• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.4
• /
• pp.529-535
• /
• 2020

It is important to secure the driver's external field view in armored vehicles surrounded by iron armor for preparation for the enemy's firepower. For this purpose, a 360 degree rotatable surveillance camera is mounted on the vehicle. In this case, the key idea is to recognize the head of the driver wearing a helmet so that the external camera rotated in exactly the same direction. In this paper, we introduce a method that uses a MEMS-based AHRS sensor and a illuminance sensor to compensate for the disadvantages of the existing optical method and implements it with low cost. The key idea is to set the direction of the camera by using the difference between the Euler angles detected by two sensors mounted on the camera and the helmet, and to adjust the direction with illuminance sensor from time to time to remove the drift error of sensors. The implemented prototype will show the camera's direction matches exactly in driver's one.

• Journal of the Korean Society of Industry Convergence
• /
• v.24 no.6_2
• /
• pp.699-706
• /
• 2021

Existing license plate recognition system is used as an optical character recognition method, but a method of using deep learning has been proposed in recent studies because it has problems with image quality and Korean misrecognition. This requires a lot of data collection, but the collection of license plates is not easy to collect due to the problem of the Personal Information Protection Act, and labeling work to designate the location of individual license plates is required, but it also requires a lot of time. Therefore, in this paper, to solve this problem, five types of license plates were created using a virtual Korean license plate generation program according to the notice of the Ministry of Land, Infrastructure and Transport. And the generated license plate is synthesized in the license plate part of collectable vehicle images to construct 10,147 learning data to be used in deep learning. The learning data classifies license plates, Korean, and numbers into individual classes and learn using YOLOv5. Since the proposed method recognizes letters and numbers individually, if the font does not change, it can be recognized even if the license plate standard changes or the number of characters increases. As a result of the experiment, an accuracy of 96.82% was obtained, and it can be applied not only to the learned license plate but also to new types of license plates such as new license plates and eco-friendly license plates.

• Korean Journal of Heritage: History & Science
• /
• v.55 no.2
• /
• pp.114-129
• /
• 2022

Securing a safe place to keep its collections in Busan, the interim capital during the Korean War, the National Museum of Korea could fulfill its mission to protect the national treasures. Right before Seoul was recaptured by the Communist forces, the museum managed to evacuate its collections to Busan in December of 1950. Until the armistice in 1953, a Korean government warehouse in Busan had to function as a temporary museum building. Protecting the national treasures in this small building, the National Museum of Korea had to maintain its role as a national museum and contribute in revitalizing cultural functions of Busan, the interim capital. The efforts led to hope for reconstructing the museum.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.55-67
• /
• 2022

Sensor data can provide fault diagnosis for equipment. However, the cause analysis for fault results of equipment is not often provided. In this study, we propose an explainable convolutional neural network framework for the sensor-based time series classification model. We used sensor-based time series dataset, acquired from vehicles equipped with sensors, and the Wafer dataset, acquired from manufacturing process. Moreover, we used Cycle Signal dataset, acquired from real world mechanical equipment, and for Data augmentation methods, scaling and jittering were used to train our deep learning models. In addition, our proposed classification models are convolutional neural network based models, FCN, 1D-CNN, and ResNet, to compare evaluations for each model. Our experimental results show that the ResNet provides promising results in the context of time series classification with accuracy and F1 Score reaching 95%, improved by 3% compared to the previous study. Furthermore, we propose XAI methods, Class Activation Map and Layer Visualization, to interpret the experiment result. XAI methods can visualize the time series interval that shows important factors for sensor data classification.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.5
• /
• pp.218-232
• /
• 2022

Researches are underway to use a radar sensor, a sensor used for object recognition in vehicles, for position estimation. In particular, a method of classifying dynamic and static objects using the Doppler velocity, the output from the radar sensor, and calculating ego-motion using only static objects has been researched recently. Also, for the existing dynamic object classification, several methods using RANSAC or robust filtering has been proposed. Still, a classification method with higher performance is needed due to the nature of the position estimation, in which even a single failure causes large effects. Hence, in this paper, we propose a method to improve the classification performance compared to existing methods through tracking and filtering of dynamic objects. Additionally, the method used a GMPHD filter to maximize tracking performance. In effect, the method showed higher performance in terms of classification accuracy compared to existing methods, and especially shows that the failure of the RANSAC could be prevented.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.5D
• /
• pp.649-654
• /
• 2008

