int main(int argc, char** argv)
{
const char *filename = argc > 1 ? argv[2] : "cells.png";
file_open = filename;
cv::Mat src;
src = cv::imread(filename, 0);
if(src.empty()){
help();
std::cout << "can not open " << filename << std::endl;
return -1;
}
//Load image for display
IplImage *img0;
img0 = cvLoadImage(filename, CV_LOAD_IMAGE_GRAYSCALE);
//Create main window and set mouse call back if mouse event and display
cvNamedWindow("Source", CV_WINDOW_AUTOSIZE);
cvShowImage("Source", img0);
rows = src.rows;
cols = src.cols;
cv::Mat BinImPad;
BinImPad = cvCreateMat((rows+2),(cols+2),src.type());
cv::Mat BinIm;
BinIm = cvCreateMat(cols,rows,src.type());
//Create the default display with logpol at the center of the image
computebin(src, BinImPad, BinIm);
computeLabels(src, BinImPad);
//cv::imshow("Binary Image", BinIm);
while(1) {
//Wait for keyboard input
char key = cvWaitKey(0);
//Key pressed, quit the program
if ( key ) break;
}
return 0;
}
/************************************************************************************************
* Start Function function *
************************************************************************************************/
string PlaceRecognition::startPlaceRecognition(CFeatureExtraction fext)
{
ofstream training_file;
CTicTac feature_time;
feature_time.Tic();
/// stores the labels for the i'th image instance for training and testing
/// images
int training_labels[len_training];
int testing_labels[len_testing];
/// The training model is built here all features are extracted in this
/// part, takes 30 seconds for 900+900 images
if (!trained_flag)
{
for (int i = 0; i < len_training; i++)
{
training[i].loadFromFile(training_paths.at(i));
fext.detectFeatures(training[i], feats_training[i], 0, numFeats);
fext.computeDescriptors(
training[i], feats_training[i], desc_to_compute);
}
for (int i = 0; i < len_testing; i++)
{
testing[i].loadFromFile(testing_paths.at(i));
fext.detectFeatures(testing[i], feats_testing[i], 0, numFeats);
fext.computeDescriptors(
testing[i], feats_testing[i], desc_to_compute);
}
trained_flag = true;
feats_testing_org = feats_testing;
} /// end of if feature extraction flag (trained flag)
CTicTac label_time;
label_time.Tic();
computeLabels(training_paths, training_count, training_labels);
computeLabels(testing_paths, testing_count, testing_labels);
int len_train_words;
len_train_words = 0;
// int len_test_words = 0;
for (int i = 0; i < len_training; i++)
len_train_words += feats_training[i].size();
if (!training_file_written_flag)
{
training_words2 = new vector<float>[len_train_words];
training_words1 = new vector<uint8_t>[len_train_words];
}
int training_word_labels[len_train_words];
CTicTac training_time;
training_time.Tic();
training_file.open("training_images_features.txt");
if (!training_file_written_flag)
{
training_file.clear();
int kount = 0;
for (int i = 0; i < len_training; i++)
{
training_file << feats_training[i].size();
for (unsigned int j = 0; j < feats_training[i].size(); j++, kount++)
{
if (descriptor_selected == 0)
{
vector<uint8_t> temp_feat;
temp_feat =
feats_training[i].getByID(j).get()->descriptors.SIFT;
training_words1[kount] =
feats_training[i].getByID(j).get()->descriptors.SIFT;
training_word_labels[kount] = training_labels[i];
for (unsigned int k = 0; k < temp_feat.size(); k++)
training_file << (int)temp_feat.at(k) << " ";
}
else if (descriptor_selected == 1)
{
vector<float> temp_feat;
temp_feat =
feats_training[i].getByID(j).get()->descriptors.SURF;
training_words2[kount] =
feats_training[i].getByID(j).get()->descriptors.SURF;
training_word_labels[kount] = training_labels[i];
for (unsigned int k = 0; k < temp_feat.size(); k++)
{
training_file << temp_feat.at(k) << " ";
