• Journal of Korean Tunnelling and Underground Space Association
• /
• v.19 no.6
• /
• pp.915-936
• /
• 2017

In this study, current status of Korean hazard mitigation guideline for tunnel operation is summarized. It shows that requirement for CCTV installation has been gradually stricted and needs for tunnel incident detection system in conjunction with the CCTV in tunnels have been highly increased. Despite of this, it is noticed that mathematical algorithm based incident detection system, which are commonly applied in current tunnel operation, show very low detectable rates by less than 50%. The putative major reasons seem to be (1) very weak intensity of illumination (2) dust in tunnel (3) low installation height of CCTV to about 3.5 m, etc. Therefore, an attempt in this study is made to develop an deep-learning based tunnel incident detection system, which is relatively insensitive to very poor visibility conditions. Its theoretical background is given and validating investigation are undertaken focused on the moving vehicles and person out of vehicle in tunnel, which are the official major objects to be detected. Two scenarios are set up: (1) training and prediction in the same tunnel (2) training in a tunnel and prediction in the other tunnel. From the both cases, targeted object detection in prediction mode are achieved to detectable rate to higher than 80% in case of similar time period between training and prediction but it shows a bit low detectable rate to 40% when the prediction times are far from the training time without further training taking place. However, it is believed that the AI based system would be enhanced in its predictability automatically as further training are followed with accumulated CCTV BigData without any revision or calibration of the incident detection system.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.4D
• /
• pp.581-586
• /
• 2006

Incidents, which is unexpected unusual events such as traffic accidents, have increased on the most roads in Korea. The obstruction of a fluent traffic flow occurred by incidents causes the traffic congestion and decreases the capacity. The Wavelet technique was applied to detect the road section and the happening time of incidents on urban freeways in this study, and this technique has been widely used in many engineering fields such as an electrical engineering, etc. The availability and validity of the Wavelet technique to the detection of incidents was examined by the occupancy rate, the important element of traffic flows, which is extracted from the data of detectors installed on Seoul Urban freeways. Then, this result is compared to the California Algorithm and the Low-Pass Filtering Algorithm among basic present detection algorithms, which are based on the occupancy rate. As a result, the false alarm rate of this method was similar as that of the California algorithm and the Low-Pass Filtering algorithm, but the detection rate is higher.

• Journal of the Korean Society of Safety
• /
• v.33 no.6
• /
• pp.85-92
• /
• 2018

This study aimed to reduce of traps incident of metro train door by suggesting preventive actions throughout analyzing why railway drivers and passengers commit unsafe behaviors which are human factors making occurrence of the incidents. The incident cases were analyzed and Incident Tree was structured by brainstorming with safety experts. In addition, the questionnaire survey was conducted for comparison with the analysis results. As the result, this study suggested driver's factors, passenger's factors, and public relation plan for safe use of metro in order to reduce the frequency of the incidents. For driver's factors, implementing job-rotation systems between railway and non-railway drivers, installing Object Detection Sensors between the metro doors and PSD, and flexible operation of dwell time were suggested. For passenger's factors, placing a platform safety person, installing a safety fence in front of the stairs and the elevators, and country wide public relations through mass media were suggested.

• Smart Media Journal
• /
• v.1 no.3
• /
• pp.48-55
• /
• 2012

In general, background subtraction based methods are used to detect the moving objects in visual tracking applications. In this paper we employed background subtraction based scheme to detect the temporarily stationary objects. We proposed two schemes for stationary object detection and we compare those in terms of detection performance and computational complexity. In the first approach we used single background and in the second approach we used dual backgrounds, generated with different learning rates, in order to detect temporarily stopped object. Finally, we used normalized cross correlation (NCC) based image comparison to monitor and track the detected stationary object in a video scene. The proposed method is robust with partial occlusion, short time fully occlusion and illumination changes, as well as it can operate in real time.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.15 no.2
• /
• pp.13-23
• /
• 2016

Many traffic centers are highly hesitant in employing existing Automatic Incident Detection Algorithms due to high false alarm rate, low detection rate, and enormous effort taken in maintaining algorithm parameters, together with complex algorithm structure and filtering/smoothing process. Concerns grow over the situation particularly in Freeway Incident Management Area This study proposes a new algorithm and introduces a novel concept, the Displaced Flow Index (DiFI) which is similar to a product of relative speed and relative occupancy for every execution period. The algorithm structure is very simple, also easy to understand with minimum parameters, and could use raw data without any additional pre-processing. To evaluate the performance of the DiFI algorithm, validation test on the algorithm has been conducted using detector data taken from Naebu Expressway in Seoul and following transferability tests with Gyeongbu Expressway detector data. Performance test has utilized many indices such as DR, FAR, MTTD (Mean Time To Detect), CR (Classification Rate), CI (Composite Index) and PI (Performance Index). It was found that the DR is up to 100%, the MTTD is a little over 1.0 minutes, and the FAR is as low as 2.99%. This newly designed algorithm seems promising and outperformed SAO and most popular AIDAs such as APID and DELOS, and showed the best performance in every category.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.31 no.3
• /
• pp.271-277
• /
• 2011

