• The Journal of Society for e-Business Studies
• /
• v.26 no.1
• /
• pp.93-106
• /
• 2021

Many recent studies on deep learning-based road crack detection have shown significantly more improved performances than previous works using algorithm-based conventional approaches. However, many deep learning-based studies are still focused on classifying the types of cracks. The classification of crack types is highly anticipated in that it can improve the crack detection process, which is currently relying on manual intervention. However, it is essential to calculate the severity of the cracks as well as identifying the type of cracks in actual pavement maintenance planning, but studies related to road crack detection have not progressed enough to automated calculation of the severity of cracks. In order to calculate the severity of the crack, the type of crack and the area of the crack in the image must be identified together. This study deals with a method of using Mobilenet-SSD that is deep learning-based object detection techniques to effectively automate the simultaneous detection of crack types and crack areas. To improve the accuracy of object-detection for road cracks, several experiments were conducted to combine the U-Net for automatic segmentation of input image and object-detection model, and the results were summarized. As a result, image masking with U-Net is able to maximize object-detection performance with 0.9315 mAP value. While referring the results of this study, it is expected that the automation of the crack detection functionality on pave management system can be further enhanced.

• International Journal of Highway Engineering
• /
• v.19 no.2
• /
• pp.45-53
• /
• 2017

PURPOSES: The objectives of this study are to develop a new cold-applied crack sealant and to evaluate its properties and field applicability by comparing with other conventionally used crack sealants. METHODS : A new cold-applied crack sealant was developed by using neoprene latex to improve material properties. The fundamental properties such as viscosity, residue %, penetration, and softening point of the developed crack sealant were tested by TxDOT criteria to evaluate crack sealing capability. Moreover, the performance of the developed cold-applied crack sealant was evaluated under both laboratory and field conditions. In the laboratory, the bond property was evaluated using the developed cold-applied crack sealant and conventional hot-applied crack sealant by the bond-properties test standardized under ASTM D 6690. In the field, test sections were constructed on three areas: a trunk road, bus-only lane, and motorway, with the developed crack sealant and three conventional crack sealants. After construction, early field-inspection was performed on the test sections. RESULTS AND CONCLUSIONS : Overall, the developed cold-applied crack sealant demonstrates reasonable storage stability, durability, and bond property compared to conventional hot-applied crack sealants. From the test sections, it was established that the developed cold-applied crack sealant does not pose construction issues. Moreover, the early performance was verified through field inspection. However, as the field inspection was conducted a week after the construction, it is necessary to conduct an inspection of performance from a long-term point of view.

• Journal of Korean Society for Geospatial Information Science
• /
• v.10 no.4 s.22
• /
• pp.77-84
• /
• 2002

Recently, damage of pavement represented by crack is depened by the increase of traffic demand up to ten million and wight, and interest about the efficient management of pavement is being increased gradually according to the growth of maintenance expense of road surface. In this study, the possibility of application for acquisition of crack information was tested by appling DCRP and digital image processing technique and measuring crack on road surface precisely. Based on this, objective and efficient road surface measurement was planned and done. Measuring crack width, acquire result of comparative high accuracy. So, it is considered that it can be utilized as plan draft data for deterioration estimation and repair reinforcement work of pavement.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.6
• /
• pp.155-163
• /
• 2019

This paper proposes a new methodology to recognize cracks on asphalt road surfaces using the image data obtained with drones. The target section was Yuseong-daero, the main highway of Daejeon. Furthermore, two object detection algorithms, such as Tiny-YOLO-V2 and Faster-RCNN, were used to recognize cracks on road surfaces, classify the crack types, and compare the experimental results. As a result, mean average precision of Faster-RCNN and Tiny-YOLO-V2 was 71% and 33%, respectively. The Faster-RCNN algorithm, 2Stage Detection, showed better performance in identifying and separating road surface cracks than the Yolo algorithm, 1Stage Detection. In the future, it will be possible to prepare a plan for building an infrastructure asset-management system using drones and AI crack detection systems. An efficient and economical road-maintenance decision-support system will be established and an operating environment will be produced.

