAP_8)) \
+    )
+#define OPENCV_ALLOCATOR_STATS_COUNTER_TYPE int
+#endif
+#endif
+
+#ifndef OPENCV_ALLOCATOR_STATS_COUNTER_TYPE
+#define OPENCV_ALLOCATOR_STATS_COUNTER_TYPE long long
+#endif
+
 #ifdef CV__ALLOCATOR_STATS_LOG
 namespace {
 #endif
 
 class AllocatorStatistics : public AllocatorStatisticsInterface
 {
-protected:
-#ifdef CV_CXX11
-    std::atomic<long long> curr, total, total_allocs, peak;
-#else
-    volatile long long curr, total, total_allocs, peak;  // overflow is possible, CV_XADD operates with 'int' only
-#endif
+#ifdef OPENCV_DISABLE_ALLOCATOR_STATS
 
 public:
-    AllocatorStatistics()
-#ifndef CV_CXX11
-        : curr(0), total(0), total_allocs(0), peak(0)
-#endif
-    {}
+    AllocatorStatistics() {}
     ~AllocatorStatistics() CV_OVERRIDE {}
 
-    // AllocatorStatisticsInterface
+    uint64_t getCurrentUsage() const CV_OVERRIDE { return 0; }
+    uint64_t getTotalUsage() const CV_OVERRIDE { return 0; }
+    uint64_t getNumberOfAllocations() const CV_OVERRIDE { return 0; }
+    uint64_t getPeakUsage() const CV_OVERRIDE { return 0; }
+
+    /** set peak usage = current usage */
+    void resetPeakUsage() CV_OVERRIDE {};
+
+    void onAllocate(size_t /*sz*/) {}
+    void onFree(size_t /*sz*/) {}
+
+#elif defined(CV_CXX11)
+
+protected:
+    typedef OPENCV_ALLOCATOR_STATS_COUNTER_TYPE counter_t;
+    std::atomic<counter_t> curr, total, total_allocs, peak;
+public:
+    AllocatorStatistics() {}
+    ~AllocatorStatistics() CV_OVERRIDE {}
 
-#ifdef CV_CXX11
     uint64_t getCurrentUsage() const CV_OVERRIDE { return (uint64_t)curr.load(); }
     uint64_t getTotalUsage() const CV_OVERRIDE { return (uint64_t)total.load(); }
     uint64_t getNumberOfAllocations() const CV_OVERRIDE { return (uint64_t)total_allocs.load(); }
@@ -52,7 +75,7 @@ public:
         CV__ALLOCATOR_STATS_LOG(cv::format("allocate: %lld (curr=%lld)", (long long int)sz, (long long int)curr.load()));
 #endif
 
-        long long new_curr = curr.fetch_add((long long)sz) + (long long)sz;
+        counter_t new_curr = curr.fetch_add((counter_t)sz) + (counter_t)sz;
 
         // peak = std::max((uint64_t)peak, new_curr);
         auto prev_peak = peak.load();
@@ -63,7 +86,7 @@ public:
         }
         // end of peak = max(...)
 
-        total += (long long)sz;
+        total += (counter_t)sz;
         total_allocs++;
     }
     void onFree(size_t sz)
@@ -71,10 +94,20 @@ public:
 #ifdef CV__ALLOCATOR_STATS_LOG
         CV__ALLOCATOR_STATS_LOG(cv::format("free: %lld (curr=%lld)", (long long int)sz, (long long int)curr.load()));
 #endif
-        curr -= (long long)sz;
+        curr -= (counter_t)sz;
     }
 
-#else
+#else  // non C++11
+
+protected:
+    typedef OPENCV_ALLOCATOR_STATS_COUNTER_TYPE counter_t;
+    volatile counter_t curr, total, total_allocs, peak;  // overflow is possible, CV_XADD operates with 'int' only
+public:
+    AllocatorStatistics()
+        : curr(0), total(0), total_allocs(0), peak(0)
+    {}
+    ~AllocatorStatistics() CV_OVERRIDE {}
+
     uint64_t getCurrentUsage() const CV_OVERRIDE { return (uint64_t)curr; }
     uint64_t getTotalUsage() const CV_OVERRIDE { return (uint64_t)total; }
     uint64_t getNumberOfAllocations() const CV_OVERRIDE { return (uint64_t)total_allocs; }
@@ -89,21 +122,21 @@ public:
         CV__ALLOCATOR_STATS_LOG(cv::format("allocate: %lld (curr=%lld)", (long long int)sz, (long long int)curr));
 #endif
 
-        uint64_t new_curr = (uint64_t)CV_XADD(&curr, (uint64_t)sz) + sz;
+        counter_t new_curr = (counter_t)CV_XADD(&curr, (counter_t)sz) + (counter_t)sz;
 
-        peak = std::max((uint64_t)peak, new_curr);  // non-thread safe
+        peak = std::max((counter_t)peak, new_curr);  // non-thread safe
 
         //CV_XADD(&total, (uint64_t)sz);  // overflow with int, non-reliable...
         total += sz;
 
