Creating Test Dataset Using utils/gen_real_data.py

[nayeemiiitd]

For creating test dataset, the code calls a method query_gt_test_set() which require correspondence's mat files. What these files contains and how can we create them ?

def query_gt_test_set():
  label_path = '/Earthbyte/tynguyen/real_rawdata/joe_data/test/labels/'
  mat_file_name_list = [label_path+'corresponences0_10.mat',
                        label_path+'correspondences11_21.mat',
                        label_path+'correspondences22_30.mat',
                        label_path+'correspondences31_40.mat',
                        label_path+'correspondences41_49.mat']
  for i in range(len(mat_file_name_list)):
    gt_array = io.loadmat(mat_file_name_list[i])
    corr1_array = gt_array['all_corr1']
    corr2_array = gt_array['all_corr2']
    if i == 0:
      complete_corr_array1 = corr1_array
      complete_corr_array2 = corr2_array
    else:
      complete_corr_array1 = np.concatenate((complete_corr_array1, corr1_array), axis=0)
      complete_corr_array2 = np.concatenate((complete_corr_array2, corr2_array), axis=0)
  # Return 200x2, 200x2 arrays.
  # To query 4 points on the first image, do:
  # complete_corr_array1[image_index*4:(image_index + 1)*4] => 4x2
  return complete_corr_array1, complete_corr_array2

[tyunist]

Hi there,

This is for our aerial image dataset. Each .mat file contains four correspondences for some pairs of input images.
Since we cannot provide this dataset which belongs to a private company, you might not need to use this function.
We also recommend an alternative aerial image dataset in README.md.
Essentially, the output of this function (query_gt_test_set()) is two 200x2 arrays:
complete_corr_array1: four points on the first image
complete_corr_array2: corresponding four points on the second image.

You can create a test set by finding 4 point correspondences for every pair of test images.