PURPOSES: In this study, algorithms were proposed for determining the crack condition of an asphalt pavement image using deep learning methods. METHODS: For the configuration of a deep learning network, the study used a Convolution Neural Network and You Only Look Once algorithms. To obtain input data for analysis, a camera was mounted on the bonnet of the vehicle to obtain images of asphalt pavement and to mark the ground-truth cracks in the asphalt pavement image. In addition, an algorithm suitable for the automatic determination function of Deep Learning was proposed in order to calculate the crack ratio and crack rating. RESULTS: The result of analysis showed that the recall rate of cracks in this system was higher from FPPW 5.0E-06 to 96.03%. Furthermore, the accuracy of the grading system was found to be 100%, enabling the determination of very accurate ratings. The rate of processing per image was 0.4448 seconds on average, and the real-time analysis of pavement images presented no problem because the assessment took place within a short time. CONCLUSIONS : Applying this system to the pavement management system is expected to reduce the time required in finishing work and to determine a quantitative crack rating.

현재의 도로설계기준은 안전주행을 위한 최소한의 요건만을 제시하고 있기 때문에 이 설계기준에 따라 건설된 도로는 운전자가 주행 중 기대하는 구조 및 환경을 충분히 반영하였다고 보기 어렵다. 따라서 한국건설기술연구원에서는 포로의 안전성을 평가하고 주행안전성을 제고하기 위해 도로안전성 조사분석차량을 개발하고 있다. 본 논문에서는 이 차량에 탑재된 다양한 자료수집 장비 중 일정거리간격으로 디지털 영상을 취득하는 영상취득시스템에 중점을 두고 기술하였다. 영상취득시스템은 도로 및 주변시설물을 운전자의 시점에서 촬영하는 전방카메라와 차선추출을 위해 차량의 좌우에서 도로면을 촬영하는 측하방카메라, 일정거리간격으로 영상촬영 신호를 발생하는 동기화장치로 이루어져 있다. 각 영상은 위치정보와 함께 저장되므로 전방영상은 길어깨 폭 측정 등의 기하구조 계산에 사용되고. 측하방영상은 도로의 선형을 대표하는 중앙차선을 추출하는데 유용하게 사용될 수 있을 것으로 판단된다.

Recently, road maintenance is important for road performance and longevity in accordance with the increase of road infrastructure, so research on efficient damage detection has been actively carried out. In this study, we developed a technology to automatically detect the cracks on the highway road surface by using the road surface image of UAV and deep learning based object detection technology, which was applied to the actual highway image to verify its performance.

Recently, there has been frequent shortage of expansion joint in expressway bridges. When that happens, maintenance budgets will be overloaded and not effective, so it is not easy to come up with a solution. In this study, we introduce a bridge inspection system that combines laser image sensing technology and automatic control technology, which have been recently applied in various fields. And this system was developed to measure bridge extension joints while traveling more than 80km/h.

Crosswalk detection is an important part of the Pedestrian Protection System in autonomous vehicles. Different methods of crosswalk detection have been introduced so far using crosswalk edge features, the distance between crosswalk blocks, laser scanning, Hough Transformation, and Fourier Transformation. However, most of these methods failed to detect crosswalks accurately, when they are damaged, faded away or partly occluded. Furthermore, these methods face difficulties when applying on real road environment where there are lot of vehicles. In this paper, we solve this problem by first using a region based binarization technique and x–axis histogram to detect the candidate crosswalk areas. Then, we apply Support Vector Machine (SVM) based classification method to decide whether the candidate areas contain a crosswalk or not. Experiment results prove that our method can detect crosswalks in different environment conditions with higher recognition rate even they are faded away or partly occluded.

We designed and implemented automatic pavement damage detector using an image processing algorithm on driving condition. The experimental results show that the detector is able to successfully monitor and detect pavement damages

We designed and implemented automatic pavement damage detector using an image processing algorithm on driving condition. The experimental results show that the detector is able to successfully monitor and detect pavement damages.