• 대한토목학회논문집
• /
• 제32권2D호
• /
• pp.129-136
• /
• 2012

무인항공기(UAV: Unmanned Aerial Vehicle), 헬리콥터, 항공기를 이용하여 실시간 교통자료를 수집하는 항공 기반 차량 검지시스템(ADS: Aerial-Based Vehicle Detection System)에 관한 연구가 미국, 일본, 독일에서 이루어져 왔다. 따라서 본 연구에서는 ADS의 교통자료 수집 시스템으로 활용 가능성을 검토하기 위하여 먼저 ADS에 의하여 수집된 자료가 이미지프로세싱 등 자료추출 기법을 거쳐 통행속도 등 교통정보를 산출할 수 있는 지를 확인하였다. 다음으로는 ADS에 의하여 수집된 자료의 신뢰성 정도가 교통정보 제공에 적합한 지를 확인하였다. 그 결과 ADS는 기존에 상시적으로 실시간 교통정보 제공을 하기 위하여 사용되고 있는 VDS 등을 대체하기에는 기술적 비용적 측면에서 어려움이 있을 것으로 파악되었다. 하지만 재해 발생 등 비반복적 교통상황이 장시간 발생할 경우 비상교통관리대책 등을 세우기 위한 보완적 방안으로 활용할 수 있을 것이다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권6호
• /
• pp.2483-2503
• /
• 2016

Traffic congestion is a severe problem in many modern cities around the world. Real-time and accurate traffic congestion identification can provide the advanced traffic management systems with a reliable basis to take measurements. The most used data sources for traffic congestion are loop detector, GPS data, and video surveillance. Video based traffic monitoring systems have gained much attention due to their enormous advantages, such as low cost, flexibility to redesign the system and providing a rich information source for human understanding. In general, most existing video based systems for monitoring road traffic rely on stationary cameras and multiple vehicle tracking method. However, most commonly used multiple vehicle tracking methods are lack of effective track initiation schemes. Based on the motion of the vehicle usually obeys constant velocity model, a novel vehicle recognition method is proposed. The state of recognized vehicle is sent to the GM-PHD filter as birth target. In this way, we relieve the insensitive of GM-PHD filter for new entering vehicle. Combining with the advanced vehicle detection and data association techniques, this multiple vehicle tracking method is used to identify traffic congestion. It can be implemented in real-time with high accuracy and robustness. The advantages of our proposed method are validated on four real traffic data.

• 한국인공지능학회지
• /
• 제11권4호
• /
• pp.21-27
• /
• 2023

This paper discusses a deep learning-based road surface analysis system that collects data by installing vibration sensors on the 4-axis wheel bearings of a vehicle, analyzes the data, and appropriately classifies the characteristics of the current driving road surface for use in the vehicle's control system. The data used for road surface analysis is real-time large-capacity data, with 48K samples per second, and the A2B protocol, which is used for large-capacity real-time data communication in modern vehicles, was used to collect the data. CAN and CAN-FD commonly used in vehicle communication, are unable to perform real-time road surface analysis due to bandwidth limitations. By using A2B communication, data was collected at a maximum bandwidth for real-time analysis, requiring a minimum of 24K samples/sec for evaluation. Based on the data collected for real-time analysis, performance was assessed using deep learning models such as LSTM, GRU, and RNN. The results showed similar road surface classification performance across all models. It was also observed that the quality of data used during the training process had an impact on the performance of each model.

• International Journal of Automotive Technology
• /
• 제6권4호
• /
• pp.351-357
• /
• 2005

Development of a real-time simulation model for high-speed and multibody tracked vehicles is difficult because they involve hundreds of highly nonlinear equations. In the development of a reliable tracked vehicle model for real-time simulation, it is helpful to use an off-line tracked vehicle model developed by considering all the degrees of freedom of each element. This paper presents a step-by-step procedure for the development of a real-time simulation model based on the off-line tracked vehicle model. The road input data, Profile IV, is used for the real time simulation and simulation results are compared with vehicle test results obtained in the military test field. It is noted that the simulation results are quite close to the test results.

• 제어로봇시스템학회논문지
• /
• 제18권4호
• /
• pp.359-364
• /
• 2012

Real-Time Traversability should be analyzed from the equiped sensors' data in real time for autonomous outdoor navigation. However, it is difficult to find out such traversability that considers the terrain roughness and the vehicle dynamics especially in case of skid type vehicle. The traversability based on real time dynamic analysis was proposed to solve such problem but in navigation with strait driving path. To adapt the method into the navigation with curved driving path, a path following controller should be incorporated into the dynamic model even though it cause the real time problem. In this paper, a dynamic model is proposed to solve the real time problem in the traversability analysis based on real time dynamic simualtion. The dynamic model contains the control dummy which is connected to the vehicle body with a universal joint to follow the curved path without controller. Simulation and experimental results on $6{\times}6$ articulated unmanned ground vehicle demonstrate the method's effectiveness and applicability into the traversability analysis on terrain with bumps.

