• Journal of the Korea Society of Computer and Information
• /
• v.17 no.1
• /
• pp.125-132
• /
• 2012

In this paper, We proposes FE-SM/SONN for recognizing blurred and smeared skid mark image caused by sudden braking of a vehicle. In a blurred and smeared skid marks, tread pattern image is ambiguous. To improve recognition of such image, FE-SM/SONN reads skid marks utilizing Fuzzy Logic and distinguishing tread pattern SONN(Self Organization Neural Networks) recognizer. In order to substantiate this finding, 48 tire models and 144 skid marks were compared and overall recognition ratio was 89%. This study showed 13.51% improved recognition compared to existing back propagation recognizer, and 8.78% improvement than FE-MCBP. The expected effect of this research is achieving recognition of ambiguous images by extracting distinguishing features, and the finding concludes that even when tread pattern image is in grey scale, Fuzzy Logic enables the tread pattern recognizable.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.1
• /
• pp.113-120
• /
• 2010

In case the traffic accident occurs, skid mark is very important factor to calculate the car speed. Especially, for the purpose of objective and scientific inspection, traffic accidents should be appraised and inspected by righteous material evidences, computer simulation, and studies such as automobile engineering, traveling and collision accident dynamics, road and traffic engineering. In this paper, it displays the results of studying cases with the reasons of traffic accidents by analyzing and studying automobile kinetics, real traffic accidents and the results of in scientific and objective ways. After computer simulation result that it is proved that compared with unpacked road condition and packed road condition. unpacked road condition is shorter than packed road condition.

• Journal of Korean Society of Transportation
• /
• v.30 no.5
• /
• pp.83-90
• /
• 2012

Driver ordinarily takes sudden braking when urgent situation is developed or when the vehicle is involved in an unexpected accident. Therefore, the most common trace at a traffic accident scene is skid mark. Currently, in investigating traffic accident, overspeed is determined by the length of skid mark. However, in order to identify accurate cause of accident, estimation of pre-braking speed which takes into account speed reduction during transient time should be considered as a requirement. In a recent study, several ways to estimate pre-braking speed were suggested, but none considered to differentiate the decelerating transient brake section and skidding section. This study analyzed trends of decelerating transient brake section and skidding section by real braking test.

• Journal of the Korean Society for Precision Engineering
• /
• v.20 no.12
• /
• pp.55-63
• /
• 2003

The traffic accident is the prerequisite of the traffic accident reconstruction. In this study, the traffic accident (forward collision) and traffic accident reconstruction (inverse collision) simulations are conducted to improve the quality and accuracy of the traffic accident reconstruction. The vehicle and tire models are used to simulate the trajectories for the post-impact motion of the vehicles after collision. The impact dynamic model applicable to the forward and inverse collision simulations is also provided. The accuracy of impact analysis for the vehicular collision depends on the accuracy of the coefficients of restitution and friction. The neural network is used to estimate these coefficients. The forward and inverse collision simulations for the multi-collisions are conducted. The new method fur the accident reconstruction is proposed to calculate the pre-impact velocities of the vehicles without using the trial and error process which requires the repeated calculations of the initial velocities until the forward collision simulation satisfies with the accident evidences. This method estimates the pre-impact velocities of the vehicles by analyzing the trajectories of the vehicles. The vehicle slides on a road surface not only under the skidding during an emergency braking but also under the steering. A vehicle over steering or cornering with excessive speed loses the traction and leaves tile yaw marks on the road surface. The new critical speed formula based on the vehicle dynamics is proposed to analyze the yaw marks and shows smaller errors than ones of the existing critical speed formula.

• Journal of Korean Society of Transportation
• /
• v.29 no.3
• /
• pp.115-122
• /
• 2011

This paper investigates the accuracy of the vehicle pre-braking speed estimated based upon measured skidding distance. Driver ordinarily takes sudden braking when urgent situation is developed in the front or when the driver is involved in an unexpected situation, and the driver may be inflicted upon an accident depending on the required stopping distance. Among factors influencing the stopping distance of vehicle such as recognition response time of driver, performance of vehicle's braking device, and state of road surface etc, pre-braking speed is seemingly the most important influencing factor. Currently, in the investigating section of traffic accidents, the state of overspeed is determined by the pre-skidding speed calculated based on the length of skid mark. In order to identify the accurate cause of the accident, it is strongly recommended that estimation of pre-braking speed should be estimated taking into account speed reduction during transient time. In this study, we propose a method for estimating more accurate exact speed information of vehicle at the time of traffic accident. The outcomes from this study potentially help better understanding of the characteristics of vehicle for traffic safety in the future.

