C++ OutputArray::needed方法代码示例

void cv::superres::Farneback::calc(InputArray _frame0, InputArray _frame1, OutputArray _flow1, OutputArray _flow2)
{
    Mat frame0 = ::getMat(_frame0, buf[0]);
    Mat frame1 = ::getMat(_frame1, buf[1]);

    CV_DbgAssert( frame1.type() == frame0.type() );
    CV_DbgAssert( frame1.size() == frame0.size() );

    Mat input0 = ::convertToType(frame0, CV_8U, 1, buf[2], buf[3]);
    Mat input1 = ::convertToType(frame1, CV_8U, 1, buf[4], buf[5]);

    if (!_flow2.needed() && _flow1.kind() != _InputArray::GPU_MAT)
    {
        call(input0, input1, _flow1);
        return;
    }

    call(input0, input1, flow);

    if (!_flow2.needed())
    {
        ::copy(_flow1, flow);
    }
    else
    {
        split(flow, flows);

        ::copy(_flow1, flows[0]);
        ::copy(_flow2, flows[1]);
    }
}

    Vec2d predict2(InputArray _sample, OutputArray _probs) const
    {
        int ptype = CV_64F;
        Mat sample = _sample.getMat();
        CV_Assert(isTrained());

        CV_Assert(!sample.empty());
        if(sample.type() != CV_64FC1)
        {
            Mat tmp;
            sample.convertTo(tmp, CV_64FC1);
            sample = tmp;
        }
        sample = sample.reshape(1, 1);

        Mat probs;
        if( _probs.needed() )
        {
            if( _probs.fixedType() )
                ptype = _probs.type();
            _probs.create(1, nclusters, ptype);
            probs = _probs.getMat();
        }

        return computeProbabilities(sample, !probs.empty() ? &probs : 0, ptype);
    }

float SVMSGDImpl::predict( InputArray _samples, OutputArray _results, int ) const
{
    float result = 0;
    cv::Mat samples = _samples.getMat();
    int nSamples = samples.rows;
    cv::Mat results;

    CV_Assert( samples.cols == weights_.cols && samples.type() == CV_32FC1);

    if( _results.needed() )
    {
        _results.create( nSamples, 1, samples.type() );
        results = _results.getMat();
    }
    else
    {
        CV_Assert( nSamples == 1 );
        results = Mat(1, 1, CV_32FC1, &result);
    }

    for (int sampleIndex = 0; sampleIndex < nSamples; sampleIndex++)
    {
        Mat currentSample = samples.row(sampleIndex);
        float criterion = static_cast<float>(currentSample.dot(weights_)) + shift_;
        results.at<float>(sampleIndex) = (criterion >= 0) ? 1.f : -1.f;
    }

    return result;
}

float AffineTransformerImpl::applyTransformation(InputArray inPts, OutputArray outPts)
{
    Mat pts1 = inPts.getMat();
    CV_Assert((pts1.channels()==2) && (pts1.cols>0));

    //Apply transformation in the complete set of points
    Mat fAffine;
    transform(pts1, fAffine, affineMat);

    // Ensambling output //
    if (outPts.needed())
    {
        outPts.create(1,fAffine.cols, CV_32FC2);
        Mat outMat = outPts.getMat();
        for (int i=0; i<fAffine.cols; i++)
            outMat.at<Point2f>(0,i)=fAffine.at<Point2f>(0,i);
    }

    // Updating Transform Cost //
    Mat Af(2, 2, CV_32F);
    Af.at<float>(0,0)=affineMat.at<float>(0,0);
    Af.at<float>(0,1)=affineMat.at<float>(1,0);
    Af.at<float>(1,0)=affineMat.at<float>(0,1);
    Af.at<float>(1,1)=affineMat.at<float>(1,1);
    SVD mysvd(Af, SVD::NO_UV);
    Mat singVals=mysvd.w;
    transformCost=std::log((singVals.at<float>(0,0)+FLT_MIN)/(singVals.at<float>(1,0)+FLT_MIN));

    return transformCost;
}

    float predict(InputArray _inputs, OutputArray _outputs, int) const
    {
        bool needprobs = _outputs.needed();
        Mat samples = _inputs.getMat(), probs, probsrow;
        int ptype = CV_64F;
        float firstres = 0.f;
        int i, nsamples = samples.rows;

