scholarly journals Road Surface Crack Detection Method Based on Conditional Generative Adversarial Networks

Sensors ◽  
2021 ◽  
Vol 21 (21) ◽  
pp. 7405
Author(s):  
Anastasiia Kyslytsyna ◽  
Kewen Xia ◽  
Artem Kislitsyn ◽  
Isselmou Abd El Kader ◽  
Youxi Wu
Keyword(s):  
Mathematical Analysis ◽  
Surface Crack ◽  
Crack Detection ◽  
Road Construction ◽  
Target Object ◽  
Road Surface ◽  
Generative Adversarial Networks ◽  
Safety Level ◽  
The Road ◽  
Adversarial Networks

Constant monitoring of road surfaces helps to show the urgency of deterioration or problems in the road construction and to improve the safety level of the road surface. Conditional generative adversarial networks (cGAN) are a powerful tool to generate or transform the images used for crack detection. The advantage of this method is the highly accurate results in vector-based images, which are convenient for mathematical analysis of the detected cracks at a later time. However, images taken under established parameters are different from images in real-world contexts. Another potential problem of cGAN is that it is difficult to detect the shape of an object when the resulting accuracy is low, which can seriously affect any further mathematical analysis of the detected crack. To tackle this issue, this paper proposes a method called improved cGAN with attention gate (ICGA) for roadway surface crack detection. To obtain a more accurate shape of the detected target object, ICGA establishes a multi-level model with independent stages. In the first stage, everything except the road is treated as noise and removed from the image. These images are stored in a new dataset. In the second stage, ICGA determines the cracks. Therefore, ICGA focuses on the redistribution of cracks, not the auxiliary elements in the image. ICGA adds two attention gates to a U-net architecture and improves the segmentation capacities of the generator in pix2pix. Extensive experimental results on dashboard camera images of the Unsupervised Llamas dataset show that our method has better performance than other state-of-the-art methods.

scholarly journals CNN-Based Road-Surface Crack Detection Model That Responds to Brightness Changes

Electronics ◽  
2021 ◽  
Vol 10 (12) ◽  
pp. 1402
Author(s):  
Taehee Lee ◽  
Yeohwan Yoon ◽  
Chanjun Chun ◽  
Seungki Ryu
Keyword(s):  
Surface Crack ◽  
Autonomous Vehicles ◽  
Crack Detection ◽  
Model Performance ◽  
Semantic Segmentation ◽  
Road Surface ◽  
Image Brightness ◽  
The Road ◽  
Detection Model ◽  
Artificial Intelligence Models

Poor road-surface conditions pose a significant safety risk to vehicle operation, especially in the case of autonomous vehicles. Hence, maintenance of road surfaces will become even more important in the future. With the development of deep learning-based computer image processing technology, artificial intelligence models that evaluate road conditions are being actively researched. However, as the lighting conditions of the road surface vary depending on the weather, the model performance may degrade for an image whose brightness falls outside the range of the learned image, even for the same road. In this study, a semantic segmentation model with an autoencoder structure was developed for detecting road surface along with a CNN-based image preprocessing model. This setup ensures better road-surface crack detection by adjusting the image brightness before it is input into the road-crack detection model. When the preprocessing model was applied, the road-crack segmentation model exhibited consistent performance even under varying brightness values.

scholarly journals NEURAL FUZZY NETWORK FOR ASSESSING TECHNOLOGICAL SOLUTIONS FOR FOREST ROADS

2020 ◽  
Vol 10 (3) ◽  
pp. 95-103
Author(s):  
Vladimir Pobedinskiy ◽  
Sergey Buldakov ◽  
Andrey Berstenev ◽  
Elena Anastas
Keyword(s):  
Neural Network ◽  
Intelligent Systems ◽  
Information Technologies ◽  
Rapid Assessment ◽  
Road Construction ◽  
Road Surface ◽  
Forest Roads ◽  
The Road ◽  
Logging Roads ◽  
Fuzzy Network

The article is devoted to the problem of improving road construction technologies, in particular, technological solutions for logging roads. As you know, in road construction, the choice and justification of technological solutions for the road surface is one of the first stages of design, the efficiency of which affects further project as a whole, timing and costs of construction. The solution to such a problem is extremely difficult and, first of all, due to the many interrelated parameters, factors, as well as the uncertainties of data in the problem. The task becomes much more complicated when it is also necessary to take into account the economic indicators of road construction project. But it is in this form that it is of the greatest interest, since these characteristics are often the most important in practice. For these reasons, the problem remains completely unsolved. Therefore, requires further research, as noted, taking into account the uncertainties in the problem. Intelligent systems based on the theory of fuzzy sets, neural networks and their hybrid solutions are proposed for this class of problems, as a result of modern achievements in the field of mathematics and information technologies. Thus, the purpose of this research was to develop a neural network for evaluating technological solutions for logging roads. The result of the research was the development of an adaptive neuro-fuzzy network such as ANFIS, which allows calculating the cost of the road surface depending on the main technological and initial financial parameters. The neural network can be recommended for the design of forest roads, as well as for rapid assessment of the effectiveness of various technological solutions during competitive (tender) selection.

scholarly journals An Automatic Detection by Classification of Cracked Pixels or Noncracked Pixels in Road Surface

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Khaddouj Taifi ◽  
Naima Taifi ◽  
Es-said Azougaghe ◽  
Said Safi
Keyword(s):  
Wavelet Transforms ◽  
Crack Detection ◽  
Automatic Detection ◽  
Detection Algorithm ◽  
Essential Elements ◽  
Road Surface ◽  
Discrete Wavelet ◽  
Second Phase ◽  
The Road