-        CV_XADD(&total_allocs, (uint64_t)1);
+        CV_XADD(&total_allocs, (counter_t)1);
     }
     void onFree(size_t sz)
     {
 #ifdef CV__ALLOCATOR_STATS_LOG
         CV__ALLOCATOR_STATS_LOG(cv::format("free: %lld (curr=%lld)", (long long int)sz, (long long int)curr));
 #endif
-        CV_XADD(&curr, (uint64_t)-sz);
+        CV_XADD(&curr, (counter_t)-sz);
     }
 #endif
 };
diff --git a/modules/core/include/opencv2/core/utils/buffer_area.private.hpp b/modules/core/include/opencv2/core/utils/buffer_area.private.hpp
index ab19da6416..f6bb93e088 100644
--- a/modules/core/include/opencv2/core/utils/buffer_area.private.hpp
+++ b/modules/core/include/opencv2/core/utils/buffer_area.private.hpp
@@ -72,6 +72,10 @@ public:
         CV_Assert(alignment % sizeof(T) == 0);
         CV_Assert((alignment & (alignment - 1)) == 0);
         allocate_((void**)(&ptr), static_cast<ushort>(sizeof(T)), count, alignment);
+#ifndef OPENCV_ENABLE_MEMORY_SANITIZER
+        if (safe)
+#endif
+            CV_Assert(ptr != NULL);
     }
 
     /** @brief Fill one of buffers with zeroes
@@ -118,9 +122,11 @@ private:
 private:
     class Block;
     std::vector<Block> blocks;
+#ifndef OPENCV_ENABLE_MEMORY_SANITIZER
     void * oneBuf;
     size_t totalSize;
     const bool safe;
+#endif
 };
 
 //! @}
diff --git a/modules/core/src/buffer_area.cpp b/modules/core/src/buffer_area.cpp
index b6bb321bba..2fe9d782ae 100644
--- a/modules/core/src/buffer_area.cpp
+++ b/modules/core/src/buffer_area.cpp
@@ -5,14 +5,10 @@
 #include "opencv2/core/utils/buffer_area.private.hpp"
 #include "opencv2/core/utils/configuration.private.hpp"
 
-#ifdef OPENCV_ENABLE_MEMORY_SANITIZER
-#define BUFFER_AREA_DEFAULT_MODE true
-#else
-#define BUFFER_AREA_DEFAULT_MODE false
-#endif
-
+#ifndef OPENCV_ENABLE_MEMORY_SANITIZER
 static bool CV_BUFFER_AREA_OVERRIDE_SAFE_MODE =
-    cv::utils::getConfigurationParameterBool("OPENCV_BUFFER_AREA_ALWAYS_SAFE", BUFFER_AREA_DEFAULT_MODE);
+    cv::utils::getConfigurationParameterBool("OPENCV_BUFFER_AREA_ALWAYS_SAFE", false);
+#endif
 
 namespace cv { namespace utils {
 
@@ -58,6 +54,7 @@ public:
             *ptr = raw_mem;
         }
     }
+#ifndef OPENCV_ENABLE_MEMORY_SANITIZER
     void * fast_allocate(void * buf) const
     {
         CV_Assert(ptr && *ptr == NULL);
@@ -66,6 +63,7 @@ public:
         *ptr = buf;
         return static_cast<void*>(static_cast<uchar*>(*ptr) + type_size * count);
     }
+#endif
     bool operator==(void **other) const
     {
         CV_Assert(ptr && other);
@@ -86,12 +84,20 @@ private:
 
 //==================================================================================================
 
+#ifndef OPENCV_ENABLE_MEMORY_SANITIZER
 BufferArea::BufferArea(bool safe_) :
     oneBuf(0),
     totalSize(0),
     safe(safe_ || CV_BUFFER_AREA_OVERRIDE_SAFE_MODE)
 {
+    // nothing
 }
+#else
+BufferArea::BufferArea(bool safe_)
+{
+    CV_UNUSED(safe_);
+}
+#endif
 
 BufferArea::~BufferArea()
 {
@@ -101,10 +107,16 @@ BufferArea::~BufferArea()
 void BufferArea::allocate_(void **ptr, ushort type_size, size_t count, ushort alignment)
 {
     blocks.push_back(Block(ptr, type_size, count, alignment));
-    if (safe)
-        blocks.back().real_allocate();
-    else
+#ifndef OPENCV_ENABLE_MEMORY_SANITIZER
+    if (!safe)
+    {
         totalSize += blocks.back().getByteCount();
+    }
+    else
+#endif
+    {
+        blocks.back().real_allocate();
+    }
 }
 
 void BufferArea::zeroFill_(void **ptr)
@@ -129,6 +141,7 @@ void BufferArea::zeroFill()
 
 void BufferArea::commit()
 {
+#ifndef OPENCV_ENABLE_MEMORY_SANITIZER
     if (!safe)
     {
         CV_Assert(totalSize > 0);
@@ -141,6 +154,7 @@ void BufferArea::commit()
             ptr = i->fast_allocate(ptr);
         }
     }
+#endif
 }
 
 void BufferArea::release()
@@ -150,11 +164,13 @@ void BufferArea::release()
         i->cleanup();
     }
     blocks.clear();
+#ifndef OPENCV_ENABLE_MEMORY_SANITIZER
     if (oneBuf)
     {
         fastFree(oneBuf);
         oneBuf = 0;
     }
+#endif
 }
 
 //==================================================================================================
diff --git a/modules/core/src/parallel.cpp b/modules/core/src/parallel.cpp
index 3f5a1d35bc..2fcf491ba6 100644
--- a/modules/core/src/parallel.cpp
+++ b/modules/core/src/parallel.cpp
@@ -638,9 +638,9 @@ int getNumThreads(void)
 
