• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.04a
• /
• pp.859-861
• /
• 2015

생산 기술이 발전함에 따라 제품의 생산량이 증가하고 컴퓨터 비전을 통한 제품의 양/불 판단 기술의 필요성이 증가하고 있다. 제품의 양/불 판단은 그 정확도가 중요하며, 동시에 빠른 검사를 위한 신속성이 요구된다. 기존 연구들에서 다양한 금속성 제품에 대한 양/불 판단과 각인된 글자에 대한 양/불 판단을 수행하는 연구가 지속되어 왔으나 자동차 에어백 부품 중 하나인 Upper Housing의 양/불을 판단하는 알고리즘은 부재하다. 본 논문에서는 Upper Housing에 대해 각인 문자의 양/불을 판정하는 알고리즘을 제안한다. 먼저 영상에서 기준점이 되는 원을 찾는 것부터 시작하여, 기준점을 기반으로 특정 각도로 회전시켜 미리 수집한 글자 이미지와의 템플릿 매칭을 통해 글자가 제대로 각인 되었는지를 판단한다. 실험에서는 에어백 부품에 대한 검사 장치에서 촬영한 동영상에 대하여 제안한 알고리즘을 적용하였고, 그 결과 높은 정확도로 글자를 검출할 수 있음을 확인하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06a
• /
• pp.191-193
• /
• 2012

본 논문은 차량용 스마트에어백 시스템이 탑승자의 머리 위치를 파악하여 지능적으로 에어백을 전개하도록 돕기 위한 얼굴 위치 검출 알고리즘을 제안한다. 차량용 임베디드 시스템은 한정된 자원에서 기능을 동작시키기 때문에 여러 가지 구현상 제한 조건들이 존재한다. 이러한 제한 조건들을 만족시키기 위해 알고리즘의 경량화 및 최적화 작업이 수반 되어져야한다. 제안하는 알고리즘에서는 이진화된 오브젝트에 거리변환(Distance Transform)을 사용하여 사람의 형태학적 모양을 분석/판단한다. 그리하여 얼굴의 위치를 검출하는 방법이다. 여러 가지 배경 상황에 관계없이 사람의 형태학적 모습을 이용하므로 사람 형태 검출에 용이하다. 설계된 알고리즘은 TI사의 TMS320DM6437 EVM 보드에서 구현하였고 구현 결과 제안한 알고리즘이 IR 영상에서 높은 인식률 및 빠른 처리 속도를 보임을 확인할 수 있었다.

• 전기의세계
• /
• v.58 no.3
• /
• pp.31-36
• /
• 2009

• Journal of Digital Convergence
• /
• v.16 no.9
• /
• pp.173-178
• /
• 2018

The vehicle collision speed in mid and high range can be checked by EDM(Event Driven memory) data recorded when the air bag works. But it's difficult to estimate the low speed of vehicle collision. And estimating the speed is important because the injury level can be changed by the impact speed. The study proposed an estimating algorithm by analysing the images recorded in car blackbox instrument. Low speed rear collision accidents simulated with wire winding motor for various vehicle types. The study estimated the impact speed with the ratio of the distance change between two vehicles and the length change of the number plate of front vehicle. The closer the vehicles are, the larger the plate length is. You can estimate the impact speed with the ratio. The impact speed is calculated with the initial distance for a specific length of number plate in the algorithm. The results can be applied to the linear rear collision because the angle of impact was not considered in this study.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.8 no.6
• /
• pp.182-193
• /
• 2000

Several metrics have been used in crash discrimination algorithms in order to have timely air bag deployment during all frontal crash modes. However, it is still challengine to have timely air bag deployment especially during the oblique, the pole and the underride crash mode. Therefore, in this paper a new crash discrimination algorithm was proposed, using the absolute value of the deceleration change multiplied by the velocity change as a metric, and processing the metric as a function of the velocity change. The new algorithm was applied for all frontal crash modes of a minivan and a sports utility vehicle, and it resulted in timely air bag deployment for all frontal crash modes including the oblique, the pole and the underride crash mode. Moreover, it was proposed that an accelerometer be installed at each side of the rails, rockers or pillars to assess the crash severity of each side and to deploy the frontal air bags at different time especially during an asymmetric crash such as an oblique and an offset crash. As an example, the deceleration pulses measured at the left and right B-pillar·rocker locations were processed through the new algorithm, and faster time-to-fires were obtained for the air bag at the struck side for the air bag at the other side.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.11 no.2
• /
• pp.148-156
• /
• 2003

