• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.2
• /
• pp.786-799
• /
• 2021

Road damage detection is important for road maintenance. With the development of deep learning, more and more road damage detection methods have been proposed, such as Fast R-CNN, Faster R-CNN, Mask R-CNN and RetinaNet. However, because shallow and deep layers cannot be extracted at the same time, the existing methods do not perform well in detecting objects with fewer samples. In addition, these methods cannot obtain a highly accurate detecting bounding box. This paper presents a Multi-level Feature Pyramids method based on M2det. Because the feature layer has multi-scale and multi-level architecture, the feature layer containing more information and obvious features can be extracted. Moreover, an attention mechanism is used to improve the accuracy of local boundary boxes in the dataset. Experimental results show that the proposed method is better than the current state-of-the-art methods.

• KIISE Transactions on Computing Practices
• /
• v.24 no.2
• /
• pp.59-66
• /
• 2018

In this paper, we propose a system to detect various damage automatically inflicted on road pavement by collecting and analyzing data from acceleration and camera sensors in real time. The proposed system sends the collected images, acceleration signals, and GPS coordinates to the road manager and the database in the remote server, shortly after detecting the damage to the road pavement. Our study makes three key contributions. The proposed system 1) enables road managers to maintain road conditions quickly, accurately, and conveniently; 2) allows road mangers to take care of various kinds of damage to the road pavement at the initial stage; and finally 3) even makes it possible to track the damage, which suggests that the integration of a high-level decision support function becomes affordable. We tested the sensitivity and precision of the proposed system against real-time data obtained from the vehicles driving on the highway at an average speed of 100 km/h. With ten iterations, the proposed system achieved an average sensitivity of 74% and an average precision of 84% in road pavement damage detection, which is comparable with the best competing schemes.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.3
• /
• pp.95-105
• /
• 2019

In recent years, image processing techniques for detecting road surface damaged spot have been actively researched. Especially, it is mainly used to acquire images through a smart phone or a black box that can be mounted in a vehicle and recognize the road surface damaged region in the image using several algorithms. In addition, in conjunction with the GPS module, the exact damaged location can be obtained. The most important technology is image processing algorithm. Recently, algorithms based on artificial intelligence have been attracting attention as research topics. In this paper, we will also discuss artificial intelligence image processing algorithms. Among them, an object detection method based on an region-based convolution neural networks method is used. To improve the recognition performance of road surface damage objects, 600 road surface damaged images and 1500 general road driving images are added to the learning database. Also, supervised learning using background object recognition method is performed to reduce false alarm and missing rate in road surface damage detection. As a result, we introduce a new method that improves the recognition performance of the algorithm to 8.66% based on average value of mAP through the same test database.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.4
• /
• pp.95-105
• /
• 2021

Road surface damage detection is essential for a comfortable driving environment and the prevention of safety accidents. Road management institutes are using automated technology-based inspection equipment and systems. As one of these automation technologies, a sensor to detect road surface damage plays an important role. For this purpose, several studies on sensors using deep learning have been conducted in recent years. Road images and label images are needed to develop such deep learning algorithms. On the other hand, considerable time and labor will be needed to secure label images. In this paper, the adversarial learning method, one of the semi-supervised learning techniques, was proposed to solve this problem. For its implementation, a lightweight deep neural network model was trained using 5,327 road images and 1,327 label images. After experimenting with 400 road images, a model with a mean intersection over a union of 80.54% and an F1 score of 77.85% was developed. Through this, a technology that can improve recognition performance by adding only road images was developed to learning without label images and is expected to be used as a technology for road surface management in the future.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.2
• /
• pp.47-54
• /
• 2022

For safe driving of autonomous vehicles, road damage detection is very important to lower the potential risk. In order to ensure safety while an autonomous vehicle is driving on the road, technology that can cope with various obstacles is required. Among them, technology that recognizes static obstacles such as poor road conditions as well as dynamic obstacles that may be encountered while driving, such as crosswalks, manholes, hollows, and speed bumps, is a priority. In this paper, we propose a method to extract similarity of images and find damaged road images using OpenCV image processing and CNN algorithm. To implement this, we trained a CNN model using 280 training datasheets and 70 test datasheets out of 350 image data. As a result of training, the object recognition processing speed and recognition speed of 100 images were tested, and the average processing speed was 45.9 ms, the average recognition speed was 66.78 ms, and the average object accuracy was 92%. In the future, it is expected that the driving safety of autonomous vehicles will be improved by using technology that detects road obstacles encountered while driving.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.3
• /
• pp.106-118
• /
• 2019