This study presents a nondestructive test for underwater PVC pipes. To use guided ultrasonic waves, specially denoted by cylindrical Lamb waves, a test setup was made in a water tank using the pitch and catch mode and specimens were made to give artificial cutouts located in the circumferential direction of the pipes. Total three states of damaged levels were considered to see how the guided waves interact with the defects. For the experimental adjustments, three different pipe diameters (60, 90, 114 mm) were tested, and two factors - incident angle (10 and $40^{\circ}$) and distance (50 and 200 mm) - were tried. From the results, regardless of the diameters and two experimental factors, it is shown that the degrees of defects were recognized through amplitude and arrived time of the very first part of the received cylindrical Lamb waves. Between amplitude and arrived time, it is found that the amplitude gives more sensitive results.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.285-288
• /
• 2010

Chinese hackers hack the e-commerce site by bypass South Korea IP to connect to the third country, finance damaging a violation incident that fake account. 7.7.DDoS attack was the case of a hacker attack that paralyzed the country's main site. In this paper, the analysis is about vulnerabilities that breaches by hackers and DDoS attacks. Hacker's attacks and attacks on the sign of correlation analysis is share the risk rating for in real time, Red, Orange, Yellow, Green. Create a blacklist of hackers and real-time attack will be studied security and air conditioning systems that attacks and defend. By studying generate forensic data and confirmed in court as evidence of accountability through IP traceback and detection about packet after Incident, contribute to the national incident response and development of forensic techniques.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.11 no.2
• /
• pp.29-38
• /
• 2012

The data quality and measurements along consecutive detector stations can vary much even in the same traffic conditions due to variety in detector types, calibration and maintenance effort, field operation periods, minor geometric changes of roads and so on. These faulty situations often create 10% or more of inherent difference in important traffic measurements between two stations even under stable low flow condition. Low detection rates(DR) and high false alarm rates(FAR) therefore sets in among many popular Automatic Incident Detection Algorithms(AIDA). This research is two-folded and aims mainly to develop a new AIDA for uninterrupted flow. For this purpose, a technique which utilizes a Simple Arithmetic Operation(SAO) of traffic variables is introduced. This SAO technique is designed to address the inherent discrepancy of detector data observed successive stations, and to overcome the degradation of AIDA performance. It was found that this new algorithm improves DR as much as 95 percent and above. And mean time to detection(MTTD) is found to be 1 minutes or less. When it comes to FAR, this new approach compared to existing AIDAs reduces FAR up to 31.0 percent. And capability in persistency check of on-going incidents was found excellent as well.

• Journal of Korean Society of Transportation
• /
• v.22 no.6
• /
• pp.77-88
• /
• 2004

This study aims at developing the model that is able to detect the compression wave, which is included as a similar situation in incidents, that causes false applicable to the similar character such as incidents in the incident detection model for expressways. In this study, it has been checked whether the number of false alarms is decreased or not by modularizing this model for being able to applicable to other models such as DES and DELOS, etc. which do not perform the compression wave test based on the compression wave test process of APID model which has been being used in the expressway traffic management system currently. The evaluation in this study focuses on the sensitivity of the model and the results analysis is performed classified by each polling cycle. And how well these models are working is evaluated by each polling cycle. In addition to this, the detection rate, the false alarm rate and the average detection time in both the existing models and the model in this study are calcuated. As a result of appling the model in this study, it is found that the false alarm rate is improved through the reasonable decrease in the number of false alarm frequencies and there are not remarkable changes concerning the detection rate and the average detection time. To sum up, it is expected that a good number of improvement effects will be occurred when this model is applied to the actual expressway traffic management system.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.19 no.1
• /
• pp.95-107
• /
• 2017

In this study, a preliminary study was undertaken for development of a tunnel incident automatic detection system based on a machine learning algorithm which is to detect a number of incidents taking place in tunnel in real time and also to be able to identify the type of incident. Two road sites where CCTVs are operating have been selected and a part of CCTV images are treated to produce sets of training data. The data sets are composed of position and time information of moving objects on CCTV screen which are extracted by initially detecting and tracking of incoming objects into CCTV screen by using a conventional image processing technique available in this study. And the data sets are matched with 6 categories of events such as lane change, stoping, etc which are also involved in the training data sets. The training data are learnt by a resilience neural network where two hidden layers are applied and 9 architectural models are set up for parametric studies, from which the architectural model, 300(first hidden layer)-150(second hidden layer) is found to be optimum in highest accuracy with respect to training data as well as testing data not used for training. From this study, it was shown that the highly variable and complex traffic and incident features could be well identified without any definition of feature regulation by using a concept of machine learning. In addition, detection capability and accuracy of the machine learning based system will be automatically enhanced as much as big data of CCTV images in tunnel becomes rich.