• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.13 no.3
• /
• pp.66-77
• /
• 2014

UTIS(Urban Traffic Information System) directly collects link travel time in urban area by using probe vehicles. Therefore it can estimate more accurate link travel speed compared to other traffic detection systems. However, UTIS includes some missing data caused by the lack of probe vehicles and RSEs on road network, system failures, and other factors. In this study, we suggest a new model, based on k-NN algorithm, for imputing missing data to provide more accurate travel time information. New imputation model is an adaptive k-NN which can flexibly adjust the number of nearest neighbors(NN) depending on the distribution of candidate objects. The evaluation result indicates that the new model successfully imputed missing speed data and significantly reduced the imputation error as compared with other models(ARIMA and etc). We have a plan to use the new imputation model improving traffic information service by applying UTIS Central Traffic Information Center.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.6
• /
• pp.621-628
• /
• 2015

This paper describes an algorithm for detecting vehicles detection in real time. The proposed algorithm has the technique based on computer vision and image processing. In real, complex environment such as one with road traffic, many algorithms have great difficulty such as low detection rate and increasing computational time due to complex backgrounds and rapid changes. To overcome this problem in this paper, the proposed algorithm consists of the following methods. First, to effectively separate the candidate regions, we use vertical and horizontal edge information, and shadow values from input image sequences. Second, we extracts features by using HOG from the selected candidate regions. Finally, this paper uses the OS fuzzy-ELM based on SLFN to classify the extracted features. The experimental results show that the proposed method perform well for detecting vehicles and improves the accuracy and the computational time of detecting.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.7 no.4
• /
• pp.118-129
• /
• 2008

This paper describes an IEEE 802.15.4-based hierarchical sensor network model for a VAWS(Vehicle Approach Warning System) which provides the drivers of vehicles approaching a sharp turn with the information about vehicles approaching the same turn from the opposite end. In the proposed network model, a tree-structured topology, that can prolong the lifetime of network is formed in a self-organizing manner by a topology control protocol. A simple but efficient routing protocol, that creates and maintains routing tables based on the network topology organized by the topology control protocol, transports data packets generated from the sensor nodes to the base station which then forwards it to a display processor. These protocols are designed as a network layer extension to the IEEE 802.15.4 MAC. In the simulation, which models a scenario with a sharp turn, it is shown that the proposed network model achieves a high-level performance in terms of both energy efficiency and throughput simultaneously.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.2
• /
• pp.114-128
• /
• 2019

Recently, the interest in the safety of autonomous vehicles has globally been increasing. Also, there is controversy over the reliability and safety about autonomous vehicle. In Korea, the K-City which is a test-bed for testing autonomous vehicles has been constructing. There is a need for test scenarios for autonomous vehicle test in terms of safety. The purpose of this study is to develop the evaluation scenario for autonomous vehicle at community roads in K-City by using crash data collected by the Korea National Police Agency and a text-mining technique. As a result, 24 scenarios were developed in order to test autonomous vehicle in community roads. Finally, the logical and concrete scenario forms were derived based on the Pegasus 5-layer format.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.2
• /
• pp.111-116
• /
• 2021

This study is a study on improving the pedestrian Care system, which delivers jaywalking events in real time to the autonomous driving control center and Autonomous driving vehicles in operation and issues warnings and announcements to pedestrians based on pedestrian signals. In order to secure reliability of object detection method of pedestrian Care system, the inspection method combined with camera sensor with Lidar sensor and the improved system algorithm were presented. In addition, for the occurrence events of Lidar sensors and intelligent CCTV received during the operation of autonomous driving vehicles, the system algorithm for the elimination of overlapping events and the improvement of accuracy of the same time, place, and object was presented.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.6
• /
• pp.107-117
• /
• 2020

With the recent development of autonomous vehicles, various sensors installed in vehicles have become common, and big data generated from those sensors is increasingly being used in the transportation field. In this study, we proposed a grid index method to efficiently process real-time vehicle sensing big data and public data such as road weather. The applicability and effect of the proposed grid space division method and grid ID generation method were analyzed. We created virtual data based on DTG data and mapped to the road link based on coordinates. As a result of analyzing the data processing speed in grid index method, the data processing performance improved by more than 2,400 times compared to the existing link unit processing method. In addition, in order to analyze the efficiency of the proposed technology, the virtually generated data was mapped and visualized.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.264-279
• /
• 2021

Most automated vehicle evaluation scenarios are developed based on the typical driving situations that automated vehicles will face. However, various situations occur during actual driving, and sometimes complex judgments are required. This study is to define a situation that requires complex judgment for safer driving of an automated vehicle as a dilemma situation, and to suggest a driving strategy necessary to secure driving safety in each situation. To this end, we defined dilemma situations based on the automated vehicle ethics guidelines, the criteria for recognition of error rate in automobile accidents, and suggestions from the automated vehicle developers. In addition, in the defined dilemma situations, the factors affecting movement for establishing driving strategies were explored, and the priorities of factors affecting driving according to the Road Traffic Act and driving strategies were derived accordingly.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.47-54
• /
• 2021

The number of freeway traffic accidents in Korea is about 4,000 as of 2020, and deaths per traffic accident is about 3.7 times higher than other roads due to non-recurring congestion and high driving speed. Most of the accident types on freeways are side and rear-end collisions, and one of the main factors is hazard traffic flow caused by merge, diverge and accidents. Therefore, the hazard traffic flow, which appears in a continuous flow such as a freeway, can be said to be important information for the driver to prevent accidents. This study tried to classify hazard traffic flows, such as the speed change point and the section where the speed difference by lane, using individual vehicle information. The homogeneous segment of speed was classified using spatial separation based on geohash and space mean speed that can indicate the speed difference of individual vehicles within the same section and the speed deviation between vehicles. As a result, I could extract the diverging influence segment and the hazard traffic flow segment that can provide dangerous segments information of freeways.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.214-227
• /
• 2021

The purpose of this study is to find the driving difficulty of automated vehicles in terms of road infrastructure operation. It was judged out of this study that the level of automated driving would be enhanced if the road situation recognition ability was advanced through the presentation of infrastructure information during the difficult driving situations. The difficulty evaluation index was divided into three stages, and a survey of experts and an AHP were conducted. The result of the AHP showed that the driving difficulty of the interrupted flow was much higher than that of the uninterrupted flow. The AHP results also showed that and the driving difficulty of unsignalized intersections and roundabouts under an interrupted flow was evaluated as the highest. The top six driving situations with high difficulty were also evaluated to occur under unsignalized intersections and roundabouts.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.3
• /
• pp.83-95
• /
• 2022

This paper proposes a system that performs object detection and distance estimation for application to autonomous vehicles. Object detection is performed by a network that adjusts the split grid to the input image ratio using the characteristics of the recently actively used deep learning model YOLOv4, and is trained to a custom dataset. The distance to the detected object is estimated using a bounding box and homography. As a result of the experiment, the proposed method improved in overall detection performance and processing speed close to real-time. Compared to the existing YOLOv4, the total mAP of the proposed method increased by 4.03%. The accuracy of object recognition such as pedestrians, vehicles, construction sites, and PE drums, which frequently occur when driving to the city center, has been improved. The processing speed is approximately 55 FPS. The average of the distance estimation error was 5.25m in the X coordinate and 0.97m in the Y coordinate.