 #elif defined HAVE_CONCURRENCY
 
-    return 1 + (pplScheduler == 0
+    return (pplScheduler == 0)
         ? Concurrency::CurrentScheduler::Get()->GetNumberOfVirtualProcessors()
-        : pplScheduler->GetNumberOfVirtualProcessors());
+        : (1 + pplScheduler->GetNumberOfVirtualProcessors());
 
 #elif defined HAVE_PTHREADS_PF
 
diff --git a/modules/dnn/misc/python/pyopencv_dnn.hpp b/modules/dnn/misc/python/pyopencv_dnn.hpp
index 69c14240c3..d729cd8b97 100644
--- a/modules/dnn/misc/python/pyopencv_dnn.hpp
+++ b/modules/dnn/misc/python/pyopencv_dnn.hpp
@@ -160,12 +160,13 @@ public:
         PyObject* args = pyopencv_from(inputs);
         PyObject* res = PyObject_CallMethodObjArgs(o, PyString_FromString("forward"), args, NULL);
         Py_DECREF(args);
-        PyGILState_Release(gstate);
         if (!res)
             CV_Error(Error::StsNotImplemented, "Failed to call \"forward\" method");
 
         std::vector<Mat> pyOutputs;
         CV_Assert(pyopencv_to(res, pyOutputs, ArgInfo("", 0)));
+        Py_DECREF(res);
+        PyGILState_Release(gstate);
 
         CV_Assert(pyOutputs.size() == outputs.size());
         for (size_t i = 0; i < outputs.size(); ++i)
diff --git a/modules/dnn/src/dnn.cpp b/modules/dnn/src/dnn.cpp
index 96c2e0a48b..542744176d 100644
--- a/modules/dnn/src/dnn.cpp
+++ b/modules/dnn/src/dnn.cpp
@@ -114,7 +114,7 @@ public:
     {
 #if INF_ENGINE_VER_MAJOR_GE(INF_ENGINE_RELEASE_2019R3)
         // Lightweight detection
-        const std::vector<std::string> devices = getCore().GetAvailableDevices();
+        const std::vector<std::string> devices = getCore("").GetAvailableDevices();
         for (std::vector<std::string>::const_iterator i = devices.begin(); i != devices.end(); ++i)
         {
             if (std::string::npos != i->find("MYRIAD") && target == DNN_TARGET_MYRIAD)
@@ -3557,7 +3557,7 @@ Net Net::readFromModelOptimizer(const String& xml, const String& bin)
 
     InferenceEngine::CNNNetwork ieNet = reader.getNetwork();
 #else
-    InferenceEngine::Core& ie = getCore();
+    InferenceEngine::Core& ie = getCore("");
     InferenceEngine::CNNNetwork ieNet = ie.ReadNetwork(xml, bin);
 #endif
 
@@ -3606,7 +3606,7 @@ Net Net::readFromModelOptimizer(
 
     InferenceEngine::CNNNetwork ieNet = reader.getNetwork();
 #else
-    InferenceEngine::Core& ie = getCore();
+    InferenceEngine::Core& ie = getCore("");
 
     std::string model; model.assign((char*)bufferModelConfigPtr, bufferModelConfigSize);
 