In the definition of non additive path, the sum of travel costs of links making up the path is not equal to the path cost. There are a variety of cases that non-additivity assumption does not hold in transportation fields. Nonetheless, traffic equilibrium models are generally built up on the fundamental hypothesis of additivity assumption. In this case traffic equilibrium models are only applicable within restrictive conditions of the path cost being linear functions of link cost. Area-wide road pricing is known as an example of realistic transportation situations, which violates such additivity assumption. Because travel fare is charged at the moment of driver's passing by exit gate while identified at entry gate, it may not be added linearly proportional to link costs. This research proposes a novel Wordrop type of traffic equilibrium model in terms of area-wide road pricing schemes. It introduces binary indicator variable for the sake of transforming non-additive path cost to additive. Since conventional shortest path and Frank-Wolfe algorithm can be applied without route enumeration and network representation is not required, it can be recognized more generalized model compared to the pre-proposed approaches. Theoretical proofs and case studies are demonstrated.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.12
• /
• pp.191-199
• /
• 2023

In this paper, we propose a method to extract the features of five sensor-only facilities built as infrastructure for autonomous cooperative driving, which are from point cloud data acquired by LiDAR. In the case of image acquisition sensors installed in autonomous vehicles, the acquisition data is inconsistent due to the climatic environment and camera characteristics, so LiDAR sensor was applied to replace them. In addition, high-intensity reflectors were designed and attached to each facility to make it easier to distinguish it from other existing facilities with LiDAR. From the five sensor-only facilities developed and the point cloud data acquired by the data acquisition system, feature points were extracted based on the average reflective intensity of the high-intensity reflective paper attached to the facility, clustered by the DBSCAN method, and changed to two-dimensional coordinates by a projection method. The features of the facility at each distance consist of three-dimensional point coordinates, two-dimensional projected coordinates, and reflection intensity, and will be used as training data for a model for facility recognition to be developed in the future.

• Journal of Digital Policy
• /
• v.2 no.4
• /
• pp.33-39
• /
• 2023

With a continuous occurrence of right-turn traffic accidents at intersections, there is an increasing demand for measures to address these incidents. In response, a technology has been developed to detect the presence of pedestrians through object detection in CCTV footage at right-turn areas and display warning messages on the screen to alert drivers. The YOLO (You Only Look Once) model, a type of object detection model, was employed to assess the performance of object detection. An algorithm was also devised to address misidentification issues and generate warning messages when pedestrians are detected. The accuracy of recognizing pedestrians or objects and outputting warning messages was measured at approximately 82%, suggesting a potential contribution to preventing right-turn accidents

• Journal of Practical Engineering Education
• /
• v.16 no.2
• /
• pp.185-193
• /
• 2024

With the advent of smartphones, people can access various information through the internet anytime and anywhere. Even in the vehicle environment, users can use the internet. Users interact with web and applications every day and get information. However, as the amount of data to be processed by the program increases, users inevitably receive a message to wait. User waiting is an inconvenient experience, but minimizing user waiting is the best way because there is time required for data processing. However, if the service processing time exceeds the expected time, users experience more severe boredom and pain. Therefore, various methods and researches are being conducted to alleviate the boredom of user waiting. The most commonly used method to alleviate user waiting boredom is loading. In this study, we investigated the effect of skeleton loading, the latest loading technique, on user waiting experience, and how attractive it is as a design technique in terms of UI compared to other loading techniques.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.5
• /
• pp.483-490
• /
• 2009

In this paper, we develop a speech interface that has acoustic echo cancelling and barge-in functionalities in the car environment. In the echo canceller, DT (Double-Talk) detection algorithm using the correlation coefficients between reference and desired signals can make DT detection errors often in the background noise. We reduce the DT detection errors by using the average power of noise and echo estimated from the input signal. In addition, to make it possible for drivers to give speech command to the system by interrupting the speaker output, barge-in functionality is implemented with the combination of DT detection and appropriate gain control of the speaker output. Through the computer simulation with the assumed car environment and experiment in the real laboratory environment, implemented speech interface has shown good performance in removing acoustic echo signals in the noisy environment with proper operation of barge-in functionality.