• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10b
• /
• pp.476-478
• /
• 1999

본 논문에서는 신경망을 이용하여 자동차 번호판을 찾는 방법을 제안한다. 신경망은 영상의 윈도우들을 분석하기 위한 필터로 사용되며 이 윈도우가 번호판을 포함하는지의 여부를 결정한다. 후 처리기는 필터링된 영상들로부터 번호판의 최종 위치를 지정한다. 신경망을 이용한 필터링 방법은 잡음이 많은 영상과 해상도가 ？은 영상을 처리할 때 유용하다. 주차장과 도로상에서 자동차 영상들을 실험한 결과 각각 96%와 92.0%의 확률로 번호판을 추출했다. 이 실험결과에서는 제안된 방법이 현실 세계의 상황에 유용함을 제시한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.10a
• /
• pp.499-502
• /
• 2011

The advances in Information Technology have made examining the condition of vehicles possible with using various functions of a Smart Phone. Users have not realized the necessity of auto diagnosis system, for previous system required professional knowledge about vehicles. Because of this inconvenience, special system which is easy to use and quick to grasp its condition by smart phone is asked for users. In this research, auto diagnosis system is designed in Windows Phone. The replacement cycles for auto consumables, examining vehicle problems, and information of eco driving indicator are delivered in real time for auto drivers by using OBD-II information which is through wifi module in OBD-II protocol adaptor connector.

• The Journal of the Korea Contents Association
• /
• v.14 no.4
• /
• pp.37-46
• /
• 2014

Industrialization and urbanization have led automobiles to transform into more than just modes of transportation; they have become daily necessities as well as extensions of living spaces where a variety of activities can be done and automotive applications of the latest information technology are accelerated. Though material abundance has increased in the modern society, the conflicts and the stress emerging from a social structure focused on competition have increased as well. Such lifestyles generate a need for personal space and media content for healing the body and the mind. This research explores the automotive application of video content with the goal of refreshing the minds of the passengers. To this end, previous studies have investigated the emotional effect of videos, focusing on the responses of diverse groups of adults (age group of 20 to 60) who frequently used automobiles, which had video displays installed in them. The results showed that watching video contents on a full window inside a car influenced the creation of positive feelings7 and emotional satisfaction. The research attempts to study the methods of providing video contents and the effects of watching them that could aid the emotional well-being of passengers, and presents the possibility of emotional satisfaction created by a convergence of cars and multimedia contents in the future.

• Journal of Power System Engineering
• /
• v.16 no.1
• /
• pp.98-105
• /
• 2012

안티핀치 시스템은 파워 윈도우 상승 시에 인체의 특정 부위가 창문 틈 사이에 끼여 발생하는 치명적인 사고를 방지하기 위한 안전 시스템이다. 이러한 안티핀치 시스템은 물체의 끼임을 검출하는 센서 방식에 따라 접촉식과 비접촉식 두 가지로 크게 구분된다. 본 논문에서는 접촉식의 한 방법으로 전류 정보에 의해 강화된 미국의 안전 규정 FMVSS 118-S5를 만족하는 안티핀치 시스템을 제안한다. 안티핀치 시스템에 사용된 전류 정보는 추가적인 장치의 부착 없이도 기존의 파워 윈도우용 모터 드라이브에 내장된 과전류 검출용 전류 센서를 이용하여 쉽게 얻을 수 있다. 또한 전류 정보는 물체의 끼임을 신속히 검출, 반영함으로써 안티핀치 시스템에 요구되는 반전력 저감에 기여한다. 특히, 본 논문에서는 전류의 임계값이 모터 경년 변화나 운전 조건에 따라 변동하는 문제점을 개선하기 위해 핀치 상태를 효과적으로 판정할 수 있는 자동 임계값 설정 방법을 제안한다. 마지막으로 다양한 실험 및 시험을 통해 제안된 안티핀치 시스템이 FMVSS 118-S5를 만족함을 보인다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.05a
• /
• pp.289-292
• /
• 2013