diff --git a/modules/dnn/src/ie_ngraph.cpp b/modules/dnn/src/ie_ngraph.cpp
index 55ba9377a0..f0975d05a0 100644
--- a/modules/dnn/src/ie_ngraph.cpp
+++ b/modules/dnn/src/ie_ngraph.cpp
@@ -524,7 +524,7 @@ void InfEngineNgraphNet::initPlugin(InferenceEngine::CNNNetwork& net)
     try
     {
         AutoLock lock(getInitializationMutex());
-        InferenceEngine::Core& ie = getCore();
+        InferenceEngine::Core& ie = getCore(device_name);
         {
             isInit = true;
             std::vector<std::string> candidates;
diff --git a/modules/dnn/src/onnx/onnx_importer.cpp b/modules/dnn/src/onnx/onnx_importer.cpp
index 714d4bfd9a..09900556f7 100644
--- a/modules/dnn/src/onnx/onnx_importer.cpp
+++ b/modules/dnn/src/onnx/onnx_importer.cpp
@@ -431,9 +431,20 @@ void ONNXImporter::populateNet(Net dstNet)
         {
             bool isSub = layer_type == "Sub";
             CV_CheckEQ(node_proto.input_size(), 2, "");
-            if (layer_id.find(node_proto.input(1)) == layer_id.end())
+            bool is_const_0 = layer_id.find(node_proto.input(0)) == layer_id.end();
+            bool is_const_1 = layer_id.find(node_proto.input(1)) == layer_id.end();
+            if (is_const_0 && is_const_1)
             {
-                Mat blob = getBlob(node_proto, constBlobs, 1);
+                Mat blob_0 = getBlob(node_proto, constBlobs, 0);
+                Mat blob_1 = getBlob(node_proto, constBlobs, 1);
+                CV_Assert(blob_0.size == blob_1.size);
+                Mat output = isSub ? (blob_0 - blob_1) : (blob_0 + blob_1);
+                constBlobs.insert(std::make_pair(layerParams.name, output));
+                continue;
+            }
+            else if (is_const_0 || is_const_1)
+            {
+                Mat blob = getBlob(node_proto, constBlobs, is_const_0 ? 0 : 1);
                 blob = blob.reshape(1, 1);
                 if (blob.total() == 1) {
                     layerParams.type = "Power";
@@ -808,6 +819,21 @@ void ONNXImporter::populateNet(Net dstNet)
             layerParams.set("end_axis", axis);
             layerParams.type = "Flatten";
         }
+        else if (layer_type == "Flatten")
+        {
+            CV_CheckEQ(node_proto.input_size(), 1, "");
+            if (constBlobs.find(node_proto.input(0)) != constBlobs.end())
+            {
+                Mat input = getBlob(node_proto, constBlobs, 0);
+                int axis = clamp(layerParams.get<int>("axis", 1), input.dims);
+
+                std::vector<int> out_size(&input.size[0], &input.size[0] + axis);
+                out_size.push_back(input.total(axis));
+                Mat output = input.reshape(1, out_size);
+                constBlobs.insert(std::make_pair(layerParams.name, output));
+                continue;
+            }
+        }
         else if (layer_type == "Unsqueeze")
         {
             CV_Assert(node_proto.input_size() == 1);
@@ -896,6 +922,31 @@ void ONNXImporter::populateNet(Net dstNet)
             constBlobs.insert(std::make_pair(layerParams.name, shapeMat));
             continue;
         }
+        else if (layer_type == "Cast")
+        {
+            if (constBlobs.find(node_proto.input(0)) != constBlobs.end())
+            {
+                Mat blob = getBlob(node_proto, constBlobs, 0);
+                int type;
+                switch (layerParams.get<int>("to"))
+                {
+                    case opencv_onnx::TensorProto_DataType_FLOAT:   type = CV_32F; break;
+                    case opencv_onnx::TensorProto_DataType_UINT8:   type = CV_8U; break;
+                    case opencv_onnx::TensorProto_DataType_UINT16:  type = CV_16U; break;
+                    case opencv_onnx::TensorProto_DataType_FLOAT16: type = CV_16S; break;
+                    case opencv_onnx::TensorProto_DataType_INT8:
+                    case opencv_onnx::TensorProto_DataType_INT16:
+                    case opencv_onnx::TensorProto_DataType_INT32:
+                    case opencv_onnx::TensorProto_DataType_INT64:   type = CV_32S; break;
+                    default: type = blob.type();
+                }
+                blob.convertTo(blob, type);
+                constBlobs.insert(std::make_pair(layerParams.name, blob));
+                continue;
+            }
+            else
+                layerParams.type = "Identity";
+        }
         else if (layer_type == "Gather")
         {
             CV_Assert(node_proto.input_size() == 2);
diff --git a/modules/dnn/src/op_inf_engine.cpp b/modules/dnn/src/op_inf_engine.cpp
index c71758ad70..f48631579a 100644
--- a/modules/dnn/src/op_inf_engine.cpp
+++ b/modules/dnn/src/op_inf_engine.cpp
@@ -604,18 +604,31 @@ static bool init_IE_plugins()
     (void)init_core->GetAvailableDevices();
     return true;
 }
-static InferenceEngine::Core& create_IE_Core_instance()
+static InferenceEngine::Core& retrieveIECore(const std::string& id, std::map<std::string, std::shared_ptr<InferenceEngine::Core> >& cores)
 {
-    static InferenceEngine::Core core;
-    return core;
+    AutoLock lock(getInitializationMutex());
+    std::map<std::string, std::shared_ptr<InferenceEngine::Core> >::iterator i = cores.find(id);
+    if (i == cores.end())
+    {
+        std::shared_ptr<InferenceEngine::Core> core = std::make_shared<InferenceEngine::Core>();
+        cores[id] = core;
+        return *core.get();
+    }
+    return *(i->second).get();
 }
-static InferenceEngine::Core& create_IE_Core_pointer()
+static InferenceEngine::Core& create_IE_Core_instance(const std::string& id)
+{
+    static std::map<std::string, std::shared_ptr<InferenceEngine::Core> > cores;
+    return retrieveIECore(id, cores);
+}
+static InferenceEngine::Core& create_IE_Core_pointer(const std::string& id)
 {
     // load and hold IE plugins
-    static InferenceEngine::Core* core = new InferenceEngine::Core();  // 'delete' is never called
-    return *core;
+    static std::map<std::string, std::shared_ptr<InferenceEngine::Core> >* cores =
+            new std::map<std::string, std::shared_ptr<InferenceEngine::Core> >();
+    return retrieveIECore(id, *cores);
 }
-InferenceEngine::Core& getCore()
+InferenceEngine::Core& getCore(const std::string& id)
 {
     // to make happy memory leak tools use:
     // - OPENCV_DNN_INFERENCE_ENGINE_HOLD_PLUGINS=0
@@ -631,9 +644,10 @@ InferenceEngine::Core& getCore()
                 false
 #endif
             );
-    static InferenceEngine::Core& core = param_DNN_INFERENCE_ENGINE_CORE_LIFETIME_WORKAROUND
-            ? create_IE_Core_pointer()
-            : create_IE_Core_instance();
+
+    InferenceEngine::Core& core = param_DNN_INFERENCE_ENGINE_CORE_LIFETIME_WORKAROUND
+            ? create_IE_Core_pointer(id)
+            : create_IE_Core_instance(id);
     return core;
 }
 #endif
@@ -641,9 +655,10 @@ InferenceEngine::Core& getCore()
 #if !defined(OPENCV_DNN_IE_VPU_TYPE_DEFAULT)
 static bool detectMyriadX_()
 {
+    AutoLock lock(getInitializationMutex());
 #if INF_ENGINE_VER_MAJOR_GE(INF_ENGINE_RELEASE_2019R3)
     // Lightweight detection
-    InferenceEngine::Core& ie = getCore();
+    InferenceEngine::Core& ie = getCore("MYRIAD");
     const std::vector<std::string> devices = ie.GetAvailableDevices();
     for (std::vector<std::string>::const_iterator i = devices.begin(); i != devices.end(); ++i)
     {
@@ -687,7 +702,6 @@ static bool detectMyriadX_()
 #if INF_ENGINE_VER_MAJOR_LE(INF_ENGINE_RELEASE_2019R1)
     InferenceEngine::InferenceEnginePluginPtr enginePtr;
     {
-        AutoLock lock(getInitializationMutex());
         auto& sharedPlugins = getSharedPlugins();
         auto pluginIt = sharedPlugins.find("MYRIAD");
         if (pluginIt != sharedPlugins.end()) {
@@ -706,9 +720,9 @@ static bool detectMyriadX_()
     try
     {
 #if INF_ENGINE_VER_MAJOR_LE(INF_ENGINE_RELEASE_2019R3)
-        auto netExec = getCore().LoadNetwork(cnn, "MYRIAD", {{"VPU_PLATFORM", "VPU_2480"}});
+        auto netExec = getCore("MYRIAD").LoadNetwork(cnn, "MYRIAD", {{"VPU_PLATFORM", "VPU_2480"}});
 #else
-        auto netExec = getCore().LoadNetwork(cnn, "MYRIAD", {{"VPU_MYRIAD_PLATFORM", "VPU_MYRIAD_2480"}});
+        auto netExec = getCore("MYRIAD").LoadNetwork(cnn, "MYRIAD", {{"VPU_MYRIAD_PLATFORM", "VPU_MYRIAD_2480"}});
 #endif
 #endif
         auto infRequest = netExec.CreateInferRequest();
@@ -739,7 +753,7 @@ void InfEngineBackendNet::initPlugin(InferenceEngine::CNNNetwork& net)
         }
         else
 #else
-        InferenceEngine::Core& ie = getCore();
+        InferenceEngine::Core& ie = getCore(device_name);
 #endif
         {
 #if INF_ENGINE_VER_MAJOR_LE(INF_ENGINE_RELEASE_2019R1)
@@ -1124,7 +1138,7 @@ void resetMyriadDevice()
     getSharedPlugins().erase("MYRIAD");
 #else
     // Unregister both "MYRIAD" and "HETERO:MYRIAD,CPU" plugins
-    InferenceEngine::Core& ie = getCore();
+    InferenceEngine::Core& ie = getCore("MYRIAD");
     try
     {
         ie.UnregisterPlugin("MYRIAD");
diff --git a/modules/dnn/src/op_inf_engine.hpp b/modules/dnn/src/op_inf_engine.hpp
index 94682614d9..6a2f73692e 100644
--- a/modules/dnn/src/op_inf_engine.hpp
+++ b/modules/dnn/src/op_inf_engine.hpp
@@ -246,7 +246,7 @@ bool isMyriadX();
 
