• 제어로봇시스템학회논문지
• /
• 제3권4호
• /
• pp.415-421
• /
• 1997

A car driving trainer for beginners developed under PC-based environment is described in this paper. For this trainer, a hardware is implemented as a practice car, and a trainer program is designed by computer image generation method to display 3-dimensional images on a CRT monitor. The trainer program consists of 3 main parts, that is, a speed estimate part, a wheel trace calculation part and a driving image generation part. Furthermore, a map editor is also installed for taking any test drive. After comparing this driving trainer to specify it was verified that the developed car driving trainer showed has good performances, such as lower cost, higher resolution and better image display speed.

• 한국정밀공학회지
• /
• 제17권7호
• /
• pp.80-89
• /
• 2000

Driving simulators provide engineers with a power tool in the development and modification stages of vehicle models. One of the most important factors to realistic simulations is the fidelity obtained by a motion bed and a real-time visual image generation algorithm. Virtual reality technology has been widely used to enhance the fidelity of vehicle simulators. This paper develops the virtual environment for such visual system as head-mounted display for a vehicle driving simulator. Virtual vehicle and environment models are constructed using the object-oriented analysis and design approach. Based on the object model, a three-dimensional graphic model is completed with CAD tools such as Rhino and Pro/ENGINEER. For real-time image generation, the optimized IRIS Performer 3D graphics library is embedded with the multi-thread methodology. The developed software for a virtual driving simulator offers an effective interface to virtual reality devices.

• 한국자동차공학회논문집
• /
• 제8권4호
• /
• pp.158-168
• /
• 2000

Vehicle driving simulators can provide engineers with benefits on the development and modification of vehicle models. One of the most important factors to realistic simulations is the fidelity given by a motion system and a real-time visual image generation system. Virtual reality technology has been widely used to achieve high fidelity. In this paper the virtual environment including a visual system like a head-mounted display is developed for a vehicle driving simulator system by employing the virtual reality technique. virtual vehicle and environment models are constructed using the object-oriented analysis and design approach. Accordint to the object model a three dimensional graphic model is developed with CAD tools such as Rhino and Pro/E. For the real-time image generation the optimized IRIS Performer 3D graphics library is embedded with the multi-thread methodology. Compared with the single loop apprach the proposed methodology yields an acceptable image generation speed 20 frames/sec for the simulator.

• ETRI Journal
• /
• 제43권4호
• /
• pp.603-616
• /
• 2021

Over the last few years, autonomous vehicles have progressed very rapidly. The odometry technique that estimates displacement from consecutive sensor inputs is an essential technique for autonomous driving. In this article, we propose a fast, robust, and accurate odometry technique. The proposed technique is light detection and ranging (LiDAR)-based direct odometry, which uses a spherical range image (SRI) that projects a three-dimensional point cloud onto a two-dimensional spherical image plane. Direct odometry is developed in a vision-based method, and a fast execution speed can be expected. However, applying LiDAR data is difficult because of the sparsity. To solve this problem, we propose an SRI generation method and mathematical analysis, two key point sampling methods using SRI to increase precision and robustness, and a fast optimization method. The proposed technique was tested with the KITTI dataset and real environments. Evaluation results yielded a translation error of 0.69%, a rotation error of 0.0031°/m in the KITTI training dataset, and an execution time of 17 ms. The results demonstrated high precision comparable with state-of-the-art and remarkably higher speed than conventional techniques.

• 한국전자통신학회논문지
• /
• 제16권6호
• /
• pp.1311-1316
• /
• 2021

본 논문에서는 이중시점 스테레오 이미지와 그에 상응하는 깊이맵을 생성하기 위해 서로 다른 초점거리를 가지고 있는 두 카메라를 결합한 이중시점 스테레오 카메라 시스템을 제안한다. 제안한 이중초점 스테레오 카메라 시스템을 이용해 깊이맵을 생성하기 위해서는 먼저 서로 다른 초점을 가진 두 카메라에 대한 카메라 정보를 추출하기 위한 카메라 보정(Camera Calibration)을 수행한다. 카메라 파라미터를 이용해 깊이맵 생성을 위한 공통 이미지 평면을 생성하고 스테레오 이미지 정렬화(Image Rectification)를 수행한다. 마지막으로 정렬화된 스테레오 이미지를 이용하여 깊이맵을 생성하였다. 본 논문에서는 깊이맵을 생성하기 위해서 SGM(Semi-global Matching) 알고리즘을 사용하였다. 제안한 이중초점 스테레오 카메라 시스템은 서로 다른 초점 카메라들이 수행해야 하는 기능을 수행함과 동시에 두 카메라를 이용한 스테레오 정합(Stereo Matching)을 통해서 현재 주행 중인 환경에서의 차량, 보행자, 장애물과의 거리 정보까지 생성할 수 있어서 보다 안전한 자율주행 차량 설계를 가능하게 하였다.

