Revision history [back]

I made an attempt to solve this by using parallel_for_ that seems to work. At the top of cascadeclassifier.cpp I added:

class Parallel_predict: public cv::ParallelLoopBody
{
private:
    const vector< Ptr<cvcascadeboost> >& v;
    int idx;
    int * result;

public:
    Parallel_predict(const vector< Ptr<cvcascadeboost> >& vectorToProcess, int i, int * r)
    : v(vectorToProcess), idx(i), result(r){ *result=1; }

    virtual void operator()( const cv::Range &r ) const {
        for (int i = r.start ; (i!=r.end)&&(*result==1) ; ++i)
        {
            if (v[i]->predict(idx)==.0f)
            {
                *result=0;
                return;
            }
        }
    }
};

Then, also in cascadeclassifier.cpp, I updated the int CvCascadeClassifier::predict( int sampleIdx ) method to look like this:

int CvCascadeClassifier::predict( int sampleIdx )
{
    CV_DbgAssert( sampleIdx < numPos + numNeg );

    int result;
    Parallel_predict p(stageClassifiers, sampleIdx, &result);
    cv::parallel_for_(cv::Range(0,(int)stageClassifiers.size()), p);
    return result;


    /* OLD CODE
    for (vector< Ptr<cvcascadeboost> >::iterator it = stageClassifiers.begin();
        it != stageClassifiers.end(); it++ )
    {
        if ( (*it)->predict( sampleIdx ) == 0.f )
            return 0;
    }
    return 1;*/
}

I have only tried this on OSX. It seems to work alright and it for sure use all of my cores :) There are however more code that could be paralellized (like in fillPassedSamples) but those are not very obvious how to attack.

/MB