 CV__DNN_INLINE_NS_END
 
-InferenceEngine::Core& getCore();
+InferenceEngine::Core& getCore(const std::string& id);
 
 template<typename T = size_t>
 static inline std::vector<T> getShape(const Mat& mat)
diff --git a/modules/dnn/src/tensorflow/tf_importer.cpp b/modules/dnn/src/tensorflow/tf_importer.cpp
index 73345cc29a..c741446717 100644
--- a/modules/dnn/src/tensorflow/tf_importer.cpp
+++ b/modules/dnn/src/tensorflow/tf_importer.cpp
@@ -458,6 +458,7 @@ private:
     tensorflow::GraphDef netTxt;
 
     std::vector<String> netInputsNames;
+    std::vector<MatShape> netInputShapes;
 };
 
 TFImporter::TFImporter(const char *model, const char *config)
@@ -1401,6 +1402,27 @@ void TFImporter::populateNet(Net dstNet)
                 netInputsNames.push_back(name);
                 layer_id[name] = 0;
             }
+            if (hasLayerAttr(layer, "shape"))
+            {
+                const tensorflow::TensorShapeProto& shape = getLayerAttr(layer, "shape").shape();
+                MatShape dims(shape.dim_size());
+                for (int i = 0; i < dims.size(); ++i)
+                    dims[i] = shape.dim(i).size();
+                if (dims.size() == 4 && predictedLayout == DATA_LAYOUT_NHWC)
+                {
+                    std::swap(dims[1], dims[3]);  // NHWC->NCWH
+                    std::swap(dims[2], dims[3]);  // NCWH->NCHW
+                    if (dims[0] == -1)  // It's OK to have undetermined batch size
+                        dims[0] = 1;
+                }
+                bool hasNeg = false;
+                for (int i = 0; i < dims.size() && !hasNeg; ++i)
+                {
+                    hasNeg = dims[i] < 0;
+                }
+                if (!hasNeg)
+                    netInputShapes.push_back(dims);
+            }
         }
         else if (type == "Split") {
             // TODO: determining axis index remapping by input dimensions order of input blob
@@ -1580,8 +1602,41 @@ void TFImporter::populateNet(Net dstNet)
             }
             else
             {
-                layerParams.set("operation", "prod");
-                int id = dstNet.addLayer(name, "Eltwise", layerParams);
+                // Check if all the inputs have the same shape.
+                bool equalInpShapes = true;
+                MatShape outShape0;
+                for (int ii = 0; ii < layer.input_size() && !netInputShapes.empty(); ii++)
+                {
+                    Pin pin = parsePin(layer.input(ii));
+                    int inpId = layer_id.find(pin.name)->second;
+
+                    // Get input shape
+                    MatShape outShape;
+                    std::vector<MatShape> inpShapes, outShapes;
+                    dstNet.getLayerShapes(netInputShapes, inpId, inpShapes, outShapes);
+                    CV_CheckGT(static_cast<int>(outShapes.size()), pin.blobIndex, "");
+                    outShape = outShapes[pin.blobIndex];
+
+                    if (ii == 0)
+                    {
+                        outShape0 = outShape;
+                    }
+                    else if (outShape != outShape0)
+                    {
+                        equalInpShapes = false;
+                        break;
+                    }
+                }
+
+                int id;
+                if (equalInpShapes || netInputShapes.empty())
+                {
+                    layerParams.set("operation", "prod");
+                    id = dstNet.addLayer(name, "Eltwise", layerParams);
+                }
+                else
+                    id = dstNet.addLayer(name, "Scale", layerParams);
+
                 layer_id[name] = id;
 