        if( needprobs )
        {
            if( _outputs.fixedType() )
                ptype = _outputs.type();
            _outputs.create(samples.rows, nclusters, ptype);
        }
        else
            nsamples = std::min(nsamples, 1);

        for( i = 0; i < nsamples; i++ )
        {
            if( needprobs )
                probsrow = probs.row(i);
            Vec2d res = computeProbabilities(samples.row(i), needprobs ? &probsrow : 0, ptype);
            if( i == 0 )
                firstres = (float)res[1];
        }
        return firstres;
    }

double computeReprojectionErrors(InputArray points3D,
                                 InputArray points2D,
                                 InputArray cameraMatrix,
                                 InputArray distCoeffs,
                                 InputArray rvec,
                                 InputArray tvec,
                                 OutputArray _proj_points2D,
                                 vector<double> *individual_error)
{
  // set proper type for the output
  Mat x = points2D.getMat();
  Mat proj_points2D = _proj_points2D.getMat();
  proj_points2D.create(x.rows, x.cols, x.type());

  // project points
  projectPoints(points3D, rvec, tvec, cameraMatrix, distCoeffs, proj_points2D);

  // save output if it is needed (no default parameter)
  if (_proj_points2D.needed())
  {
    proj_points2D.copyTo(_proj_points2D);
  }

  // return error
  return calib::norm(x, proj_points2D, individual_error);
}

float StatModel::calcError( const Ptr<TrainData>& data, bool testerr, OutputArray _resp ) const
{
    CV_TRACE_FUNCTION_SKIP_NESTED();
    Mat samples = data->getSamples();
    int layout = data->getLayout();
    Mat sidx = testerr ? data->getTestSampleIdx() : data->getTrainSampleIdx();
    const int* sidx_ptr = sidx.ptr<int>();
    int i, n = (int)sidx.total();
    bool isclassifier = isClassifier();
    Mat responses = data->getResponses();
    int responses_type = responses.type();

    if( n == 0 )
        n = data->getNSamples();

    if( n == 0 )
        return -FLT_MAX;

    Mat resp;
    if( _resp.needed() )
        resp.create(n, 1, CV_32F);

    double err = 0;
    for( i = 0; i < n; i++ )
    {
        int si = sidx_ptr ? sidx_ptr[i] : i;
        Mat sample = layout == ROW_SAMPLE ? samples.row(si) : samples.col(si);
        float val = predict(sample);
        float val0 = (responses_type == CV_32S) ? (float)responses.at<int>(si) : responses.at<float>(si);

        if( isclassifier )
            err += fabs(val - val0) > FLT_EPSILON;
        else
            err += (val - val0)*(val - val0);
        if( !resp.empty() )
            resp.at<float>(i) = val;
        /*if( i < 100 )
        {
            printf("%d. ref %.1f vs pred %.1f\n", i, val0, val);
        }*/
    }

    if( _resp.needed() )
        resp.copyTo(_resp);

    return (float)(err / n * (isclassifier ? 100 : 1));
}

float cv::EMD( InputArray _signature1, InputArray _signature2,
               int distType, InputArray _cost,
               float* lowerBound, OutputArray _flow )
{
    Mat signature1 = _signature1.getMat(), signature2 = _signature2.getMat();
    Mat cost = _cost.getMat(), flow;

    CvMat _csignature1 = signature1;
    CvMat _csignature2 = signature2;
    CvMat _ccost = cost, _cflow;
    if( _flow.needed() )
    {
        _flow.create(signature1.rows, signature2.rows, CV_32F);
        flow = _flow.getMat();
        _cflow = flow;
    }

    return cvCalcEMD2( &_csignature1, &_csignature2, distType, 0, cost.empty() ? 0 : &_ccost,
                       _flow.needed() ? &_cflow : 0, lowerBound, 0 );
}

        void detectAndCompute(InputArray image, InputArray mask,
                              std::vector<KeyPoint>& keypoints,
                              OutputArray descriptors,
                              bool useProvidedKeypoints)
        {
            Mat img = image.getMat();

            if (img_width != img.cols) {
                img_width = img.cols;
                impl.release();
            }

