• 한국멀티미디어학회논문지
• /
• 제19권2호
• /
• pp.264-270
• /
• 2016

In this paper, we proposed a method which can detect pedestrians from CCTV video and estimate the height of the detected objects. We separate the foreground using Gaussian mixture model and the pedestrian is detected using the conditions such as the width-height ratio and the size of the candidate objects. In order to obtain the optimal model for estimating the height of pedestrian, we get many training data from the pedestrian whose height is known. Using these training data, we designed optimal Wiener height estimator and used to estimate the height of pedestrians. The height of the pedestrian at various distance is estimated and the accuracy is evaluated. In the experimental results, proposed method shows that it can estimate the height of pedestrian for various positions effectively.

• 대한임베디드공학회논문지
• /
• 제18권5호
• /
• pp.259-265
• /
• 2023

Pedestrian detection is used to effectively detect pedestrians in various situations based on deep learning. Pedestrian detection has difficulty detecting pedestrians due to problems such as camera performance, pedestrian description, height, and occlusion. Even in the same pedestrian, performance in detecting them can differ according to the height of the pedestrian. The height of general pedestrians encompasses various scales, such as those of infants, adolescents, and adults, so when the model is applied to one group, the extraction of data becomes inaccurate. Therefore, this study proposed a pedestrian detection method that fine-tunes the pedestrian area by Refining Layer and Feature Concatenation to consider various heights of pedestrians. Through this, the score and location value for the pedestrian area were finely adjusted. Experiments on four types of test data demonstrate that the proposed model achieves 2-5% higher average precision (AP) compared to Faster R-CNN and DRPN.

• 한국ITS학회 논문지
• /
• 제15권5호
• /
• pp.54-61
• /
• 2016

본 연구는 차량-보행자 사고시 보행자의 신장에 따라 보행자의 두부가 승용차의 전면유리에 닿을 수 있는 최저 속도를 제시하기 위하여 수행되었다. 마디모(MADYMO) 프로그램을 사용하여, NF쏘나타 차량에 대하여 보행자의 신장을 160cm, 170cm 180cm로 구분하여 평가하였다. 평가 결과, 승용차의 최저 속도값은 보행자의 신장이 160cm인 경우 약 49km/h, 170cm일 때 약 41km/h, 그리고 180cm일 때 약 29km/h로 나타났다. 이러한 값은 승용차 대 보행자 교통사고에서 승용차의 전면유리에 보행자 두부의 충돌흔적이 있을 시 속도추정의 중요 자료로 활용할 수 있을 것으로 기대된다.

• 한국기계가공학회지
• /
• 제6권3호
• /
• pp.105-111
• /
• 2007

The type of pedestrian accident can be characterized by vehicular frontal shape and the height of pedestrian. The trajectory of pedestrian after collision by passenger car is different from that by bus due to vehicular frontal shape. The frontal shape of SUV vehicles is dissimilar to passenger car and bus. So, the trajectory and throw distance of pedestrian by SUV vehicles is not the same of passenger car and bus. In this paper, a series of pedestrian kinetic simulation were conducted to inspect the difference in throw distance between SUV vehicle and passenger car and bus by PC-CRASH that is the program for kinetic analysis of articulated body. From the results, if the height of pedestrian is taller than 1.70m, there is no difference in throw distance between SUV vehicle and passenger car, but if the height of pedestrian is about 1.55m throw distance of SUV vehicle is about 4m longer than that of passenger car at each impact speed. The throw distance of pedestrian by Bus is shorter than that of passenger car and SUV at each impact speed.

• 한국전자통신학회논문지
• /
• 제9권9호
• /
• pp.1035-1042
• /
• 2014

객체인식은 지능적이고 다양화된 범죄 예방을 위한 영상 감시 시스템에서 중요한 기술 중 하나이다. 사람의 신체 정보인 키는 그 대상이 가지고 있는 신체적인 특징 중 하나로 신원을 확인하는데 중요한 정보가 될 수 있다. 본 논문에서는 CCTV 영상으로부터 보행자를 검출하고 검출된 객체인 보행자의 키를 추정하는 방법을 제안하였다. 이를 위하여 GMM(Gaussian Mixture Model) 방식을 이용하여 움직이는 객체를 분리하고, 분리된 후보 객체들의 가로세로 비율, 크기 등의 조건을 이용하여 보행자를 검출하였다. 제안한 방법을 CCTV 영상에 적용하고 동일 보행자에 대하여 근거리, 중거리, 원거리의 위치에서 키를 추정하고 정확성을 평가하였다. 실험결과 근거리에서 97%, 중거리에서 98%, 원거리에서 97% 이상의 정확도로 키 추정이 가능함을 보였다. 또한 영상내의 보행자는 위치에 따라 크기가 다르지만 실험을 통하여 제안하는 방법이 보행자의 위치에 관계없이 키를 추정하는데 효과적임을 확인하였다.