• Journal of Korean Society of Transportation
• /
• v.27 no.1
• /
• pp.43-51
• /
• 2009

This paper investigates the accuracy of vehicle pre-braking speed estimates based upon tire/roadway coefficient of friction (drag factor) measurements and skid mark measurements Data for pre-braking and pre-skidding speeds were collected to determine if there were any correlations between pre-braking speeds and pre-skidding speeds. Braking tests were performed on two vehicles using various measurement devices including a fifth wheel, a speed gun, and a vericom 2000. The vehicle speeds, braking distances, skid mark distances, and deceleration histories were recorded. From these data. coefficients of friction and vehicle pre-skidding speeds for the tested road surface were calculated. The pre-skidding speeds were then compared to the actual pre-braking speeds of the vehicles in order to establish relationships between pre-skidding and pre-braking speed. A correlation between the Pre-skidding speed and the actual pre-braking speed was established for the study data.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2006.05a
• /
• pp.353-356
• /
• 2006

자동차사고는 소득증대와 차량증가와 함께 도로확충 및 정비가 필수임에도 불구하고 자동차 사고는 갈수록 대형화되고 있다. 그러나 교통사고 발생시 누가 가해자이고 피해자인지를 정확하게 구별하기는 매우 어려운 일이다. 특히 교통사고 발생시 목격자가 없을 경우에는 교통사고원인을 규명하기가 더욱 어려워진다. 본 연구에서는 이러한 문제점을 해결하기위해서 뺑소니 교통사고 발생시에 퍼지 및 지능형 알고리즘을 시용해서 스키드마크 길이를 입력하면 도로의 종류, 타이어의 종류, 자동차 종류, 날씨 조건을 고려하여 최적의 자동차 속도를 산출하였으며, 컴퓨터 시물레이션을 통해서 기존의 방법보다 20-30% 정확하게 예측하였다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2008.04a
• /
• pp.366-369
• /
• 2008

무선 센서 네트워크(Wireless Sensor Network)는 차세대 IT 기술로서 소형, 저가, 저전력을 필요로 하며, 외부 환경의 모니터링과 제어기능을 수행할 수 있다. 이것은 소형 장치 안에 마이크로프로세서, 각종 센서, 액추에이터, 유 ${\cdot}$ 무선 통신 장치를 내장하는 수백 혹은 수천 개의 센서 노드로 구성된다. 본 논문에서는 이러한 센서 네트워크를 이용하여 기상의 악천 후 속에서 차량 및 도로 상황 정보를 실시간으로 미리 획득하고 분석하여 운전자에게 미리 도로의 안전속도를 통보할 수 있는 실시간 차량 안전속도 서비스 시스템을 설계하고 구현된 결과를 보여 주고자 한다. 본 시스템은 노면의 종류 및 기상 상태 등에 대한 정보를 수집하여 이를 바탕으로 운전자에게 안전 속도를 알려줌으로써 교통사고를 효과적으로 예방할 수 있는 방법을 제공할 수 있다.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.40-40
• /
• 2000

Generally a RF AGC controls the roll gap using the variation of rolling force caused by the roll eccentricity and the entry thickness of material, but these can not be classified. The Feed- forward AGC method, which controls the next stand roll 9ap by estimation the skid mark of the previous stand output thickness is needed to supplement the shortage of RF AGC. In this paper, an improved filtering method of skid mark which take account of the kinds of materials, the final objective thickness and the roll speed is proposed, In addition, an improved estimation method of control point using the speedometer and looper angle is suggested, Via simulation, the performance improvement of the suggested FF AGC method is verified.

• Journal of Korean Society of Transportation
• /
• v.20 no.4
• /
• pp.7-17
• /
• 2002

본 연구는 차대차 충돌사고시 차량충돌위치와 충돌속도 분석기법을 사고사례를 통해 연구하였다. 차량충돌위치는 사고현장 노면에 생성된 타이어 마크를 이용하여 수학적방법으로, 충돌속도는 실제 사고차량 최종정지위치와 모의충돌실험을 통해 분석된 차량 최종정지위치와의 차를 목적함수로 하여 이를 최소로 수렴하는 최적화기법을 이용하였다. 연구결과, 승용차량 오른쪽 앞바퀴 위치는 중앙선으로부터 좌측으로 0.45m 떨어진 진행방향 1차로 상이고, 왼쪽 앞바퀴는 중앙으로부터 좌측으로 0.345m 떨어진 지점에 위치한 상태이다. 최적화기법을 이용하여 사고차량의 충돌속도를 분석한 결과. 최적화의 오차율이 0.8%인 경우 충돌속도는 승용차량 67.75Km/h, 짚형 승용차량 29.67Km/h로 분석되었으며, 충돌 후 x축에 대한 속도는 승용차량 20.0Km/h, 짚형승용차량 15.69Km/h이고, y축에 대한 속도는 승용차량 15.68Km/h, 짚형 승용차량 7.66Km/h로 분석되었다. 반면, 기존 충돌속도 분석모형식을 이용하여 사고차량의 충돌속도를 분석한 결과 승용차량 64.97Km/h, 짚형승용차량 31.27Km/h로 도출되었다. 따라서, 최적화기법을 통해 분석한 충돌속도와 기존 분석모형식을 이용하여 분석한 충돌속도와의 오차가 승용차량 2.78Km/h, 짚형승용차량 1.6Km/h로 최적화기법을 이용하여 분석한 결과에 대한 신뢰성이 높은 것으로 연구결과 도출되었다 따라서, 추후 차 대 차 충돌사고를 분석함에 있어 타이어 흔적을 이용한 수학적방법과 모의충돌실험을 통한 최적화기법을 이용하면 충돌속도는 물론 충돌전.후 차량의 운동특성에 대한 정확한 분석이 이루어질 수 있을 것으로 기대된다.