            if (img_height != img.rows) {
                img_height = img.rows;
                impl.release();
            }

            if (impl.empty()) {
                AKAZEOptionsV2 options;
                options.descriptor = descriptor;
                options.descriptor_channels = descriptor_channels;
                options.descriptor_size = descriptor_size;
                options.img_width = img_width;
                options.img_height = img_height;
                options.dthreshold = threshold;
                options.omax = octaves;
                options.nsublevels = sublevels;
                options.diffusivity = diffusivity;

                impl = makePtr<AKAZEFeaturesV2>(options);
            }

            impl->Create_Nonlinear_Scale_Space(img);

            if (!useProvidedKeypoints)
            {
                impl->Feature_Detection(keypoints);
            }

            if (!mask.empty())
            {
                KeyPointsFilter::runByPixelsMask(keypoints, mask.getMat());
            }

            if( descriptors.needed() )
            {
                Mat& desc = descriptors.getMatRef();
                impl->Compute_Descriptors(keypoints, desc);

                CV_Assert((!desc.rows || desc.cols == descriptorSize()));
                CV_Assert((!desc.rows || (desc.type() == descriptorType())));
            }
        }

        void detectAndCompute(InputArray image, InputArray mask,
                              std::vector<KeyPoint>& keypoints,
                              OutputArray descriptors,
                              bool useProvidedKeypoints)
        {
            Mat img = image.getMat();
            if (img.type() != CV_8UC1 && img.type() != CV_16UC1)
                cvtColor(image, img, COLOR_BGR2GRAY);

            Mat img1_32;
            if ( img.depth() == CV_32F )
                img1_32 = img;
            else if ( img.depth() == CV_8U )
                img.convertTo(img1_32, CV_32F, 1.0 / 255.0, 0);
            else if ( img.depth() == CV_16U )
                img.convertTo(img1_32, CV_32F, 1.0 / 65535.0, 0);

            CV_Assert( ! img1_32.empty() );

            AKAZEOptions options;
            options.descriptor = descriptor;
            options.descriptor_channels = descriptor_channels;
            options.descriptor_size = descriptor_size;
            options.img_width = img.cols;
            options.img_height = img.rows;
            options.dthreshold = threshold;
            options.omax = octaves;
            options.nsublevels = sublevels;
            options.diffusivity = diffusivity;

            AKAZEFeatures impl(options);
            impl.Create_Nonlinear_Scale_Space(img1_32);

            if (!useProvidedKeypoints)
            {
                impl.Feature_Detection(keypoints);
            }

            if (!mask.empty())
            {
                KeyPointsFilter::runByPixelsMask(keypoints, mask.getMat());
            }

            if( descriptors.needed() )
            {
                Mat& desc = descriptors.getMatRef();
                impl.Compute_Descriptors(keypoints, desc);

                CV_Assert((!desc.rows || desc.cols == descriptorSize()));
                CV_Assert((!desc.rows || (desc.type() == descriptorType())));
            }
        }

void cv::gpu::GeneralizedHough_GPU::download(const GpuMat& d_positions, OutputArray h_positions_, OutputArray h_votes_)
{
    if (d_positions.empty())
    {
        h_positions_.release();
        if (h_votes_.needed())
            h_votes_.release();
        return;
    }

    CV_Assert(d_positions.rows == 2 && d_positions.type() == CV_32FC4);

    h_positions_.create(1, d_positions.cols, CV_32FC4);
    Mat h_positions = h_positions_.getMat();
    d_positions.row(0).download(h_positions);

    if (h_votes_.needed())
    {
        h_votes_.create(1, d_positions.cols, CV_32SC3);
        Mat h_votes = h_votes_.getMat();
        GpuMat d_votes(1, d_positions.cols, CV_32SC3, const_cast<int3*>(d_positions.ptr<int3>(1)));
        d_votes.download(h_votes);
    }
}

bool CustomPattern::findPattern(InputArray image, OutputArray matched_features, OutputArray pattern_points,
                                const double ratio, const double proj_error, const bool refine_position, OutputArray out,
                                OutputArray H, OutputArray pattern_corners)
{
    CV_Assert(!image.empty() && proj_error > 0);