• 한국자동차공학회논문집
• /
• 제20권6호
• /
• pp.67-72
• /
• 2012

Novel Front End Module(FEM) with improved pedestrian protection is very important to reduce the severity of pedestrian injury. The FEM needs to have enough space from hood to absorb the energy from any pedestrian collision. In this study, the cooling performance of the FEM to cool the engine was investigated under 25% height reduction. The results indicated that the cooling performance analysis was about 86% level compared to that of the conventional FEM. Also, good qualitative agreement between CFD predictions and experimental measurements was found. This FEM needs the cooling performance enhancement for changed air flow path at the frontal part of vehicle. Therefore, we showed an improved performance using air guide setup and shape modification under the high load condition.

• 한국ITS학회 논문지
• /
• 제16권5호
• /
• pp.85-95
• /
• 2017

본 논문의 목적은 트럭과 보행자의 충돌사고에서 트럭의 중량, 속도와 범퍼 높이가 보행자 전도거리에 미치는 영향을 분석하고, 나아가 이를 이용한 보행자 전도거리에 대한 모형식을 제시하는 데 있다. 이를 위해 교통사고 재현 프로그램인 PC-crash를 이용하여 트럭의 중량을 5t, 15t, 25t으로 적용하고, 각 트럭의 앞 범퍼 하단 높이를 0.3m부터 0.6m까지 0.1m씩 높여감과 동시에 트럭의 속도를 10km/h부터 100km/h까지 10km/h씩 높여가며 실험하였다. 트럭의 속도와 범퍼 높이는 보행자 전도거리에 유의한 변수로 확인되었고, 트럭 중량은 보행자 전도거리에 유의하지 않은 변수로 나타났다. 또한 다중회귀분석을 이용하여 제시한 모형식은 조정된 $R^2$ 값이 93.3%로 매우 우수한 설명력을 가지는 것으로 나타났다.

• 동력기계공학회지
• /
• 제13권2호
• /
• pp.56-62
• /
• 2009

The fatalities of pedestrian account for about 40.0% of all fatalities in Korea 2005. Vehicle-Pedestrian accident generates trajectory of pedestrian. In pedestrian involved accident, the most important data to inspect accident is throw distance of pedestrian. The throw distance of pedestrian can be influenced by many variables. But existing studies have been done for simple factors. The variables that influence trajectory of pedestrian can be classified into vehicular factors, pedestrian factors, and road factors. The trajectory of pedestrian, dynamic characteristics of multi-body were analyzed by PC-CRASH, a kinetic analysis program for a traffic accident. PC-CRASH enables an analyst to investigate the effect of many variables. The influence of the offset of impact point was analyzed by Working Model. Based on the results, the variables that influence trajectory of pedestrian were vehicular frontal shape, vehicular impact speed, the offset of impact point, the height of pedestrian, friction coefficients of pedestrian. However the weight of pedestrian did not affect trajectory of pedestrian considerably.

• KIEAE Journal
• /
• 제14권5호
• /
• pp.89-96
• /
• 2014

This study provides the basic resource for establishing the environment design policies around elementary school for the students and analyzes the actual pedestrian environment conditions of elementary school in order to improve safety of from crime for them. For this, the field survey are conducted on risk of from crime in 10 sidewalks of 5 elementary schoolin Ilsan new town. The result of this are the followings ;1) There are schools which have difference between the height of road and the height of pedestrian path. 2) There are schools which are insufficient distance for securing front sight because of shape of pedestrian path. 3) In entrance there are facilities interfering with natural surveillance within school boundaries such as stone written school motto, storehouse, wash room, doorpost. 4) In entrance there are schools with no security office, emergency bell and CCTV. 4) The openness in the bottom of fence is lower than that of upper because of shrubs and material of fence. 5) There are concealed places and cars in back gate area interfering with natural surveillance.

• 한국자동차공학회논문집
• /
• 제19권3호
• /
• pp.9-15
• /
• 2011

This study analyzed contributing factors affecting leg injury severity in pedestrian-vehicle crashes. A Binary Logistic Regression (BLR) method was used to identify the factors. Independent variables include characteristics for pedestrian, vehicle, road, and environmental conditions. The leg injury severity is classified into two classes, which are dependent variables in this study, such as 'severe' and 'minor' injuries. Pedestrian age, collision speed, and the height of vehicle were identified as significant factors for the leg injury. The probabilistic outcome of predicting leg injury severity can be effectively used in not only deriving pedestrian-related safety policies but also developing advanced vehicular technologies for pedestrian protection.