Citation: Li, P.; Xia, H.; Zhou, B.; Yan,
F.; Guo, R. A Method to Improve the
Accuracy of Pavement Crack
Identification by Combining a
Semantic Segmentation and Edge
Detection Model. Appl. Sci. 2022, 12,
4714. https://doi.org/10.3390/
app12094714
Academic Editor: Luís Picado
Santos
Received: 24 March 2022
Accepted: 4 May 2022
Published: 7 May 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
A Method to Improve the Accuracy of Pavement Crack
Identification by Combining a Semantic Segmentation
and Edge Detection Model
Peigen Li
1
, Haiting Xia
1,2,
* , Bin Zhou
3
, Feng Yan
1
and Rongxin Guo
1
1
Yunnan Key Laboratory of Disaster Reduction in Civil Engineering,
Faculty of Civil Engineering and Mechanics, Kunming University of Science and Technology,
Kunming 650500, China; pgli@stu.kust.edu.cn (P.L.); yanfengkmust@163.com (F.Y.); guorx@kust.edu.cn (R.G.)
2
Faculty of Civil Aviation and Aeronautics, Kunming University of Science and Technology,
Kunming 650500, China
3
Yunnan Jiantou Boxin Engineering Construction Center Test Co., Ltd., Kunming 650217, China;
fang@stu.kust.edu.cn
* Correspondence: haiting.xia@kust.edu.cn
Abstract:
In recent years, deep learning-based detection methods have been applied to pavement
crack detection. In practical applications, surface cracks are divided into inner and edge regions for
pavements with rough surfaces and complex environments. This creates difficulties in the image
detection task. This paper is inspired by the U-Net semantic segmentation network and holistically
nested edge detection network. A side-output part is added to the U-Net decoder that performs edge
extraction and deep supervision. A network model combining two tasks that can output the semantic
segmentation results of the crack image and the edge detection results of different scales is proposed.
The model can be used for other tasks that need both semantic segmentation and edge detection.
Finally, the segmentation and edge images are fused using different methods to improve the crack
detection accuracy. The experimental results show that mean intersection over union reaches 69.32 on
our dataset and 61.05 on another pavement dataset group that did not participate in training. Our
model is better than other detection methods based on deep learning. The proposed method can
increase the MIoU value by up to 5.55 and increase the MPA value by up to 10.41 when compared to
previous semantic segmentation models.
Keywords: convolutional neural network; crack detection; semantic segmentation; edge detection
1. Introduction
Highway pavements are affected by many factors such as the natural environment,
load conditions, structural combinations, materials, construction techniques, and technical
levels, which can produce various types of distress. With the construction of highways,
pavement maintenance has begun increasing sharply. Accurate pavement distress detection
results can provide reliable and effective technical support for pavement maintenance
management decision making, improve highway pavement service performance, and
reduce traffic accidents. However, traditional manual detection methods are often affected
by subjective judgment in detecting highway pavement distress. There were considerable
errors and low detection efficiencies. Therefore, automatic distress recognition and feature
measurement of collected pavement images are the mainstream means of pavement detection.
The adoption of information management technology is an inevitable way to improve
the level of highway maintenance management and realize efficient and orderly organiza-
tion and management. For example, for common cracks on the highway, the development
of an effective pavement crack identification algorithm can evaluate the pavement condition
in advance and provide the basic data for maintenance decision making for the highway
Appl. Sci. 2022, 12, 4714. https://doi.org/10.3390/app12094714 https://www.mdpi.com/journal/applsci