In recent years, research and development on image object recognition using artificial intelligence have been actively carried out, and it is expected to be used for road maintenance. Among them, artificial intelligence models for object detection of road surface are continuously introduced. In order to develop such object recognition algorithms, a backbone network that extracts feature maps is essential. In this paper, we will discuss how to select the appropriate neural network. To accomplish it, we compared with 4 different deep neural networks using 6,000 road surface damage images. Based on three evaluation methods for analyzing characteristics of neural networks, we propose a method to determine optimal neural networks. In addition, we improved the performance through optimal tuning of hyper-parameters, and finally developed a light backbone network that can achieve 85.9% accuracy of road surface damage classification.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.4
• /
• pp.71-79
• /
• 2019

By using convolutional neural networks (CNNs) based on semantic segmentation, road surface damage detection has being studied. In order to generate the CNN model, it is essential to collect the input and the corresponding labeled images. Unfortunately, such collecting pairs of the dataset requires a great deal of time and costs. In this paper, we proposed a road surface damage detection technique based on semi-supervised learning using pseudo labels to mitigate such problem. The model is updated by properly mixing labeled and unlabeled datasets, and compares the performance against existing model using only labeled dataset. As a subjective result, it was confirmed that the recall was slightly degraded, but the precision was considerably improved. In addition, the $F_1-score$ was also evaluated as a high value.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.2
• /
• pp.104-113
• /
• 2019

The road management institute needs lots of cost to repair road surface damage. These damages are inevitable due to natural factors and aging, but maintenance technologies for efficient repair of the broken road are needed. Various technologies have been developed and applied to cope with such a demand. Recently, maintenance technology for road surface damage repair is being developed using image information collected in the form of a black box installed in a vehicle. There are various methods to extract the damaged region, however, we will discuss the image recognition technology of the deep neural network structure that is actively studied recently. In this paper, we introduce a new neural network which can estimate the road damage and its location in the image by region-based convolution neural network algorithm. In order to develop the algorithm, about 600 images were collected through actual driving. Then, learning was carried out and compared with the existing model, we developed a neural network with 10.67% accuracy.

• Smart Structures and Systems
• /
• v.16 no.6
• /
• pp.1049-1068
• /
• 2015

In the paper, the authors propose the application of operational deflection shapes (ODS) for the detection of structural changes in technical objects. The ODS matrix is used to formulate the spatial filter that is further used for damage detection as a classical modal filter (Meirovitch and Baruh 1982, Zhang et al. 1990). The advantage of the approach lies in the fact that no modal analysis is required, even on the reference spatial filter formulation and other components apart from structural ones can be filtered (e.g. harmonics of rotational velocity). The proposed methodology was tested experimentally on a laboratory stand, a frame-like structure, excited from two sources: an impact hammer, which provided a wide-band excitation of all modes, and an electro-dynamic shaker, which simulated a harmonic component in the output spectra. The damage detection capabilities of the proposed method were tested by changing the structural properties of the model and comparing the results with the original ones. The quantitative assessment of damage was performed by employing a damage index (DI) calculation. Comparison of the output of the ODS filter and the classical modal filter is also presented and analyzed in the paper. The closing section of the paper describes the verification of the method on a real structure - a road viaduct.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.14 no.1
• /
• pp.1-12
• /
• 2015

Intrusive Vehicle Detectors have excellent detection performance compared to other types of detector, but disadvantages of high installation and maintenance costs, short life time due to greater damage to roads and paving materials. In contrast, Non-Intrusive Vehicle Detectors attached to the stationary pole have advantages because it does not damage the road surface and easy and less expensive to maintain. Despite these advantages, Non-Intrusive type detectors are still not been widely used in traffic signal control systems because of the low detection performance. In this study, a FMCW(Frequency Modulated Continuous Wave) radar Vehicle Detector was designed as an alternative detector for the signalized intersection, and the performance evaluation was presented by purpose applicability.