• Transactions on Electrical and Electronic Materials
• /
• 제8권4호
• /
• pp.166-169
• /
• 2007

In applying LCD to TV application, one of the most significant factors to be improved is image sticking on the moving picture. LCD is different from CRT in the sense that it's continuous passive device, which holds images in entire frame period, while impulse type device generate image in very short time. To reduce image sticking problem related to hold type display mode, we made an experiment to drive TN-LCD like CRT. We made articulate images by turn on-off backlight, and we realized the ratio of Back Light on-off time by counting between on time and off time for video signal input during 1 frame (16.7 ms). Conventional CCFL (cold cathode fluorescent lamp) cannot follow fast on-off speed, so we evaluated new fluorescent substances of light source to improve residual light characteristic of CCFL. We realized articulate image generation similar to CRT by CCFL blinking drive and TN-LCD overdriving. As a result, reduced image sticking phenomenon was validated by naked eye and response time measurement.

• 대한임베디드공학회논문지
• /
• 제14권1호
• /
• pp.1-9
• /
• 2019

In this paper, we propose a method of generating a 2D gray image from LiDAR 3D reflection intensity. The proposed method uses the Fully Convolutional Network (FCN) to generate the gray image from 2D reflection intensity which is projected from LiDAR 3D intensity. Both encoder and decoder of FCN are configured with several convolution blocks in the symmetric fashion. Each convolution block consists of a convolution layer with $3{\times}3$ filter, batch normalization layer and activation function. The performance of the proposed method architecture is empirically evaluated by varying depths of convolution blocks. The well-known KITTI data set for various scenarios is used for training and performance evaluation. The simulation results show that the proposed method produces the improvements of 8.56 dB in peak signal-to-noise ratio and 0.33 in structural similarity index measure compared with conventional interpolation methods such as inverse distance weighted and nearest neighbor. The proposed method can be possibly used as an assistance tool in the night-time driving system for autonomous vehicles.

• ETRI Journal
• /
• 제44권6호
• /
• pp.1004-1019
• /
• 2022

For autonomous driving without high-definition maps, we present a model capable of generating multiple plausible paths from egocentric images for autonomous vehicles. Our generative model comprises two neural networks: feature extraction network (FEN) and path generation network (PGN). The FEN extracts meaningful features from an egocentric image, whereas the PGN generates multiple paths from the features, given a driving intention and speed. To ensure that the paths generated are plausible and consistent with the intention, we introduce an attentive discriminator and train it with the PGN under a generative adversarial network framework. Furthermore, we devise an interaction model between the positions in the paths and the intentions hidden in the positions and design a novel PGN architecture that reflects the interaction model for improving the accuracy and diversity of the generated paths. Finally, we introduce ETRIDriving, a dataset for autonomous driving, in which the recorded sensor data are labeled with discrete high-level driving actions, and demonstrate the state-of-the-art performance of the proposed model on ETRIDriving in terms of accuracy and diversity.

• 한국IT서비스학회지
• /
• 제22권2호
• /
• pp.57-70
• /
• 2023

In order to establish an autonomous driving environment, it is necessary to study traffic safety and demand prediction by analyzing information generated from the transportation infrastructure beyond relying on sensors by the vehicle itself. In this paper, we propose a real-time traffic information generation method using sensor convergence technology of transportation infrastructure. The proposed method uses sensors such as cameras and radars installed in the transportation infrastructure to generate information such as crosswalk pedestrian presence or absence, crosswalk pause judgment, distance to stop line, queue, head distance, and car distance according to each characteristic. create information An experiment was conducted by comparing the proposed method with the drone measurement result by establishing a demonstration environment. As a result of the experiment, it was confirmed that it was possible to recognize pedestrians at crosswalks and the judgment of a pause in front of a crosswalk, and most data such as distance to the stop line and queues showed more than 95% accuracy, so it was judged to be usable.

• 한국산업정보학회논문지
• /
• 제24권2호
• /
• pp.25-31
• /
• 2019

최근 인공지능 기술이 급격히 발전하면서 첨단 운전자 지원 시스템 분야에 딥러닝 기술을 접목하여 기존의 기술보다 뛰어난 성능을 보여주기 위한 여러 연구들이 진행 되고 있다. 이러한 동향에 맞춰 본 논문 또한 첨단 운전자 지원 시스템의 핵심 요소 중 하나인 차로이탈 경고시스템에 딥러닝 기술을 접목한 방법을 제안한다. 제안하는 방법과 기존의 차선검출 기반의 경고시스템과의 비교 실험을 통해 그 성능을 평가 하였다. 고속도로 주행영상과 시내 주행영상을 이용한 두 가지의 서로 다른 환경에서 모두 제안하는 방법이 정확도 및 정밀도 부분에서 더 높은 수치를 보여주었다.