Automatic detection and monitoring of the condition of cracks in the road surface are essential elements to ensure road safety and quality of service. A crack detection method based on wavelet transforms (2D-DWT) and Jerman enhancement filter is used. This paper presents different contributions corresponding to the three phases of the proposed system. The first phase presents the contrast enhancement technique to improve the quality of roads surface image. The second phase proposes an effective detection algorithm using discrete wavelet (2D-DWT) with “db8” and two-level sub-band decomposition. Finally, in the third phase, the Jerman enhancement filter is usually used with different parameters of the control response uniformity “ τ ” to enhance for cracks detection. The experimental results in this article provide very powerful results and the comparisons with five existing methods show the effectiveness of the proposed technique to validate the recognition of surface cracks.

scholarly journals Non-autoclaved foam concrete for layers of highways surface dressing

2020 ◽  
Vol 2020 (2) ◽  
pp. 35-41
Author(s):  
Iryna Hornikovska ◽  
◽  
Vadym Kahanov ◽  
Keyword(s):  
Operating Cost ◽  
Road Construction ◽  
Road Surface ◽  
Transport Infrastructure ◽  
Foam Concrete ◽  
Insulating Material ◽  
The Road ◽  
Effective Heat ◽  
Geographical Regions ◽  
Pavement Structure

The article is devoted to the problems associated freeze with the calculated estimation of the parameters of the structural and heat-insulating antifreeze layer in the subgrade of non-rigid roads on various soil bases. The main physical, technical and deformation characteristics of monolithic dispersed non-autoclaved foam concrete reinforced with polypropylene fiber of grades of density from 600 to 1000 kg/m3 are investigated. Freezing of subsoil waters directly under the roadway pavement and, as a result, its increase in volume, leads to significant deformations of the road surface. Under such conditions, the period of defectfree operation of the roadway pavement is significantly reduced, which in turn leads to the need to repair it in a more intensive mode. One of the ways to reduce the operating cost and maintenance costs of the road transport infrastructure is to introduce into the design and construction practice new structural concepts for road surface dressing that ensure high quality pavement during the normative operational period. This can be achieved by introducing an effective heat-insulating material into the pavement structure as an anti-frost layer in order to elimi-nate the effect of frost lift of the roadway pavement of non-rigid roads. Since domestic and foreign experience freeze in the road construction has proven the effectiveness of the use of heatinsulating materials in the road surface dressing construction, in recent years in Ukraine there has been increased interest in the use of non-autoclaved foam concrete as a modern and highly effective heat-insulating material in road construction. The installation of a heat-insulating layer made of non-autoclaved foam concrete allows us to completely or partially prevent freezing or overheating of the surface dressing base, reduce the influence of periodic variations in environmental temperature, which in turn will increase the durability of the pavement structure. The publication presents nomograms for determining the optimal thickness of the heat-insulating anti-frost heavy course (layer) of road surface dressing (based on sand, loamy sand, clay and loam) done at the street and road network for all climatic and geographical regions of Ukraine.

Road Surface Crack Detection: An Implementation of Various Edge Detection Methods

2020 ◽  
Author(s):  
Ramesh Kulkarni ◽  
Kavita Tewari ◽  
Anandalakshmi Kumar ◽  
Sayali Gogate ◽  
Vinita Chanchlani
Keyword(s):  
Edge Detection ◽  
Surface Crack ◽  
Crack Detection ◽  
Road Surface ◽  
Detection Methods

Analisis Gradasi Penggunaan Material Agregat Base Class A Spesifikasi BinaMarga 2010 Rev 3 Proyek Pelebaran Jalan Sp. Ujung Aji – Batas Kota Kabanjahe

2019 ◽  
Vol 3 (1) ◽  
Author(s):  
Brian Baya Sembiring. ST ◽  
Parada Afkiki Eko Saputra, ST,MT
Keyword(s):  
Road Construction ◽  
Analysis Data ◽  
Road Surface ◽  
The Road ◽  
Class A ◽  
On The Road ◽  
Observation Method ◽  
The Right ◽  
The Given ◽  
Filter Analysis

Road is a land transportation infrastructure that covers all parts of the road, including complementary buildings and equipment intended for traffic. Road Structure Improvement is one project that aims to improve the quality of roads. As the object of work to be studied is the widening of the sp. Ujung Aji - Limits of the City of Kabanjahe. Road construction with a flexible layered pavement with cover or without overlays is usually often damaged such as: cracks, hollows, bumps on the road surface. In other conditions it is often seen that the grooves of the former water flow to the subgrade are visible. The situation is more extreme and often occurs, namely the road surface peels to reach the foundation layer, so that the aggregate looks scattered. This study uses the direct observation method in the widening project of Jalan Simpang Ujung Aji - Bts. Kabanjahe City. This research was carried out at the time of laying and compaction of the bottom road foundation layer such as Base B and Base A. Activities carried out included data collection, data processing, analysis and observations in the Laboratory. The results of the filter analysis of rough gradations are good, which is in the middle between the given gradation boundaries, does not coincide and does not come out of the given gradation limit. Based on aggregate filter analysis data, it can be concluded that the results of the gradation of aggregate class A percent are retained and passed the filter in accordance with the general specifications of Bina Marga 2010 revision 3 and according to class A aggregate planning. the specimen is completely waterless, so the weighing results in the right balance.

Sign in / Sign up

Export Citation Format

Share Document