• 한국도로학회:학술대회논문집
• /
• 2006.03a
• /
• pp.97-104
• /
• 2006

• Journal of Institute of Control, Robotics and Systems
• /
• v.11 no.4
• /
• pp.337-343
• /
• 2005

In this paper, experimental studies of force control of the crack tracking robot are presented. The crack tracking robot should maintain constant contact with the road to perform cleaning process of the crack effectively. Regulating desired force on the road requires a sophisticated force control algorithm. Here, two main force control algorithms such as the impedance force control and the explicit force control are used. Performances of two force control algorithms are compared.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.5
• /
• pp.133-148
• /
• 2022

In this study, a road pavement crack deterioration model was developed for a pavement road sections of the Sejong-city. Data required for model development were acquired using a deep learning-based road asset monitoring system. Road pavement monitoring was conducted on the same sections in 2021 and 2022. The developed model was analyzed by dividing it into a method for estimating the annual average amount of deterioration and a method based on Bayesian Markov Mixture Hazard model. As a result of the analysis, it was found that an analysis results similar to the crack deterioration model developed based on the data acquired from the Automatic pavement investigation equipmen was derived. The results of this study are expected to be used as basic data by local governments to establish road management plans.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2003.05a
• /
• pp.1053-1060
• /
• 2003

The temperature variation of the concrete pavement in the early age significantly affects the initiation and propagation of its early age cracks. This implies that the measurement and analysis of early age temperature trend are necessary to examine the causes of early age cracks in the concrete pavement. In this study, it is investigated how the early age temperature trend in the concrete pavement affects the random crack initiation and behaviors of saw-cut joints using the actual construction site which is located at the KHC test road. During 72 hours after placing the concrete pavement, the ambient air temperature and temperatures at the top, middle, and bottom in the concrete pavement were measured and the random crack initiation in concrete slabs and early age behaviors in the joints were surveyed. The investigation results indicate that the first random crack was initiated at one of the slabs placed in the early morning which have higher temperature changes during early 72 hours. In addition, the joints that were saw-cut in the morning were cracked more rapidly than those saw-cut in the afternoon.

• International Journal of Highway Engineering
• /
• v.18 no.2
• /
• pp.43-49
• /
• 2016

PURPOSES : The field application and performance of continuously reinforced concrete pavement (CRCP), constructed by using the mechanical tube-feeding method, are evaluated in this study. METHODS: The location of the rebar was evaluated by using the MIRA system. The early-age CRCP performance was evaluated via visual survey, in which the crack spacing and crack width were examined. RESULTS: The location of longitudinal reinforcing bars was evaluated via MIRA testing and the results showed that the longitudinal rebars all lie within a given tolerance limit (${\pm}2.5cm$) of the target elevation. In addition, owing to the low temperature when the concrete was pured, the crack spacing in the Dae-Gu direction is slightly wider than that of the Gwang-Ju direction. Almost all of the crack spacings lay within the range of 1.0 m~3.0 m. A crack width of <0.3 mm was measured at the pavement surface. However, as revealed by the field survey, the crack spacing was not correlated with the crack width. CONCLUSIONS : In CRCP constructed by using the mechanical tube-feeding method, almost all of the longitudinal reinforcing bars lay within the tolerance limit (2.5 cm) of the target elevation. The concrete-placing temperature affects the crack spacing, owing to variations in the zero-stress temperature. Crack survey results show that there is no correlation between the crack spacing and crack width in CRCP.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.3
• /
• pp.467-475
• /
• 2018

The purpose of this study is to propose the evaluation criteria of asphalt pavement condition in narrow regional road considering the traffic environment in order to reduce road budget of local governments. In general, narrow regional roads are considered relatively less important because they have low travel speed and low traffic volume of heavy-vehicle. Generally, automatic surveying equipment is used for investigations of pavement condition, but the operating costs are not efficient for the narrow regional roads because the cost is too high. This study presents the pavement condition evaluation index suitable for narrow regional roads. In this study, the pavement condition evaluation index is presented considering the traffic environment of narrow regional roads. The pavement condition were classified into three classes based on the crack measured by visual inspection, and the validity of the pavement condition evaluation index presented through the expert's questionnaire survey was examined. Pavement condition for the narrow regional roads was classified into three grades based on the index values calculated by visual inspection. Expert's surveys were conducted to evaluate the validity of the proposed pavement condition evaluation. The proposed evaluation index shows a high correlation with questionnaire survey result ($R^2=0.88$). The proposed evaluation index which is obtained through visual crack inspection under limited conditions can be applied to narrow regional roads. In addition, it is expected that it will be effective not only for road management but also for road management budget by more economical evaluation method of pavement condition.