Authors:
Rodrigo Rill-García
1
;
2
;
Eva Dokladalova
2
and
Petr Dokládal
3
Affiliations:
1
Laboratoire Navier, Univ. Gustave Eiffel, CNRS, ENPC, Marne-la-Vallée, France
;
2
LIGM, Univ Gustave Eiffel, CNRS, ESIEE Paris, Marne-la-Vallée, France
;
3
Center for Mathematical Morphology, MINES Paris – PSL Research University, Fontainebleau, France
Keyword(s):
Transfer Learning, Image Generation, Crack Detection, Inaccurate Labels.
Abstract:
In crack detection, pixel-accurate predictions are necessary to measure the width – an important indicator of the severity of a crack. However, manual annotation of images to train supervised models is a hard and time-consuming task. Because of this, manual annotations tend to be inaccurate, particularly at pixel-accurate level. The learning bias introduced by this inaccuracy hinders pixel-accurate crack detection. In this paper we propose a novel tool aimed for synthetic image generation with accurate crack labels – Syncrack. This parametrizable tool also provides a method to introduce controlled noise to annotations, emulating human inaccuracy. By using this, first we do a robustness study of the impact of training with inaccurate labels. This study quantifies the detrimental effect of inaccurate annotations in the final prediction scores. Afterwards, we propose to use Syncrack to avoid this detrimental effect in a real-life context. For this, we show the advantages of using Syncra
ck generated images with accurate annotations for crack detection on real road images. Since supervised scores are biased by the inaccuracy of annotations, we propose a set of unsupervised metrics to evaluate the segmentation quality in terms of crack width.
(More)