                 for (int ii = 0; ii < layer.input_size(); ii++)
diff --git a/modules/dnn/test/test_onnx_importer.cpp b/modules/dnn/test/test_onnx_importer.cpp
index c5c40d957c..b2b7b5debe 100644
--- a/modules/dnn/test/test_onnx_importer.cpp
+++ b/modules/dnn/test/test_onnx_importer.cpp
@@ -199,6 +199,11 @@ TEST_P(Test_ONNX_layers, MaxPooling_Sigmoid)
     testONNXModels("maxpooling_sigmoid");
 }
 
+TEST_P(Test_ONNX_layers, Cast)
+{
+    testONNXModels("cast");
+}
+
 TEST_P(Test_ONNX_layers, Concatenation)
 {
     if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
@@ -402,6 +407,7 @@ TEST_P(Test_ONNX_layers, DynamicReshape)
     testONNXModels("dynamic_reshape");
     testONNXModels("dynamic_reshape_opset_11");
     testONNXModels("flatten_by_prod");
+    testONNXModels("flatten_const");
 }
 
 TEST_P(Test_ONNX_layers, Reshape)
diff --git a/modules/dnn/test/test_tf_importer.cpp b/modules/dnn/test/test_tf_importer.cpp
index adfbb028de..d2a5e67c32 100644
--- a/modules/dnn/test/test_tf_importer.cpp
+++ b/modules/dnn/test/test_tf_importer.cpp
@@ -186,6 +186,13 @@ TEST_P(Test_TensorFlow_layers, eltwise)
     runTensorFlowNet("eltwise_sub");
 }
 
+TEST_P(Test_TensorFlow_layers, channel_broadcast)
+{
+    if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
+        applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
+    runTensorFlowNet("channel_broadcast");
+}
+
 TEST_P(Test_TensorFlow_layers, pad_and_concat)
 {
     runTensorFlowNet("pad_and_concat");
diff --git a/modules/objdetect/test/test_qrcode.cpp b/modules/objdetect/test/test_qrcode.cpp
index cda5a02311..79a060db0e 100644
--- a/modules/objdetect/test/test_qrcode.cpp
+++ b/modules/objdetect/test/test_qrcode.cpp
@@ -284,7 +284,7 @@ TEST_P(Objdetect_QRCode_Close, regression)
     ASSERT_FALSE(corners.empty());
     ASSERT_FALSE(decoded_info.empty());
 #else
-    ASSERT_TRUE(qrcode.detect(src, corners));
+    ASSERT_TRUE(qrcode.detect(barcode, corners));
 #endif
 
     const std::string dataset_config = findDataFile(root + "dataset_config.json");
@@ -349,7 +349,7 @@ TEST_P(Objdetect_QRCode_Monitor, regression)
     ASSERT_FALSE(corners.empty());
     ASSERT_FALSE(decoded_info.empty());
 #else
-    ASSERT_TRUE(qrcode.detect(src, corners));
+    ASSERT_TRUE(qrcode.detect(barcode, corners));
 #endif
 
     const std::string dataset_config = findDataFile(root + "dataset_config.json");
diff --git a/modules/python/CMakeLists.txt b/modules/python/CMakeLists.txt
index 616f500c95..a51acf386e 100644
--- a/modules/python/CMakeLists.txt
+++ b/modules/python/CMakeLists.txt
@@ -41,6 +41,7 @@ add_subdirectory(python3)
 else()  # standalone build
 
 cmake_minimum_required(VERSION 2.8.12)
+project(OpenCVPython CXX C)
 include("./standalone.cmake")
 