    Mat img = image.getMat();
    vector<Point2f> m_ftrs;
    vector<Point3f> pattern_pts;
    Mat _H;
    vector<Point2f> scene_corners;
    if (!findPatternPass(img, m_ftrs, pattern_pts, _H, scene_corners, 0.6, proj_error, refine_position))
        return false; // pattern not found

    Mat mask = Mat::zeros(img.size(), CV_8UC1);
    vector<vector<Point> > obj(1);
    vector<Point> scorners_int(scene_corners.size());
    for (uint i = 0; i < scene_corners.size(); ++i)
        scorners_int[i] = (Point)scene_corners[i]; // for drawContours
    obj[0] = scorners_int;
    drawContours(mask, obj, 0, Scalar(255), FILLED);

    // Second pass
    Mat output;
    if (!findPatternPass(img, m_ftrs, pattern_pts, _H, scene_corners,
                         ratio, proj_error, refine_position, mask, output))
        return false; // pattern not found

    Mat(m_ftrs).copyTo(matched_features);
    Mat(pattern_pts).copyTo(pattern_points);
    if (out.needed()) output.copyTo(out);
    if (H.needed()) _H.copyTo(H);
    if (pattern_corners.needed()) Mat(scene_corners).copyTo(pattern_corners);

    return (!m_ftrs.empty());
}

bool CustomPattern::init(Mat& image, const float pixel_size, OutputArray output)
{
    image.copyTo(img_roi);
    //Setup object corners
    obj_corners = std::vector<Point2f>(4);
    obj_corners[0] = Point2f(0, 0); obj_corners[1] = Point2f(img_roi.cols, 0);
    obj_corners[2] = Point2f(img_roi.cols, img_roi.rows); obj_corners[3] = Point2f(0, img_roi.rows);

    if (!detector)   // if no detector chosen, use default
    {
        detector = FeatureDetector::create("ORB");
        detector->set("nFeatures", 2000);
        detector->set("scaleFactor", 1.15);
        detector->set("nLevels", 30);
    }

    detector->detect(img_roi, keypoints);
    if (keypoints.empty())
    {
        initialized = false;
        return initialized;
    }
    refineKeypointsPos(img_roi, keypoints);

    if (!descriptorExtractor)   // if no extractor chosen, use default
        descriptorExtractor = DescriptorExtractor::create("ORB");
    descriptorExtractor->compute(img_roi, keypoints, descriptor);

    if (!descriptorMatcher)
        descriptorMatcher = DescriptorMatcher::create("BruteForce-Hamming(2)");

    // Scale found points by pixelSize
    pxSize = pixel_size;
    scaleFoundPoints(pxSize, keypoints, points3d);

    if (output.needed())
    {
        Mat out;
        drawKeypoints(img_roi, keypoints, out, CV_RGB(255, 0, 0));
        out.copyTo(output);
    }

    initialized = !keypoints.empty();
    return initialized; // initialized if any keypoints are found
}

void SparsePyrLkOptFlowEstimatorGpu::run(
        InputArray frame0, InputArray frame1, InputArray points0, InputOutputArray points1,
        OutputArray status, OutputArray errors)
{
    frame0_.upload(frame0.getMat());
    frame1_.upload(frame1.getMat());
    points0_.upload(points0.getMat());

    if (errors.needed())
    {
        run(frame0_, frame1_, points0_, points1_, status_, errors_);
        errors_.download(errors.getMatRef());
    }
    else
        run(frame0_, frame1_, points0_, points1_, status_);

    points1_.download(points1.getMatRef());
    status_.download(status.getMatRef());
}

void DensePyrLkOptFlowEstimatorGpu::run(
        InputArray frame0, InputArray frame1, InputOutputArray flowX, InputOutputArray flowY,
        OutputArray errors)
{
    frame0_.upload(frame0.getMat());
    frame1_.upload(frame1.getMat());

    optFlowEstimator_.winSize = winSize_;
    optFlowEstimator_.maxLevel = maxLevel_;
    if (errors.needed())
    {
        optFlowEstimator_.dense(frame0_, frame1_, flowX_, flowY_, &errors_);
        errors_.download(errors.getMatRef());
    }
    else
        optFlowEstimator_.dense(frame0_, frame1_, flowX_, flowY_);

    flowX_.download(flowX.getMatRef());
    flowY_.download(flowY.getMatRef());
}