• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.10 no.2
• /
• pp.42-54
• /
• 2011

This study presented an algorithm to detect zigzag driving maneuver that is highly associated with vehicle crash occurrence. In general, the zigzag driving results from the driver's inattention including drowsy driving and driving while intoxicated. Therefore, the technology to detect such unsafe driving maneuver will provide us with a valuable opportunity to prevent crash in the road. The proposed detection algorithm used angular velocity data obtained from a gyro sensor. Performance evaluations of the algorithm presented promising results for the actual implementation in practice. The outcome of this study can be used as novel information contents under the ubiquitous transportation systems environment.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.4
• /
• pp.370-380
• /
• 2002

This paper proposes an ATR (Automatic Target Recognition) algorithm for identifying non-occluded and occluded military vehicles in natural FLIR (Forward Looking InfraRed) images. After segmenting a target, a radial function is defined from the target boundary to extract global shape features. Also, to extract local shape features of upper region of a target, a distance function is defined from boundary points and a line between two extreme points. From two functions and target contour, four global and four local shape features are proposed. They are much more invariant to translation, rotation and scale transform than traditional feature sets. In the experiments, we show that the proposed feature set is superior to the traditional feature sets with respect to the similarity-transform invariance and recognition performance.

• Journal of Korean Society of Transportation
• /
• v.20 no.5
• /
• pp.23-31
• /
• 2002

The headway of vehicles entering an intersection is closely related with the saturation flow rate and is a basic parameter required for determining the saturation headway and the start-up lost delay. Since such headway value reflects the drivers' behaviors and features of the intersection, all intersections don't have an equal value, but are affected by number and location of their lanes, changing types, local characteristics and time zone. Accordingly, this study attempted to suggest proper values on the basis of data by investigating headway in lanes. Number of exclusive through lanes was divided into single lane, double lanes and triple lanes, the locations of lanes were divided into inside lane, central lane and outside lane. As a result of investigating the headway, single through lane, double through lanes-inside lane, and triple through lane-outside lane showed as 1.73 sec., 1.71 sec. and 1.93sec., respectively. The result of calculating the area factor of business areas by fixing 1.00 for the residental area and applying relation between headway and saturation flow rate was 0.96. In the case of start-up lost delay lead dual left turn and directional separation were 1.41 sec. and 3.27 sec., respectively, showing the great difference. Therefore, different start-up lost delay according to changing type should be applied.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.12
• /
• pp.150-157
• /
• 2015

Pedestrian detection has largely been researched as one of the important technologies for autonomous driving vehicle and preventing accidents. There are two categories for pedestrian detection, camera-based and LIDAR-based. LIDAR-based methods have the advantage of the wide angle of view and insensitivity of illuminance change while camera-based methods have not. However, there are several problems with 3D LIDAR, such as insufficient resolution to detect distant pedestrians and decrease in detection rate in a complex situation due to segmentation error and occlusion. In this paper, two methods using GM-PHD filter are proposed to improve the poor rates of pedestrian detection algorithms based on 3D LIDAR. First one improves detection performance and resolution of object by automatic accumulation of points in previous frames onto current objects. Second one additionally enhances the detection results by applying the GM-PHD filter which is modified in order to handle the poor situation to classified multi target. A quantitative evaluation with autonomously acquired road environment data shows the proposed methods highly increase the performance of existing pedestrian detection algorithms.

• Fire Science and Engineering
• /
• v.32 no.1
• /
• pp.108-115
• /
• 2018

The purpose of this study was to classify VR programs according to their characteristics and associations by the disaster management phase and firefighting school curriculum, and set priorities among VR fire training and training programs using AHP analysis., The relative priority is given considering its importance and urgency. As a result of the study, firefighting education and training classes showed the highest level of response. The relative priority of the subcategories was highest in the prevention stage. The simulation implementation for the evacuation experience was highest in closed spaces, such as a subway, and the simulation for the special firefighting vehicle was highest in the contrast phase. In the response phase, real fire simulation training was the highest. In the recovery phase, virtual reality training was the most effective in determining the fire situation based on the fire database.

• The Journal of the Korea Contents Association
• /
• v.10 no.12
• /
• pp.84-90
• /
• 2010

In this paper, we propose a quadratic discriminant analysis based approach for improving the discriminating strength of weak classifiers based on simple Haar-like features that were used in the Viola-Jones object detection framework. Viola and Jones built a strong classifier using a boosted ensemble of weak classifiers. However, their single threshold (or decision boundary) based weak classifier is sub-optimal and too weak for efficient discrimination between object class and background. A quadratic discriminant analysis based approach is presented which leads to hyper-quadric boundary between the object class and background class, thus realizing multiple thresholds based weak classifiers. Experiments carried out for car detection using 1000 positive and 3000 negative images for training, and 500 positive and 500 negative images for testing show that our method yields higher classification performance with fewer classifiers than single threshold based weak classifiers.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.4
• /
• pp.1-12
• /
• 2017

Traffic accidents are caused by a combination of human factors, vehicle factors, and environmental factors. In the case of traffic accidents where rental cars are involved, the possibility and the severity of traffic accidents are expected to be different from those of other traffic accidents due to the unfamiliar environment of the driver. In this study, we developed a model to forecast the severity of rental car accidents by using Naive Bayes classifier for Busan, Gangneung, and Jeju city. In addition, we compared the prediction accuracy performance of two models where one model uses the variables of which statistical significance were verified in a prior study and another model uses the entire available variables. As a result of the comparison, it is shown that the prediction accuracy is higher when using the variables with statistical significance.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.3
• /
• pp.103-114
• /
• 2004

This paper deals with a system that is capable of recognizing hand-signals in 3-dimensional space. The system uses 2 color cameras as input devices. Vision-based gesture recognition system is known to be user-friendly because of its contact-free characteristic. But as with other applications using a camera as an input device, there are difficulties under complex background and varying illumination. In order to detect hand region robustly from a input image under various conditions without any special gloves or markers, the paper uses previous position information and adaptive hand color model. The paper defines a hand-signal as a combination of two basic elements such as 'hand pose' and 'hand trajectory'. As an extensive classification method for hand pose, the paper proposes 2-stage classification method by using 'small group concept'. Also, the paper suggests a complementary feature selection method from images from two color cameras. We verified our method with a hand-signal application to our driving simulator.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.3
• /
• pp.147-157
• /
• 2022

Recently, many studies have been conducted to analyze traffic or object recognition that classifies vehicles through artificial intelligence-based prediction models using CCTV (Closed Circuit TeleVision)or drone images. In order to develop an object recognition deep learning model for accurate traffic estimation, systematic data construction is required, and related standardized guidelines are insufficient. In this study, previous studies were analyzed to derive guidelines for establishing artificial intelligence-based training data for traffic estimation using drone images, and business reports or training data for artificial intelligence and quality management guidelines were referenced. The guidelines for data construction are divided into data acquisition, preprocessing, and validation, and guidelines for notice and evaluation index for each item are presented. The guidelines for data construction aims to provide assistance in the development of a robust and generalized artificial intelligence model in analyzing the estimation of road traffic based on drone image artificial intelligence.

• 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.