Many car manufacturers have frequently adopted an aggressive inflator and a lower threshold speed for airbag deployment in order to meet an injury requirement for unbolted occupant at high speed crash test. Consequently, today's occupant safety restraint system has a weakness due to an airbag induced injury at low speed crash event. This paper proposes a new crash algorithm to improve the weakness by suppressing airbag deployment at low speed crash event in case of belted condition. The proposed algorithm consists of two major blocks-crash severity algorithm and deployment logic block. The first block decides crash severity with two levels by means of velocity and crash energy calculation from acceleration signal. The second block implemented by simple AND/OR logic combines the crash severity level and seat belt status information to generate firing commands for airbag and belt pretensioner. Furthermore, it can be extended to adopt additional sensor information from passenger presence detection sensor and safing sensor. A simulation using real crash data for a 1,800cc passenger vehicle has been conducted to verify the performance of proposed algorithm.

• Journal of Auto-vehicle Safety Association
• /
• v.13 no.4
• /
• pp.66-72
• /
• 2021

This study was initiated to improve of the defect investigation method using event data recorders (EDR) and suggested a solution through the regulation and system analysis of EDR. The EDR data has been used for various purposes such as the vehicle defect investigation and the traffic accident investigation. However the EDR regulation has not been updated since the implementation in 2012. "Trigger Threshold" can be used to analyze a single accident such as the frontal crash, the side crash, and the rollover. In the case of a complex accident in which a rollover accident and a crash accident occur simultaneously, it is difficult to analyze a complex accident due to current "Trigger Threshold". This study proposed the method of separating the "Trigger Threshold" into a crash accident and a rollover accident so that accidents can be analyzed using the EDR data even when a complex accident occurs. In addition, it proposed the improvement method to quickly use the data of EDR in accident reconstruction software.

• Computational Structural Engineering
• /
• v.12 no.1
• /
• pp.27-34
• /
• 1999

독자적인 자동차 충돌해석용 프로그램 개발 및 응용기술을 목표로 Explicit 수식화, 셀 요소의 정식화, 교체요소의 정식화, 비선형스프링 요소의 개발, 초탄성 고무재료의 개발, Hourglass 제어, 접촉알고리즘 정식화 등의 프로그램의 기본 모듈을 구성하였고, 그래프 출력용 포스트 프로그램을 개발하였다. 비선형스프링, 에어백 모듈, 안전벨트 모듈 등이 개발되었으며, 자체구조물들의 정면·측면 충돌해석을 수행하고 상용충돌해석프로그램들과 그 결과를 비교하여 개발된 프로그램의 신뢰성을 확인하였다. 또한, 측면충돌 모델을 사용하여 설계초기단계에서 빠른 해석을 수행할 수 있도록 하는 Hybrid 모델링 기법을 개발하여 기존의 쉘모델의 결과와 비교·검토하였다. Hybrid 모델링시 조인트 부의 특성을 측면해석 모델에 적용하여 그 타당성을 검증하였다.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.9 s.351
• /
• pp.135-141
• /
• 2006

In order to prevent traffic accident, it is very important that the driver regulates the location of rear view mirror using the automatic seat regulation system which guarantees the maximum vision of the possibility for accuracy. In order to solve this problem the paper deals with the automatic seat control system which guarantees comfortable and safe seating and good visual field. Also a automatic car seat control algorithm has been developed to regulate the back mirror. Particularly, the automatic seat control algorithm function for the air bag operation in case of an accident has been added depending on passengers weight. Moreover when the driver passes a dangerous area an algorithm has been developed which gives the driver a naming sign and has been simulated in a ubiquitous environment. The simulation result proved that the Intelligence analysis for traffic accidents can reduce franc accidents more than 25% than the currently existing methods.

• Journal of the Korean Society of Safety
• /
• v.35 no.2
• /
• pp.94-99
• /
• 2020

Bikers can be subjected to injuries from unexpected accidents even if they wear basic helmets. A properly designed airbag can efficiently protect the critical areas of the human body. This study introduces a wearable smart airbag system using machine learning techniques to protect human neck and shoulders. When a bicycle accident happens, a microprocessor analyzes the biker's motion data to recognize if it is a critical accident by comparing with accident classification models. These models are trained by a variety of possible accidents through machine learning techniques, like k-means and SVM methods. When the microprocessor decides it is a critical accident, it issues an actuation signal for the gas inflater to inflate the airbag. A protype of the wearable smart airbag with the machine learning techniques is developed and its performance is tested using a human dummy mounted on a moving cart.