• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.6
• /
• pp.1195-1202
• /
• 2016

Recently, a lot of studies that applying the big data technology to various fields, are progressing actively. In the maritime domain, the big data is the meaningful information which makes and gathers by the navigation and communication equipment from the many ships on the ocean. Also, importance of the maritime safety is emphasized, because maritime accidents are rising with increasing of maritime traffic. To support prevention of maritime accidents, in this paper, we developed a vessel traffic display and statistic system based on AIS messages from the many vessels of maritime. Also, to verify the developed system, we conducted tests for vessel track display function and vessel traffic statistic function based on two test scenarios. Therefore, we verified the effectiveness of the developed system for vessel tracks display, abnormal navigation patterns, checking failure of AIS equipments and maritime traffic statistic analyses.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.1243-1244
• /
• 2022

In recent years, the growing interest in off-site construction has led to factories scaling up their manufacturing and production processes in the construction sector. Consequently, continuous large-scale site monitoring in low-variability environments, such as prefabricated components production plants (precast concrete production), has gained increasing importance. Although many studies on computer vision-based site monitoring have been conducted, challenges for deploying this technology for large-scale field applications still remain. One of the issues is collecting and transmitting vast amounts of video data. Continuous site monitoring systems are based on real-time video data collection and analysis, which requires excessive computational resources and network traffic. In addition, it is difficult to integrate various object information with different sizes and scales into a single scene. Various sizes and types of objects (e.g., workers, heavy equipment, and materials) exist in a plant production environment, and these objects should be detected simultaneously for effective site monitoring. However, with the existing object detection algorithms, it is difficult to simultaneously detect objects with significant differences in size because collecting and training massive amounts of object image data with various scales is necessary. This study thus developed a large-scale site monitoring system using edge computing and a small-object detection system to solve these problems. Edge computing is a distributed information technology architecture wherein the image or video data is processed near the originating source, not on a centralized server or cloud. By inferring information from the AI computing module equipped with CCTVs and communicating only the processed information with the server, it is possible to reduce excessive network traffic. Small-object detection is an innovative method to detect different-sized objects by cropping the raw image and setting the appropriate number of rows and columns for image splitting based on the target object size. This enables the detection of small objects from cropped and magnified images. The detected small objects can then be expressed in the original image. In the inference process, this study used the YOLO-v5 algorithm, known for its fast processing speed and widely used for real-time object detection. This method could effectively detect large and even small objects that were difficult to detect with the existing object detection algorithms. When the large-scale site monitoring system was tested, it performed well in detecting small objects, such as workers in a large-scale view of construction sites, which were inaccurately detected by the existing algorithms. Our next goal is to incorporate various safety monitoring and risk analysis algorithms into this system, such as collision risk estimation, based on the time-to-collision concept, enabling the optimization of safety routes by accumulating workers' paths and inferring the risky areas based on workers' trajectory patterns. Through such developments, this continuous large-scale site monitoring system can guide a construction plant's safety management system more effectively.

• International Journal of Highway Engineering
• /
• v.11 no.1
• /
• pp.69-83
• /
• 2009

According to the accident statistics of 2006, it can be recognized that drivers' characteristics and driving behaviors are the most causational factors on the traffic accidents. At present, many recording tools such as digital speedometer or black box are distributed in the market to meet social requests of decreasing traffic accidents and increasing safe driving behaviors. However, it is also true that the system preventing any possible vehicle accidents in advance has not been developed. In this study, we developed critical value for deciding dangerous driving behaviors. The developed critical value could be used to contribute to safety driving management systematization and safety driving behaviors.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.22 no.4
• /
• pp.771-783
• /
• 2012

This paper proposes a scheme to collect video data of the vehicle black box in order to strengthen the public safety. The existing schemes, such as surveillance system with the fixed CCTV and car black box, have privacy issues, network traffic overhead and the storage space problems because all video data are sent to the central server. In this paper, the central server only collects the video data related to the accident or the criminal offense using the GPS information and time in order to investigation of the accident or the criminal offense. The proposed scheme addresses the privacy issues and reduces network traffic overhead and the storage space of the central server since the central server collects the video data only related to the accident and the criminal offense. The implementation and experiment shows that our service is feasible. The proposed service can be used as a component of remote surveillance system to prevent the criminal offense and to investigate the criminal offense.

• Journal of Digital Convergence
• /
• v.12 no.6
• /
• pp.259-264
• /
• 2014

Digital convergence means a service or new product which appeared through fusion of unit technologies in information and communication regions. In 2011, The Government introduced "IT Convergence Technology Prediction Survey 2025". Smart mobility is a main factor in smart city which is main example of convergence. A intelligent transport system(ITS) is a key factor of smart mobility. The conventional transport systems include road, car, signal systems. But the ITS is a transport system containing additional technologies such as electronics, control, communication to increase traffic safety and effectiveness of traffic facilities. In this paper, we described intelligent transport system related with our life.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.3
• /
• pp.1-13
• /
• 2020

