File descriptions:

road_damage_dataset.tar.gz contains the image data and ground truth for the train set, and the image data for the test set. The image annotations are saved in XML files in PASCAL VOC format(http://host.robots.ox.ac.uk/pascal/VOC/voc2008/htmldoc/voc.html#SECTION00031000000000000000) Users can parse the annotations using the PASCAL Development Toolkit.

sample_submission.csv is the correct format of the submission file.
It contains two columns:

  • ImageId: the id of the test image, for example ILSVRC2012_test_00000001
  • PredictionString: the prediction string should be a space delimited of 5 integers. For example, Adachi_test_00000001 - PredictionString: the prediction string should be a space delimited of 5 integers. For example, 2 240 170 260 240 means it's label 2, with a bounding box of coordinates (x_min, y_min, x_max, y_max). We accept up to 5 predictions. For example, if you submit 3 42 24 170 186 1 292 28 430 198 4 168 24 292 190 5 299 238 443 374 2 160 195 294 357 6 3 214 135 356 which contains 6 bounding boxes, we will only take the first 5 into consideration.

Notes: The damage types are: [D00, D01, D10, D11, D20, D40, D43, D44]. The corresponding categorical values are indexes starting at 1 of the alphanumerical ordered damage types: [1, 2, 3, 4, 5, 6, 7, 8]. Also, although the image dataset contains "D30" (means "Rutting"), you don't have to predict "D30". That's because the number of D30 is quite few.