bool BowVocabulary::computeTrainingData(TrainingData& trainingDataOut, const string& vocabularyImgsList, const string& samplesImgsList, bool outputAnalyzedImages) {
if (_bowImgDescriptorExtractor->getVocabulary().rows == 0) {
Mat vocabulary;
if (!computeVocabulary(vocabulary, vocabularyImgsList)) {
return false;
}
}
Mat trainSamples;
Mat trainLabels(0, 1, CV_32SC1);
if (loadTrainingSamples(trainSamples) && loadTrainingLabels(trainLabels)) {
trainingDataOut.setTrainSamples(trainSamples);
trainingDataOut.setTrainLabels(trainLabels);
return true;
}
ifstream imgsList(vocabularyImgsList);
if (imgsList.is_open()) {
vector<string> fileNames;
string filename;
while (getline(imgsList, filename)) {
fileNames.push_back(filename);
}
int numberOfFiles = fileNames.size();
int samplesWordSize = _bowImgDescriptorExtractor->getVocabulary().rows;
cout << "\n -> Analysing " << numberOfFiles << " training images..." << endl;
PerformanceTimer performanceTimer;
performanceTimer.start();
//#pragma omp parallel for schedule(dynamic)
for (int i = 0; i < numberOfFiles; ++i) {
Mat imagePreprocessed;
string imageFilenameShort = IMGS_DIRECTORY + fileNames[i];
string imageFilenameFull = imageFilenameShort + IMAGE_TOKEN;
if (_imagePreprocessor->loadAndPreprocessImage(imageFilenameFull, imagePreprocessed, CV_LOAD_IMAGE_GRAYSCALE, false)) {
vector<KeyPoint> keypoints;
_featureDetector->detect(imagePreprocessed, keypoints);
vector< vector <KeyPoint> > keypointsTargetClass;
vector<KeyPoint> keypointsNonTargetClass;
ImageUtils::splitKeyPoints(imageFilenameShort, keypoints, keypointsTargetClass, keypointsNonTargetClass);
for (size_t targetClassInstancePosition = 0; targetClassInstancePosition < keypointsTargetClass.size(); ++targetClassInstancePosition) {
if (keypointsTargetClass[targetClassInstancePosition].size() > 3) {
Mat descriptorsTargetClass;
_bowImgDescriptorExtractor->compute(imagePreprocessed, keypointsTargetClass[targetClassInstancePosition], descriptorsTargetClass);
//#pragma omp critical
if (descriptorsTargetClass.rows > 0 && descriptorsTargetClass.cols == samplesWordSize) {
trainSamples.push_back(descriptorsTargetClass);
trainLabels.push_back(1);
}
}
}
if (keypointsNonTargetClass.size() > 3) {
Mat descriptorsNonTargetClass;
_bowImgDescriptorExtractor->compute(imagePreprocessed, keypointsNonTargetClass, descriptorsNonTargetClass);
//#pragma omp critical
if (descriptorsNonTargetClass.rows > 0 && descriptorsNonTargetClass.cols == samplesWordSize) {
trainSamples.push_back(descriptorsNonTargetClass);
trainLabels.push_back(0);
}
}
if (outputAnalyzedImages) {
stringstream imageOutputFilename;
imageOutputFilename << SAMPLES_BUILD_OUTPUT_DIRECTORY << fileNames[i] << FILENAME_SEPARATOR << _vocabularyFilename << IMAGE_OUTPUT_EXTENSION;
for (size_t targetClassInstancePosition = 0; targetClassInstancePosition < keypointsTargetClass.size(); ++targetClassInstancePosition) {
if (keypointsTargetClass[targetClassInstancePosition].size() > 0) {
cv::drawKeypoints(imagePreprocessed, keypointsTargetClass[targetClassInstancePosition], imagePreprocessed, TARGET_KEYPOINT_COLOR);
}
}
if (keypointsNonTargetClass.size() > 0) {
cv::drawKeypoints(imagePreprocessed, keypointsNonTargetClass, imagePreprocessed, NONTARGET_KEYPOINT_COLOR);
}
imwrite(imageOutputFilename.str(), imagePreprocessed);
}
}
}
cout << " -> Computed " << trainSamples.rows << " training samples from " << numberOfFiles << " images in " << performanceTimer.getElapsedTimeFormated() << "\n" << endl;
if (trainSamples.rows != trainLabels.rows || trainSamples.rows == 0 || trainLabels.rows == 0) {
cout << "\n !> Invalid training data!\n\n\n" << endl;
return false;
}
trainingDataOut.setTrainSamples(trainSamples);
trainingDataOut.setTrainLabels(trainLabels);
saveTrainingSamples(trainSamples);
saveTrainingLabels(trainLabels);
return true;
}
return false;
}