When pedestrians cross a pedestrian crossing during a pedestrian signal, there is a problem that pedestrians are exposed to the danger of traffic accidents due to permissive-left turning and right-turning vehicles. In order to solve this problem, there is an increasing demand to improve the traffic signal system to increase pedestrian safety at the signal crossing. This study aims to examine the feasibility of introducing a leading pedestrian interval(LPI) to prevent conflict between unprotected left and right turn vehicles and pedestrians. In this study, the need for LPI was surveyed by experts and the general public. As a result of the survey, many opinions indicated that the introduction of LPI was necessary. In addition, after selecting the non-protected left and right turn pilot operation targets, LPI was installed on two signal intersections. After installation, the speed analysis of the arrival vehicle in the pedestrian crossing and the violation rate of the pedestrian signal were analyzed. As a result of analysis, when the walking signal was equalized, the speed of the arriving vehicle in the pedestrian crossing was reduced, and the violation rate of the walking signal was improved.

• Journal of Korean Society of Transportation
• /
• v.26 no.4
• /
• pp.17-28
• /
• 2008

Favorable policies for freight vehicles (i.e., trucks), such as exclusive "Truck-ways," have been proposed, and at the same time restricted policies for freight vehicles have been suggested because transportation of goods by truck aggravates traffic congestion and environmental conditions in urban areas. This study discusses the limitations of assessment processes for freight vehicle route management systems which have been carried out from limited perspectives such as physical distribution efficiency and traffic circulation. The objective of this study is to propose an assessment method of truck route management systems in urban areas which includes more varied criteria. This research modified the two existing assessment indices of physical distribution efficiency and traffic circulation. In addition two new assessment indexes are proposed: (i) exposure indices for population directly influenced by nitrous oxide, a representative pollutant, and (ii) a friction index between trips for attending elementary school and freight vehicle trips. It was found that from the perspective of physical distribution efficiency and traffic circulation, the "before" alternative is better than "after". However, from the aspect of traffic safety and environmental impacts the "after" alternative is better than "before". It is expected that the proposed evaluation method in this study would be useful when identifying reasonable policies for truck route management in urban areas.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.34 no.1
• /
• pp.243-250
• /
• 2014

Modern roundabouts referred to as relatively safer and more efficient traffic facility than the signalized intersections have been recently deployed and operated and accordingly more research efforts to improve its safety and efficiency have been made so far. This paper introduces a new traffic information system named as Smart Roundabout coupled with Connected Vehicle technique like Vehicle-to-Roadside communication, which has not been attempted before and evaluates its performance with a microscopic simulation model, VISSIM. The proposed system functions to collect driving information of circulating vehicles in the roundabout such as location, speed, critical headway, etc. and help approaching vehicles decide whether to enter the roundabout with an on-board equipment instrumented in the individual vehicle on the basis of calculated gap acceptance of interest. This new system is expected to secure more safety and increase the capacity of the modern roundabout.

• Journal of Advanced Marine Engineering and Technology
• /
• v.40 no.10
• /
• pp.906-915
• /
• 2016

In this study, a network monitoring system, including a secure 460-Network and a 460-Gateway, is designed and developed according with the requirements of the IEC (International Electro-Technical Commission) 61162-460 network standard for the safety and security of networks on board ships. At present, internal or external unauthorized access to or malicious attack on a ship's on board systems are possible threats to the safe operation of a ship's network. To secure the ship's network, a 460-Network was designed and implemented by using a 460-Switch, 460-Nodes, and a 460-Gateway that contains firewalls and a DMZ (Demilitarized Zone) with various application servers. In addition, a 460-firewall was used to block all traffic from unauthorized networks. 460-NMS (Network Monitoring System) is a network-monitoring software application that was developed by using an simple network management protocol (SNMP) SharpNet library with the .Net 4.5 framework and a backhand SQLite database management system, which is used to manage network information. 460-NMS receives network information from a 460-Switch by utilizing SNMP, SNMP Trap, and Syslog. 460-NMS monitors the 460-Network load, traffic flow, current network status, network failure, and unknown devices connected to the network. It notifies the network administrator via alarms, notifications, or warnings in case any network problem occurs. Once developed, 460-NMS was tested both in a laboratory environment and for a real ship network that had been installed by the manufacturer and was confirmed to comply with the IEC 61162-460 requirements. Network safety and security issues onboard ships could be solved by designing a secure 460-Network along with a 460-Gateway and by constantly monitoring the 460-Network according to the requirements of the IEC 61162-460 network standard.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.7 no.4
• /
• pp.49-60
• /
• 2008

The current VIPS are not effective in safety point of view, because they are originally developed for mimicking loop detectors. Therefore, it is important to identify vehicle trajectories in real time, because recognizing vehicle movements over a detection zone enables to identify which situations are hazardous, and what causes them to be hazardous. In order to improve limited safety functions of the current VIPS, this research has developed a computer vision system of monitoring individual vehicle trajectories based on image processing, and offer the detailed information, for example, incident detection and conflict as well as traffic information via tracking image detectors. This system is capable of recognizing individual vehicle maneuvers and increasing the effectiveness of various traffic situations. Experiments were conducted for measuring the cases of incident detection and abnormal vehicle trajectory with rapid lane change.