• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.302-302
• /
• 2021

지하차도의 경우 국지 및 돌발홍수가 발생할 경우 대부분 침수됨에도 불구하고 2020년 7월 23일 부산 지역에 밤사이 시간당 80mm가 넘는 폭우가 발생하면서 순식간에 지하차도 천장까지 물이 차면서 선제적인 차량 통제가 우선적으로 수행되지 못하여 미처 대피하지 못한 3명의 운전자 인명사고가 발생하였다. 수재해를 비롯한 재난 관리를 빠르게 수행하기 위해서는 기존의 정부 및 관주도 중심의 단방향의 재난 대응에서 벗어나 정형 데이터와 비정형 데이터를 총칭하는 빅데이터의 통합적 수집 및 분석을 수행이 필요하다. 본 연구에서는 부산지역의 지하차도와 인접한 지하터널 CCTV 자료(센서)를 통한 재난 발생 시 인명피해를 최소화 정보 제공을 위한 Object Detection(객체 탐지)연구를 수행하였다. 지하터널 침수가 발생한 부산지역의 CCTV 영상을 사용하였으며, 영상편집에 사용되는 CCTV 자료의 음성자료를 제거하는 인코딩을 통하여 불러오는 영상파일 용량파일 감소 효과를 볼 수 있었다. 지하차도에 진입하는 물체를 탐지하는 방법으로 YOLO(You Only Look Once)를 사용하였으며, YOLO는 가장 빠른 객체 탐지 알고리즘 중 하나이며 최신 GPU에서 초당 170프레임의 속도로 실행될 수 있는 YOLOv3 방법을 적용하였으며, 분류작업에서 보다 높은 Classification을 가지는 Darknet-53을 적용하였다. YOLOv3 방법은 기존 객체탐지 모델 보다 좀 더 빠르고 정확한 물체 탐지가 가능하며 또한 모델의 크기를 변경하기만 하면 다시 학습시키지 않아도 속도와 정확도를 쉽게 변경가능한 장점이 있다. CCTV에서 오전(일반), 오후(침수발생) 시점을 나눈 후 Car, Bus, Truck, 사람을 분류하는 YOLO 알고리즘을 적용하여 지하터널 인근 Object Detection을 실제 수행 하였으며, CCTV자료를 이용하여 실제 물체 탐지의 정확도가 높은 것을 확인하였다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.23 no.1
• /
• pp.182-196
• /
• 2024

This study introduces driving pattern analysis and change detection methods using smartphone sensors, based on contrastive learning. These methods characterize driving patterns without labeled data, allowing accurate classification with minimal labeling. In addition, they are robust to domain changes, such as different vehicle types. The study also examined the applicability of these methods to smartphones by comparing them with six lightweight deep-learning models. This comparison supported the development of smartphone-based driving pattern analysis and assistance systems, utilizing smartphone sensors and contrastive learning to enhance driving safety and efficiency while reducing the need for extensive labeled data. This research offers a promising avenue for addressing contemporary transportation challenges and advancing intelligent transportation systems.

• The Journal of Bigdata
• /
• v.9 no.1
• /
• pp.89-100
• /
• 2024

In the field of computer vision, models such as You Look Only Once (YOLO) and ResNet are widely used due to their real-time performance and high accuracy. However, to apply these models in real-world environments, factors such as runtime compatibility, memory usage, computing resources, and real-time conditions must be considered. This study compares the characteristics of three deep model runtimes: ONNX Runtime, TensorRT, and OpenCV DNN, and analyzes their performance on two models. The aim of this paper is to provide criteria for runtime selection for practical applications. The experiments compare runtimes based on the evaluation metrics of time, memory usage, and accuracy for vehicle license plate recognition and classification tasks. The experimental results show that ONNX Runtime excels in complex object detection performance, OpenCV DNN is suitable for environments with limited memory, and TensorRT offers superior execution speed for complex models.

