NHA12D: A New Pavement Crack Dataset and a Comparison Study Of Crack Detection Algorithms

TL;DR

This paper introduces NHA12D, a comprehensive pavement crack dataset, and compares various crack detection algorithms, highlighting the strengths of U-Net with VGG-16 and identifying key challenges like false positives and the need for better concrete pavement detection.

Contribution

The paper presents a new annotated pavement crack dataset (NHA12D) with diverse images and provides a comparative analysis of state-of-the-art crack detection algorithms.

Findings

U-Net with VGG-16 performs best overall

High false-positive rate due to confusion with concrete joints

Significant room for improvement in concrete pavement crack detection

Abstract

Crack detection plays a key role in automated pavement inspection. Although a large number of algorithms have been developed in recent years to further boost performance, there are still remaining challenges in practice, due to the complexity of pavement images. To further accelerate the development and identify the remaining challenges, this paper conducts a comparison study to evaluate the performance of the state of the art crack detection algorithms quantitatively and objectively. A more comprehensive annotated pavement crack dataset (NHA12D) that contains images with different viewpoints and pavements types is proposed. In the comparison study, crack detection algorithms were trained equally on the largest public crack dataset collected and evaluated on the proposed dataset (NHA12D). Overall, the U-Net model with VGG-16 as backbone has the best all-around performance, but models generally fail to distinguish cracks from concrete joints, leading to a high false-positive rate. It also found that detecting cracks from concrete pavement images still has huge room for improvement. Dataset for concrete pavement images is also missing in the literature. Future directions in this area include filling the gap for concrete pavement images and using domain adaptation techniques to enhance the detection results on unseen datasets.