void Nieto::ExpectationMaximizationArmadillo(const Mat1b &inGrayFrameRoi, int maxIters, map<string, double> &_means0, map<string, double> &_covs0, map<string, double> &_weights0) {
double tempoInicio = static_cast<double>(getTickCount());
const int nClusters = 4; // 4 classes => {pavement, markings, objects, unknown}
Mat1b grayFrameRoiClone = inGrayFrameRoi.clone();
Mat1b trainGrayFrameRoiClone = inGrayFrameRoi.clone();
resize(grayFrameRoiClone, trainGrayFrameRoiClone, Size(160, 35), 0, 0, INTER_NEAREST);
Mat1d samples = trainGrayFrameRoiClone.reshape(1, trainGrayFrameRoiClone.rows * trainGrayFrameRoiClone.cols);
arma::mat armaSamples(reinterpret_cast<double*>(samples.data), samples.rows, samples.cols);
// cout << "size armaSamples: " << arma::size(armaSamples) << endl;
// formata o _means0
arma::mat means0(1, nClusters);
means0.at(0, 0) = _means0["pavement"];
means0.at(0, 1) = _means0["markings"];
means0.at(0, 2) = _means0["objects"];
means0.at(0, 3) = 255.0 / 2.0;
// cout << "size means0: " << arma::size(means0) << endl;
// formata o _covs0
arma::mat covs0(1, nClusters);
covs0.at(0, 0) = _covs0["pavement"];
covs0.at(0, 1) = _covs0["markings"];
covs0.at(0, 2) = _covs0["objects"];
covs0.at(0, 3) = ((255.0 / 2.0) / sqrt(3)) * ((255.0 / 2.0) / sqrt(3));
// cout << "size covs0: " << arma::size(covs0) << endl;
// formata o _weights0
arma::mat weights0(1, nClusters);
weights0.at(0, 0) = _weights0["pavement"];
weights0.at(0, 1) = _weights0["markings"];
weights0.at(0, 2) = _weights0["objects"];
weights0.at(0, 3) = _weights0["unknown"];
// cout << "size weights0: " << arma::size(weights0) << endl;
// if (!(size(means0) != size(covs0))) cout << "1 - ok!" << endl;
// if (!(weights0.n_cols != means0.n_cols)) cout << "2 - ok!" << endl;
// if (!(weights0.n_rows != 1)) cout << "3 - ok!" << endl;
arma::gmm_diag em;
em.set_params(means0, covs0, weights0);
em.learn(armaSamples.t(), nClusters, arma::eucl_dist, arma::keep_existing, 0, maxIters, 1e-10, false);
// calcula o tempo de execu��o
double tempoFim = static_cast<double>(getTickCount());
double tempoExecutando = ((tempoFim - tempoInicio) / getTickFrequency()) * 1000;
// exibe as sa�das definidas (texto e/ou imagem)
if (verbose) cout << "- em armadillo (1 feature): " << tempoExecutando << " ms" << endl;
if (display) {
// predict
Mat1b predictedImage = Mat1b(grayFrameRoiClone.size(), uchar(0));
for (int j = 0; j < predictedImage.rows; ++j) {
unsigned char *ptRowSrc = grayFrameRoiClone.ptr<uchar>(j);
unsigned char *ptRowDst = predictedImage.ptr<uchar>(j);
for (int i = 0; i < predictedImage.cols; ++i) {
arma::vec v;
v << ptRowSrc[i];
int emPredicted = em.assign(v, arma::eucl_dist);
switch (emPredicted) {
case 0: ptRowDst[i] = 160; break;
case 1: ptRowDst[i] = 255; break;
case 2: ptRowDst[i] = 80; break;
case 3: ptRowDst[i] = 0; break;
}
}
}
imshow("EM Armadillo - 1 Feature", predictedImage);
}
}
void Nieto::ExpectationMaximizationOpenCV(const Mat1b &inGrayFrameRoi, int maxIters, map<string, double> &_means0, map<string, double> &_covs0, map<string, double> &_weights0) {
double tempoInicio = static_cast<double>(getTickCount());
const int nClusters = 4; // 4 classes => {pavement, markings, objects, unknown}
const bool aplicaResize = true;
EM em = EM(nClusters, EM::COV_MAT_DIAGONAL);
Mat1b grayFrameRoiClone = inGrayFrameRoi.clone();
Mat1b trainGrayFrameRoiClone = inGrayFrameRoi.clone();
if (aplicaResize) resize(grayFrameRoiClone, trainGrayFrameRoiClone, Size(160, 35), 0, 0, INTER_NEAREST);
Mat1d samples = trainGrayFrameRoiClone.reshape(1, trainGrayFrameRoiClone.rows * trainGrayFrameRoiClone.cols);
// formata o _means0
Mat1d means0 = Mat1d(nClusters, 1, CV_64FC1);
means0.at<double>(0) = _means0["pavement"];
means0.at<double>(1) = _means0["markings"];
means0.at<double>(2) = _means0["objects"];
means0.at<double>(3) = 255.0 / 2.0;
// formata o _covs0
vector<Mat> covs0 = {
Mat1d(1, 1, _covs0["pavement"]),
Mat1d(1, 1, _covs0["markings"]),
Mat1d(1, 1, _covs0["objects"]),
Mat1d(1, 1, ((255.0 / 2.0) / sqrt(3)) * ((255.0 / 2.0) / sqrt(3)))
};
// formata o _weights0
// Mat1d weights0 = *(Mat1f(nClusters, 1, CV_64FC1) << 0.75, 0.10, 0.10, 0.05);
Mat1d weights0 = *(Mat1f(nClusters, 1, CV_64FC1) <<
_weights0["pavement"],
_weights0["markings"],
_weights0["objects"],
_weights0["unknown"]
);
// cout << means0 << endl;
em.set("maxIters", maxIters);
em.trainE(samples, means0, covs0, weights0);
// calcula o tempo de execu��o
double tempoFim = static_cast<double>(getTickCount());
double tempoExecutando = ((tempoFim - tempoInicio) / getTickFrequency()) * 1000;
// exibe as sa�das definidas (texto e/ou imagem)
if (verbose) cout << "- em opencv (1 feature): " << tempoExecutando << " ms" << endl;
if (display) {
// predict
Mat1b predictedImage = Mat1b(grayFrameRoiClone.size(), uchar(0));
for (int j = 0; j < predictedImage.rows; ++j) {
unsigned char *ptRowSrc = grayFrameRoiClone.ptr<uchar>(j);
unsigned char *ptRowDst = predictedImage.ptr<uchar>(j);
for (int i = 0; i < predictedImage.cols; ++i) {
Vec2d emPredicted = em.predict(ptRowSrc[i]);
switch ((int)emPredicted[1]) {
case 0: ptRowDst[i] = 160; break;
case 1: ptRowDst[i] = 255; break;
case 2: ptRowDst[i] = 80; break;
case 3: ptRowDst[i] = 0; break;
}
}
}
imshow("EM OpenCV - 1 Feature", predictedImage);
}
}
