TrueDeep: A systematic approach of crack detection with less data

TL;DR

This paper presents a domain knowledge-guided deep learning approach for crack detection that achieves high performance with significantly less annotated data, reducing costs and energy consumption.

Contribution

It introduces a method combining domain knowledge with deep learning to reduce data requirements for crack segmentation tasks.

Findings

Achieves comparable performance with only 23% of data

Significantly improves results on multiple blind datasets

Reduces annotation and training costs

Abstract

Supervised and semi-supervised semantic segmentation algorithms require significant amount of annotated data to achieve a good performance. In many situations, the data is either not available or the annotation is expensive. The objective of this work is to show that by incorporating domain knowledge along with deep learning architectures, we can achieve similar performance with less data. We have used publicly available crack segmentation datasets and shown that selecting the input images using knowledge can significantly boost the performance of deep-learning based architectures. Our proposed approaches have many fold advantages such as low annotation and training cost, and less energy consumption. We have measured the performance of our algorithm quantitatively in terms of mean intersection over union (mIoU) and F score. Our algorithms, developed with 23% of the overall data; have a similar performance on the test data and significantly better performance on multiple blind datasets.