}
}
else if (descriptor_selected == 2)
{
vector<float> temp_feat;
temp_feat =
feats_training[i].getByID(j).get()->descriptors.SpinImg;
training_words2[kount] =
feats_training[i].getByID(j).get()->descriptors.SpinImg;
training_word_labels[kount] = training_labels[i];
for (unsigned int k = 0; k < temp_feat.size(); k++)
{
training_file << temp_feat.at(k) << " ";
}
}
else if (descriptor_selected == 3)
;
// //!< Polar image descriptor
else if (descriptor_selected == 4)
;
// //!< Log-Polar image descriptor
else if (descriptor_selected == 5)
{
vector<uint8_t> temp_feat;
temp_feat =
feats_training[i].getByID(j).get()->descriptors.ORB;
training_words1[kount] =
feats_training[i].getByID(j).get()->descriptors.ORB;
training_word_labels[kount] = training_labels[i];
for (unsigned int k = 0; k < temp_feat.size(); k++)
{
int temp_var; //= (int) temp_feat.at(k);
temp_var = (int)training_words1[kount].at(k);
training_file << temp_var << " ";
}
}
else if (descriptor_selected == 6)
{
vector<uint8_t> temp_feat;
temp_feat =
feats_training[i].getByID(j).get()->descriptors.BLD;
training_words1[kount] =
feats_training[i].getByID(j).get()->descriptors.BLD;
training_word_labels[kount] = training_labels[i];
for (unsigned int k = 0; k < temp_feat.size(); k++)
training_file << (int)temp_feat.at(k) << " ";
}
else if (descriptor_selected == 7)
{
vector<uint8_t> temp_feat;
temp_feat =
feats_training[i].getByID(j).get()->descriptors.LATCH;
training_words1[kount] =
feats_training[i].getByID(j).get()->descriptors.LATCH;
training_word_labels[kount] = training_labels[i];
for (unsigned int k = 0; k < temp_feat.size(); k++)
training_file << (int)temp_feat.at(k) << " ";
}
training_file << " #" << training_labels[i] << " $"
<< training_word_labels[kount] << endl;
} // end of inner for loop for number of key-points
} // end of outer for loop for number of images
training_file.close();
// testing_file.close();
this->training_words_org = training_words2;
this->training_words_org2 = training_words1;
this->training_word_labels_org = training_word_labels;
training_word_labels_org = new int[kount];
for (int i = 0; i < kount; i++)
{
training_word_labels_org[i] = training_word_labels[i];
}
this->total_vocab_size_org = len_train_words;
this->training_file_written_flag = true;
} // end of writting training features to a file
CTicTac testing_time;
testing_time.Tic();
/// now extracting features for Place Recognition for testing dataset
int predicted_classes[len_testing];
CTicTac time_prediction;
time_prediction.Tic();
int predicted_Label = 1;
if (descriptor_selected == 1)
predicted_Label = predictLabel(
feats_testing_org, training_words_org, training_word_labels_org,
total_vocab_size_org, current_index_test_image);
else
predicted_Label = predictLabel2(
feats_testing_org, training_words_org2, training_word_labels_org,
total_vocab_size_org, current_index_test_image);
current_index_test_image++;
/// use a bag of words kind of framework here
predicted_classes[current_index_test_image] = predicted_Label;
if (predicted_classes[current_index_test_image] ==
testing_labels[current_index_test_image])
correct++;
else
incorrect++;
stringstream output;
output << endl
<< endl
<< "PLACE RECOGNITION RESULTS " << endl
<< endl
<< "actual label : "
<< findPlaceName(
testing_labels[current_index_test_image % len_testing])
<< ".\n"
<< endl
<< " predicted label : " << findPlaceName(predicted_Label) << ".\n"
<< endl
<< " correct = " << correct << " incorrect = " << incorrect << ".\n"
<< " Current Accuracy: "
<< 100.00 * (double)correct / (double)(incorrect + correct) << " % "
<< endl
<< " image " << current_index_test_image << " of " << len_testing
<< endl;
return output.str();
}