본 논문은 SVM(Support Vector Machine) 학습알고리즘을 이용하여 자동차 썬루프 장치의 볼트 유무를 검사하는 자동차 부품 검사 장비에 관한 것이다. 자동화 시스템은 높은 정밀도와 생산성을 위한 빠른 처리 속도를 요구한다. 이를 위해 본 논문에서는 선형 SVM 학습알고리즘을 활용하여 자동차 썬루프 장치의 볼트 유무를 검사하는 알고리즘을 개발하였다. SVM 알고리즘은 분류를 위한 알고리즘이지만 ROI(Region-Of-Interest) 내의 모든 윈도우에 대한 분류를 수행하여 검출기 역할을 할 수 있도록 한다. 볼트가 있는 경우와 볼트가 없는 경우가 아닌 네거티브 샘플을 확보하기 위해 검출 대상 물체 주변에서 다양한 네거티브 샘플들을 추출한다. 그 결과 물체가 예상 위치에서 다소 빗나가는 경우에도 볼트 유무를 판별할 수 있을 뿐 아니라 볼트의 위치까지 검출할 수 있고, 처리 속도에서 자동화 시스템이 요구하는 수준에 도달함을 실험 결과를 통해 검증한다.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.5 no.4
• /
• pp.21-28
• /
• 1997

The vehicle handling performances have a close relation with the driver's safety. And the CAT(Computer aided testing) system has been introduced as a powerful tool for improving the handling performances. In this study, a CAT system for effectively measuring and analysing the handling performances is developed based on the windows GUI(Graphic user interface) environment. Especially, in order to derive a lot of significant handling performance parameters from a series of proving ground tests, the CAT system has various functions related to real time measurement, time domain analysis, frequency domain analysis, steady state analysis and so on.

• Proceedings of the KIPE Conference
• /
• 2004.07a
• /
• pp.325-329
• /
• 2004

본 논문은 하이브리드 전기자동차의 12V보조배터리 충전용 DC-DC 컨버터의 최적설계에 관한 것으로 하이브리드 전기자동차의 특성상 DC-DC 컨버터는 최대부하의 $30\%\~70\%$ 정도의 비교적 낮은 부하영역에서 주로 동작하므로 이에 따른 적절한 설계가 요구된다. 따라서 DC-DC 컨버터의 주 동작영역에서 효율이 높도록 주요 설계요소인 스위칭 주파수와 고주파 변압기의 누설인덕턴스를 적절히 선정하고 코아의 윈도우 면적을 최소화하는 최적설계에 관한 연구이다.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.8 no.1
• /
• pp.92-100
• /
• 2000

The model gas reaction tests were carried out to investigate the purification characteristics of methane on the exclusive catalyst for NGV. The experiment was conducted with the factors which affect the conversion efficiency of methane, such as Redox ratio, coexistence components of CO, MO, $H_2$O, precious metals and additives. The catalyst loaded with larger amount of pd and with additive La showed lower light-off temperature. In the presence of CO and NO, the conversion efficiency of methane was varied according to the kind of additive loaded. The conversion efficiency of methane was dropped for the catalyst loaded with La under lean air-fuel ratio, while it increased for the one loaded with Ti+Zr for the same condition. It was shown that the water vapor inhibited methane from oxidation by its poisoning on the surface of catalyst.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38B no.7
• /
• pp.543-552
• /
• 2013

For the safety messages in IEEE 802.11p/WAVE vehicles network environment, strict periodic beacon broadcasting requires status advertisement to assist the driver for safety. In crowded networks where beacon message are broadcasted at a high number of frequencies by many vehicles, which used for beacon sending, will be congested by the wireless medium due to the contention-window based IEEE 802.11p MAC. To resolve the congestion, we consider a MAC scheme based on slotted p-persistent CSMA as a simple non-cooperative Bayesian game which involves payoffs reflecting the attempt probability. Then, we derive Bayesian Nash Equilibrium (BNE) in a closed form. Using the BNE, we propose new congestion control algorithm to improve the performance of the beacon rate under saturation condition in IEEE 802.11p/WAVE vehicular networks. This algorithm explicitly computes packet delivery probability as a function of contention window (CW) size and number of vehicles. The proposed algorithm is validated against numerical simulation results to demonstrate its stability.

• Journal of Software Assessment and Valuation
• /
• v.16 no.2
• /
• pp.153-162
• /
• 2020

Digital image forgery detection is one of very important fields in the field of digital forensics. As the forged images change naturally through the advancement of technology, it has made it difficult to detect forged images. In this paper, we use passive forgery detection for copy paste forgery in digital images. In addition, it detects copy-paste forgery using the L₀ Norm-based LE operator, and compares the detection accuracy with the forgery detection using the existing L₂, L₁ Norm-based LE operator. In comparison of detection rates, the proposed lower triangular(Ayalneh and Choi) window was more robust to BAG mismatch detection than the conventional window filter. In addition, in the case of using the lower triangular window, the performance of image forgery detection was measured increasingly higher as the L₂, L₁ and L₀ Norm LE operator was performed.