• 한국컴퓨터정보학회논문지
• /
• 제20권12호
• /
• pp.37-44
• /
• 2015

In this paper, we propose the assistance method to enable safe driving through analysis of dangerous driving behavior using real-time alarm by vehicle speed, azimuth data and smartphone. For this method, smartphone is receiving driving data from digital tachograph using communication. Safe driving habit is a very important issue to commercial vehicle because that driver's long time driving than other vehicle type driver. Existing methods are very inefficient to improve immediately dangerous driving habits during driving because proceed driving behavior analysis after the vehicle operation. We propose the new safe driving assistance method that can prevent traffic accidents by real-time and improve the driver's wrong driving habits through real-time dangerous driving behavior analysis and notification the result to the driver. We have confirmed that the method in this paper will help to improve driving habits and can be applied through the proposed method implementation and simulation experiment.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2018년도 추계학술대회
• /
• pp.548-551
• /
• 2018

대다수 차량은 문제가 발생하면 사용자가 직접 정비소에 방문하여 정비가 이뤄지는 형태를 취하고 있다. 정비가 이뤄지는 동안 사용자는 운행을 하지 못하는 불편함과 함께, 대상 차량이 수익을 창출하는 차량이라면 경제적인 손실도 감수해야 한다. 실시간으로 차량 정보를 수집하고, 수집된 빅데이터를 기반으로 차량에서 발생할 수 있는 문제를 파악하여 사후 서비스 보다는 사전 서비스를 제공한다면, 안정된 차량 운행에 도움을 줄 수 있으며, 경제적 손실도 감소할 수 있다. 이에 본 논문에서는 IoT기반 게이트웨이를 설계하고, 실시간 차량 정보를 수집하여 빅데이터를 구성하여 실시간으로 차량 정보를 제공할 수 있는 플랫폼을 설계하였다.

• 전기학회논문지
• /
• 제62권10호
• /
• pp.1458-1464
• /
• 2013

This paper proposed a new real time catenary impedance estimation technique using synchronized power data from the measured data of operating vehicle and substation for catenary protective relay and fault locator setting. This paper presented estimation equation of catenary impedance using synchronized power data between substation and vehicle of AT feeding system for the performance verification of the proposed technique. Also AC feeding system is modeled through power analysis program and performance was verified through simulation according to various load changes. We verified that average 2.38%(distance equivalent 23.8 m) error appeared between the proposed estimation equation of catenary impedance and power analysis program simulation output in no connection double track system between up track and down track. Furthermore, We confirmed that estimation error is bigger depending on the increasing the distance from substation and vehicle impedance using only using vehicle current when calculating vehicle impedance in connection double track system between up track and down track. But, We confirmed that the proposed technique estimated accurately catenary impedance regardless of vehicle impedance and distance from substation.

• 자동차안전학회지
• /
• 제12권1호
• /
• pp.52-61
• /
• 2020

In recent years, the increasing interest in health-care requires the industrial products to be well-designed ergonomically. In the commercial vehicle industry, several researchers have demonstrated the driver's posture has great effect on the orthopedic desease such as fatigue, back pain, scoliosis, and so on. However, the existing sensor systems developed for measuring the driver posture in real time have suffered from inaccuracy and low reliability issues. Here, we suggest our smart vehicle seat system capable of real-time driver posture monitoring by using the air bag sensor package with high sensitivity and reliability. The ergonomic numerical model which can evaluate a driver's posture has been developed on the basis of the human body segmentation method followed by simulation-based validation. Our experimental analysis of obtained pressure distribution of a vehicle seat under the different driver's postures revealed our smart vehicle system successfully achieved the driver's real-time posture data in great agreement with our numerical model.

• Journal of Positioning, Navigation, and Timing
• /
• 제9권2호
• /
• pp.131-138
• /
• 2020

In this paper, we analyze the delay phenomenon that can occur when controlling an unmanned aerial vehicle using a camera and describe a solution to solve the phenomenon. The group of pictures (GOP) value is changed in order to reduce the delay according to the frame data size that can occur in the moving image data transmission. The appropriate GOP values were determined through experimental data accumulation and validated through camera self-test, system integration laboratory (SIL) verification test and system integration test.