Pixel-accurate road crack detection in presence of inaccurate annotations

Recent road crack detection methods obtain appealing scores but typically allow a few pixel tolerance margin. This is acceptable for locating cracks, but not for measuring their width (indicator of the cracks' severity). Our baseline model, U-VGG19, obtains an F-score of 71.77% on CrackForest, which is superior to other approaches when no tolerance is admitted. However, increasing the scores without tolerance is difficult due to inaccurate annotations. We propose a novel synthetic dataset, Syncrack, as a benchmark for the evaluation of training with inaccurate annotations. Our results show that inaccurate annotations have a detrimental impact on the F-measure, decreasing it by up to 20%. To overcome this, we study label noise correction techniques using weakly supervised learning. Training U-VGG19 with these corrected labels improves the results on Syncrack by up to 12%. Obtained results on the CrackForest and Aigle-RN datasets support that these approaches are useful for real-life data too. (c) 2022 Elsevier B.V. All rights reserved.

Automated summary

Recent road crack detection methods achieve high scores in crack localization but still show inaccuracies in crack width measurement. By introducing a synthetic dataset and label noise correction techniques, accuracy and robustness of crack detection can be improved to some extent.