static void parallel_for_impl(const cv::Range& range, const cv::ParallelLoopBody& body, double nstripes)
{
    if ((numThreads < 0 || numThreads > 1) && range.end - range.start > 1)
    {
        ParallelLoopBodyWrapperContext ctx(body, range, nstripes);
        ProxyLoopBody pbody(ctx);
        cv::Range stripeRange = pbody.stripeRange();
        if( stripeRange.end - stripeRange.start == 1 )
        {
            body(range);
            return;
        }

#if defined HAVE_TBB

#if TBB_INTERFACE_VERSION >= 8000
        tbbArena.execute(pbody);
#else
        pbody();
#endif

#elif defined HAVE_HPX
        pbody();
#elif defined HAVE_OPENMP

        #pragma omp parallel for schedule(dynamic) num_threads(numThreads > 0 ? numThreads : numThreadsMax)
        for (int i = stripeRange.start; i < stripeRange.end; ++i)
            pbody(Range(i, i + 1));

#elif defined HAVE_GCD

        dispatch_queue_t concurrent_queue = dispatch_get_global_queue(DISPATCH_QUEUE_PRIORITY_DEFAULT, 0);
        dispatch_apply_f(stripeRange.end - stripeRange.start, concurrent_queue, &pbody, block_function);

#elif defined WINRT

        Concurrency::parallel_for(stripeRange.start, stripeRange.end, pbody);

#elif defined HAVE_CONCURRENCY

        if(!pplScheduler || pplScheduler->Id() == Concurrency::CurrentScheduler::Id())
        {
            Concurrency::parallel_for(stripeRange.start, stripeRange.end, pbody);
        }
        else
        {
            pplScheduler->Attach();
            Concurrency::parallel_for(stripeRange.start, stripeRange.end, pbody);
            Concurrency::CurrentScheduler::Detach();
        }

#elif defined HAVE_PTHREADS_PF

        parallel_for_pthreads(pbody.stripeRange(), pbody, pbody.stripeRange().size());

#else

#error You have hacked and compiling with unsupported parallel framework

#endif

        ctx.finalize();  // propagate exceptions if exists
    }
    else
    {
        body(range);
    }
}


    class ProxyLoopBody : public ParallelLoopBodyWrapper
    {
    public:
        ProxyLoopBody(ParallelLoopBodyWrapperContext& ctx_)
        : ParallelLoopBodyWrapper(ctx_)
        {}

        void operator ()() const  // run parallel job
        {
            cv::Range range = this->stripeRange();
            hpx::parallel::for_loop_strided(
                    hpx::parallel::execution::par,
                    range.start, range.end, 1,
                    &ctx.body);
        }
    };