 endif()
diff --git a/samples/cpp/intelligent_scissors.cpp b/samples/cpp/intelligent_scissors.cpp
new file mode 100644
index 0000000000..6141c1f7b5
--- /dev/null
+++ b/samples/cpp/intelligent_scissors.cpp
@@ -0,0 +1,232 @@
+#include <iostream>
+#include <cmath>
+#include <string>
+#include <vector>
+#include <queue>
+#include <opencv2/core/core.hpp>
+#include <opencv2/highgui/highgui.hpp>
+#include <opencv2/imgproc/imgproc.hpp>
+
+using namespace cv;
+struct Pix
+{
+    Point next_point;
+    double cost;
+
+    bool operator > (const Pix &b) const
+    {
+        return cost > b.cost;
+    }
+};
+
+struct Parameters
+{
+    Mat img, img_pre_render, img_render;
+    Point end;
+    std::vector<std::vector<Point> > contours;
+    std::vector<Point> tmp_contour;
+    Mat zero_crossing, gradient_magnitude, Ix, Iy, hit_map_x, hit_map_y;
+};
+
+
+static float local_cost(const Point& p, const Point& q, const Mat& gradient_magnitude, const Mat& Iy, const Mat& Ix, const Mat& zero_crossing)
+{
+    float fG = gradient_magnitude.at<float>(q.y, q.x);
+    float dp;
+    float dq;
+    const float WEIGHT_LAP_ZERO_CROSS = 0.43f;
+    const float WEIGHT_GRADIENT_MAGNITUDE = 0.14f;
+    const float WEIGHT_GRADIENT_DIRECTION = 0.43f;
+    bool isDiag = (p.x != q.x) && (p.y != q.y);
+
+    if ((Iy.at<float>(p) * (q.x - p.x) - Ix.at<float>(p) * (q.y - p.y)) >= 0)
+    {
+        dp = Iy.at<float>(p) * (q.x - p.x) - Ix.at<float>(p) * (q.y - p.y);
+        dq = Iy.at<float>(q) * (q.x - p.x) - Ix.at<float>(q) * (q.y - p.y);
+    }
+    else
+    {
+        dp = Iy.at<float>(p) * (p.x - q.x) + (-Ix.at<float>(p)) * (p.y - q.y);
+        dq = Iy.at<float>(q) * (p.x - q.x) + (-Ix.at<float>(q)) * (p.y - q.y);
+    }
+    if (isDiag)
+    {
+        dp /= sqrtf(2);
+        dq /= sqrtf(2);
+    }
+    else
+    {
+        fG /= sqrtf(2);
+    }
+    return  WEIGHT_LAP_ZERO_CROSS * zero_crossing.at<uchar>(q) +
+            WEIGHT_GRADIENT_DIRECTION * (acosf(dp) + acosf(dq)) / static_cast<float>(CV_PI) +
+            WEIGHT_GRADIENT_MAGNITUDE * fG;
+}
+
+static void find_min_path(const Point& start, Parameters* param)
+{
+    Pix begin;
+    Mat &img = param->img;
+    Mat cost_map(img.size(), CV_32F, Scalar(FLT_MAX));
+    Mat expand(img.size(), CV_8UC1, Scalar(0));
+    Mat processed(img.size(), CV_8UC1, Scalar(0));
+    Mat removed(img.size(), CV_8UC1, Scalar(0));
+    std::priority_queue < Pix, std::vector<Pix>, std::greater<Pix> > L;
+
+    cost_map.at<float>(start) = 0;
+    processed.at<uchar>(start) = 1;
+    begin.cost = 0;
+    begin.next_point = start;
+
+    L.push(begin);
+    while (!L.empty())
+    {
+        Pix P = L.top();
+        L.pop();
+        Point p = P.next_point;
+        processed.at<uchar>(p) = 0;
+        if (removed.at<uchar>(p) == 0)
+        {
+            expand.at<uchar>(p) = 1;
+            for (int i = -1; i <= 1; i++)
+            {
+                for(int j = -1; j <= 1; j++)
+                {
+                    int tx = p.x + i;
+                    int ty = p.y + j;
+                    if (tx < 0 || tx >= img.cols || ty < 0 || ty >= img.rows)
+                        continue;
+                    if (expand.at<uchar>(ty, tx) == 0)
+                    {
+                        Point q = Point(tx, ty);
+                        float cost = cost_map.at<float>(p) + local_cost(p, q, param->gradient_magnitude, param->Iy, param->Ix, param->zero_crossing);
+                        if (processed.at<uchar>(q) == 1 && cost < cost_map.at<float>(q))
+                        {
+                            removed.at<uchar>(q) = 1;
+                        }
+                        if (processed.at<uchar>(q) == 0)
+                        {
+                            cost_map.at<float>(q) = cost;
+                            param->hit_map_x.at<int>(q)= p.x;
+                            param->hit_map_y.at<int>(q) = p.y;
+                            processed.at<uchar>(q) = 1;
+                            Pix val;
+                            val.cost = cost_map.at<float>(q);
+                            val.next_point = q;
+                            L.push(val);
+                        }
+                    }
+                }
+            }
+        }
+    }
+}
+
+
+static void onMouse(int event, int x, int y, int , void* userdata)
+{
+    Parameters* param = reinterpret_cast<Parameters*>(userdata);
+    Point &end = param->end;
+    std::vector<std::vector<Point> > &contours = param->contours;
+    std::vector<Point> &tmp_contour = param->tmp_contour;
+    Mat &img_render = param->img_render;
+    Mat &img_pre_render = param->img_pre_render;
+
+    if (event == EVENT_LBUTTONDOWN)
+    {