• Proceedings of the KSR Conference
• /
• 2011.05a
• /
• pp.1300-1305
• /
• 2011

Environmental Impact is getting more attention in many feasibility studies for railroad-related projects and research items. For sustainable growth and green transportation, the benefits typically used for feasibility studies in railway-related projects, are composed mostly of economic criterions which is not considering growing attention on changing paradigm. Based on the analysis of current methodologies, improvements in estimating environmental impact especially on noise and pollution are suggested.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.1
• /
• pp.15-26
• /
• 2013

This paper proposes a classification method of parallel, vertical parking states and pillars for parking assist system using ultrasonic sensors. Since, in general parking space detection module, the compressed amplitude of ultrasonic data are received, the analysis of them is difficult. To solve these problems, in preprocessing state, symmetric transform and noise removal are performed. In feature extraction process, four features, standard deviation of distance, reconstructed peak, standard deviation of reconstructed signal and sum of width, are proposed. Gaussian fitting model is used to reconstruct saturated peak signal and discriminability of each feature is measured. To find the best combination among these features, multi-class SVM and subset generator are used for more accurate and robust classification. The proposed method shows 92 % classification rate and proves the applicability to parking space detection modules.

• Composites Research
• /
• v.16 no.4
• /
• pp.22-28
• /
• 2003

This article deals with the manufacture and test results of asbestos-free friction material for Aluminium at toy disk. In order to obtain optimum formulation, various formulations of fibres, matrix, modifiers, fillers, etc were designed and evaluated. The constant friction and brake dynamometer tests were performed to know weak and strong point for each friction material. The C21 formulation of various tested formulations exhibited superior friction constant(0.38∼38), fade rate (18%) by JASO C406 test mode and maximum wear 1.6 mm. disc wear 0.08 mm by JASO C427 test mode. The surface morphology of AL alloy disk(before and after test) was observed by Scanning Electron Microscope(SEM) and Image Analyzer.

• Journal of Korean Society of Transportation
• /
• v.17 no.5
• /
• pp.111-122
• /
• 1999

A service network design model for LTL freight transportation is formulated as a mixed integer Programming Problem with two heuristic solution a1gorithms. The Proposed model derives the transportation Path for each origination-destination pair, taking into account transportation cost over the links and handling costs over the nodes. The first algorithm searches for a local minimum solution from a given initial solution by improving the quality of solution repeatedly while the second a1gorithm searches for a better solution using Simulated Annealing Method. For both solution algorithms, the initial solution is derived by a modified reverse Diikstras shortest Path a1gorithm. An illustrative example, Presented in the last part of the Paper, shows that the proposed algorithms find solutions which reduce the cost by 12% and 15% respectively, compared to the initial solution.

• Journal of Internet Computing and Services
• /
• v.7 no.3
• /
• pp.13-30
• /
• 2006

In this paper, a telematics service platform, which supports the management and diagnosis of automobile and controls the automobile's convenience equipment is designed and implemented. Using the service platform, telematics software can be developed independent of the lower part of automobiles's network devices, each hardware devices, and wireless network devices. The platform classifies each device's service and provides it with the fixed form of API(Application Programming Interface). This API consists of the wireless connection for a mobile device, the CAN network for controlling an automobile, the receiving part of GPS data for location base service, and the message parser for different data formats of different network.

• Journal of Korean Society of Transportation
• /
• v.29 no.2
• /
• pp.7-14
• /
• 2011

This paper discusses operational technique and effectiveness of Variable Speed Limits system that is implemented to control the traffic-flow on the Naebu Expressway. As the first step of the analysis, traffic data collected from vehicle detectors are corrected and smoothed. Applying a pattern analysis technique to the traffic data, the weekday traffic is classified into four different groups, and median of each group is calculated. Using three state variables, i.e., diverted traffic volume, average density and average speed, the conditions of roadway segments are determined. Computational outputs resulted from the application of the proposed model to the scenarios show that implementation of Variable Speed Limits system improved both safety and efficiency of the expressway. For the operational strategy, this paper also presents the change rate of the speed limit, and the effective duration of the speed limit according to the entering traffic volume.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.4
• /
• pp.428-436
• /
• 2014

This paper proposes a statistical regression method for classifying pillars and vehicles in parking area using a single ultrasonic sensor. There are three types of information provided by the ultrasonic sensor: TOF, the peak and the width of a pulse, from which 67 different features are extracted through segmentation and data preprocessing. The classification using the multiple SVM and the multinomial logistic regression are applied to the set of extracted features, and has achieved the accuracy of 85% and 89.67%, respectively, over a set of real-world data. The experimental result proves that the proposed feature extraction and classification scheme is applicable to the object classification using an ultrasonic sensor.