• International Journal of Highway Engineering
• /
• v.14 no.1
• /
• pp.85-94
• /
• 2012

The term "incident duration time" is defined as the time from the occurrence of incident to the completion of the handling process. Reductions in incident durations minimize damages by traffic accidents. This study aims to develop models to identify factors that influence incident duration by investigating traffic accidents on highways. For this purpose, four models were established including an integrated model (Model 1) incorporating all accident data and detailed models (Model 2, 3 and 4) analyzing accidents by location such as basic section, bridges and tunnels. The result suggested that the location of incident influences incident duration and the time of arrival of accident treatment vehicles is the most sensitive factor. Also, significant implications were identified with regard to vehicle to vehicle accidents and accidents by trucks, in night or in weekends. It is expected that the result of this study can be used as important information to develop future policies to manage traffic accidents.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.2
• /
• pp.129-152
• /
• 2024

In the application of deep learning object detection via CCTV in tunnels, a large number of false positive detections occur due to the poor environmental conditions of tunnels, such as low illumination and severe perspective effect. This problem directly impacts the reliability of the tunnel CCTV-based accident detection system reliant on object detection performance. Hence, it is necessary to reduce the number of false positive detections while also enhancing the number of true positive detections. Based on a deep learning object detection model, this paper proposes a false positive data training method that not only reduces false positives but also improves true positive detection performance through retraining of false positive data. This paper's false positive data training method is based on the following steps: initial training of a training dataset - inference of a validation dataset - correction of false positive data and dataset composition - addition to the training dataset and retraining. In this paper, experiments were conducted to verify the performance of this method. First, the optimal hyperparameters of the deep learning object detection model to be applied in this experiment were determined through previous experiments. Then, in this experiment, training image format was determined, and experiments were conducted sequentially to check the long-term performance improvement through retraining of repeated false detection datasets. As a result, in the first experiment, it was found that the inclusion of the background in the inferred image was more advantageous for object detection performance than the removal of the background excluding the object. In the second experiment, it was found that retraining by accumulating false positives from each level of retraining was more advantageous than retraining independently for each level of retraining in terms of continuous improvement of object detection performance. After retraining the false positive data with the method determined in the two experiments, the car object class showed excellent inference performance with an AP value of 0.95 or higher after the first retraining, and by the fifth retraining, the inference performance was improved by about 1.06 times compared to the initial inference. And the person object class continued to improve its inference performance as retraining progressed, and by the 18th retraining, it showed that it could self-improve its inference performance by more than 2.3 times compared to the initial inference.

• Proceedings of the KIEE Conference
• /
• 1992.07b
• /
• pp.789-793
• /
• 1992

For improving the power supply reliability and minimizing maintenance work of E.H.V. underground transmission line, new surveillance systems are strongly desired for use in the field of electric power transmission. For underground installation, high system reliability is required because E.H.V. cables, if an accident happen, can have a serious impact on social activities and human life. In answer to this requirement, applications of optical fiber transmission system have been widely developed in a variety of field. The main function of this system are cable fault location, oil leak detection, and surveillance of the cable circuit and tunnel condition.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.416-421
• /
• 2021

In case of the road slips due to heavy snow and the temperature drops below 0 degrees, black ice which mainly occurs on the road, bridges for vehicles, and tunnel entrances, is not recognized by the driver's view because the image of the asphalt is transmitted through it. So cars' slip situation occurs, which leads to a big traffic accident and a large amount of loss of life and property. This study proposes a method to check the road condition using an infrared camera and to identify black ice through deep learning.

• Tunnel and Underground Space
• /
• v.27 no.5
• /
• pp.282-294
• /
• 2017

This study analyzed the development status and applications of collision avoidance systems for mine safety management. The definitions of collision avoidance system used in Australia and USA were compared. Sensing technologies utilized in the collision avoidance systems were reviewed. In addition, several collision avoidance systems developed in oversea mining company, such as $MineAlert^{TM}$ Collision Awareness System, Cat $MineStar^{TM}$, and Intelligent Proximity Detection, were reviewed. In the domestic mining industry, no collision avoidance system was used. However, similar systems were utilized in the construction and railroad industry. Collision avoidance system can prevent unexpected collision accident and thus improve worker's safety in mine. Therefore, it is necessary to analyze and apply sensors and system appropriate for the domestic mining environment via review of overseas collision avoidance system.