+        end = Point(x, y);
+        if (!contours.back().empty())
+        {
+            for (int i = static_cast<int>(tmp_contour.size()) - 1; i >= 0; i--)
+            {
+                contours.back().push_back(tmp_contour[i]);
+            }
+            tmp_contour.clear();
+        }
+        else
+        {
+            contours.back().push_back(end);
+        }
+        find_min_path(end, param);
+
+        img_render.copyTo(img_pre_render);
+        imshow("lasso", img_render);
+    }
+    else if (event == EVENT_RBUTTONDOWN)
+    {
+        img_pre_render.copyTo(img_render);
+        drawContours(img_pre_render, contours, static_cast<int>(contours.size()) - 1, Scalar(0,255,0), FILLED);
+        addWeighted(img_pre_render, 0.3, img_render, 0.7, 0, img_render);
+        contours.resize(contours.size() + 1);
+        imshow("lasso", img_render);
+    }
+    else if (event == EVENT_MOUSEMOVE && !contours.back().empty())
+    {
+        tmp_contour.clear();
+        img_pre_render.copyTo(img_render);
+        Point val_point = Point(x, y);
+        while (val_point != end)
+        {
+            tmp_contour.push_back(val_point);
+            Point cur = Point(param->hit_map_x.at<int>(val_point), param->hit_map_y.at<int>(val_point));
+            line(img_render, val_point, cur, Scalar(255, 0, 0), 2);
+            val_point = cur;
+        }
+        imshow("lasso", img_render);
+    }
+}
+
+const char* keys =
+{
+    "{help h | |}"
+    "{@image | fruits.jpg| Path to image to process}"
+};
+
+
+int main( int argc, const char** argv )
+{
+    Parameters param;
+    const int EDGE_THRESHOLD_LOW = 50;
+    const int EDGE_THRESHOLD_HIGH = 100;
+    CommandLineParser parser(argc, argv, keys);
+    parser.about("\nThis program demonstrates implementation of 'intelligent scissors' algorithm\n"
+                 "To start drawing a new contour select a pixel, click LEFT mouse button.\n"
+                 "To fix a path click LEFT mouse button again.\n"
+                 "To finish drawing a contour click RIGHT mouse button.\n");
+    if (parser.has("help"))
+    {
+        parser.printMessage();
+        return 1;
+    }
+    std::vector<std::vector<Point> > c(1);
+    param.contours = c;
+    std::string filename = parser.get<std::string>(0);
+
+    Mat grayscale, img_canny;
+    param.img = imread(samples::findFile(filename));
+    param.hit_map_x.create(param.img.rows, param.img.cols, CV_32SC1);
+    param.hit_map_y.create(param.img.rows, param.img.cols, CV_32SC1);
+
+    cvtColor(param.img, grayscale, COLOR_BGR2GRAY);
+    Canny(grayscale, img_canny, EDGE_THRESHOLD_LOW, EDGE_THRESHOLD_HIGH);
+
+    threshold(img_canny, param.zero_crossing, 254, 1, THRESH_BINARY_INV);
+    Sobel(grayscale, param.Ix, CV_32FC1, 1, 0, 1);
+    Sobel(grayscale, param.Iy, CV_32FC1, 0, 1, 1);
+    param.Ix.convertTo(param.Ix, CV_32F, 1.0/255);
+    param.Iy.convertTo(param.Iy, CV_32F, 1.0/255);
+
+    // Compute gradients magnitude.
+    double max_val = 0.0;
+    magnitude(param.Iy, param.Ix, param.gradient_magnitude);
+    minMaxLoc(param.gradient_magnitude, 0, &max_val);
+    param.gradient_magnitude.convertTo(param.gradient_magnitude, CV_32F, -1/max_val, 1.0);
+
+    param.img.copyTo(param.img_pre_render);
+    param.img.copyTo(param.img_render);
+
+    namedWindow("lasso");
+    setMouseCallback("lasso", onMouse, &param);
+    imshow("lasso", param.img);
+    waitKey(0);
+}
diff --git a/samples/dnn/tf_text_graph_ssd.py b/samples/dnn/tf_text_graph_ssd.py
index b466548502..bf1d788d41 100644
--- a/samples/dnn/tf_text_graph_ssd.py
+++ b/samples/dnn/tf_text_graph_ssd.py
@@ -64,7 +64,7 @@ def createSSDGraph(modelPath, configPath, outputPath):
     # Nodes that should be kept.
     keepOps = ['Conv2D', 'BiasAdd', 'Add', 'AddV2', 'Relu', 'Relu6', 'Placeholder', 'FusedBatchNorm',
                'DepthwiseConv2dNative', 'ConcatV2', 'Mul', 'MaxPool', 'AvgPool', 'Identity',
-               'Sub', 'ResizeNearestNeighbor', 'Pad', 'FusedBatchNormV3']
+               'Sub', 'ResizeNearestNeighbor', 'Pad', 'FusedBatchNormV3', 'Mean']
 
     # Node with which prefixes should be removed
     prefixesToRemove = ('MultipleGridAnchorGenerator/', 'Concatenate/', 'Postprocessor/', 'Preprocessor/map')
@@ -235,7 +235,7 @@ def createSSDGraph(modelPath, configPath, outputPath):
     # Connect input node to the first layer
     assert(graph_def.node[0].op == 'Placeholder')
     # assert(graph_def.node[1].op == 'Conv2D')
-    weights = graph_def.node[1].input[0]
+    weights = graph_def.node[1].input[-1]
     for i in range(len(graph_def.node[1].input)):
         graph_def.node[1].input.pop()
     graph_def.node[1].input.append(graph_def.node[0].name)