• The Journal of Bigdata
• /
• v.4 no.2
• /
• pp.207-220
• /
• 2019

Recent developments in information and communication technology has enabled the deployment of sensor based data to provide real-time services. In Korea, The Korea Transportation Safety Authority is collecting driving information of all commercial vehicles through a fitted digital tachograph (DTG). This information gathered using DTG can be utilized in various ways in the field of transportation. Notably in autonomous driving, the real-time analysis of this information can be used to prevent or respond to dangerous driving behavior. However, there is a limit to processing a large amount of data at a level suitable for real-time services using a traditional database system. In particular, due to a such technical problem, the processing of large quantity of traffic big data for real-time commercial vehicle operation information analysis has never been attempted in Korea. In order to solve this problem, this study optimized the new database server system and confirmed that a real-time service is possible. It is expected that the constructed database system will be used to secure base data needed to establish digital twin and autonomous driving environments.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.717-719
• /
• 2015

The research and development of the unmanned vehicle is being carried out actively in domestic and foreign countries. The research is being carried out to provide various services so that the weakness of system such as conventional 2D-based navigation systems can be supplemented and the driving can be safer. This paper suggests the method that enables real-time video processing in more efficient way by realizing the location detection and signal recognition technique of traffic signals in video. In order to overcome the limit of conventional methods that have a difficulty in analyzing the signal as it is sensitive to brightness change, the proposed method realizes the program that grasps the depth data in front of the vehicle using video processing, analyzes the signal by detecting traffic signal and estimates color components of traffic signal in front and the distance between traffic signal and the vehicle.

• Annual Conference of KIPS
• /
• 2018.10a
• /
• pp.509-511
• /
• 2018

셀프 카메라로 배경과 함꼐 사용자 자기 자신의 전신 샷을 찍을 수 있도록 도와주는 '셀카봉'이 등장하였지만 아직도 사용자부터 카메라까지 거리의 한계가 존재하기 때문에 셀프 카메라를 찍는 것에 불편함이 있다. 이러한 문제점을 해결하기 위해 드론을 이용하여 셀프 카메라를 찍을 수 있도록 하는 기술을 제안한다. Real-Time 영상처리를 이용해 웹과 드론이 서로 통신을 하여 Haar Cascade 알고리즘을 기반으로 사용자의 얼굴을 실시간으로 인식하고 PID 제어를 통해 드론을 자동으로 조종한다면 사용자의 제스쳐에 인식해 드론의 촬영 기능을 컨트롤 할 수 있도록 한다.

• Broadcasting and Media Magazine
• /
• v.27 no.2
• /
• pp.35-42
• /
• 2022

3차원 깊이 영상은 시점으로부터 객체까지의 거리와 관련된 정보를 제공하는 영상으로 최근 자율주행 자동차, 스마트 드론, 로보틱스, 증강 현실, 의료 영상 등에 핵심 정보로 활용되는 매우 중요한 정보이다. 이에 따라 컴퓨터 비전 분야에서는 2차원 영상으로부터 3차원 깊이 정보를 획득하는 연구가 계속되어 왔고, 최근 인공지능 기술의 발달에 힘입어 그 성능도 나날이 향상되고 있다. 그 중에서도 스테레오 영상 간의 매칭을 통하여 깊이 정보를 획득하는 스테레오 매칭 기술은 데이터베이스 구축이 비교적 용이하고 획득 환경이 제한적이지 않다는 장점으로 인해 널리 활용되고 있다. 하지만 텍스쳐가 없는 영역, 패턴이 반복되는 영역, 가림 영역 등에서 성능에 한계를 보이기 때문에, 깊이 영상의 신뢰도를 추정하는 스테레오 깊이 영상의 신뢰도 추정 기술을 이용하여 깊이 정보를 효과적으로 복원할 수 있다. 본 고에서는 스테레오 매칭을 통하여 획득한 깊이 영상의 신뢰도 추정 기술의 발전 동향을 살펴보고 현재 기술의 한계점과 향후 나아갈 방향에 대해서 토의한다.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.12
• /
• pp.158-164
• /
• 2015

Lane detection is one of the key parts among autonomous vehicle technologies because lane keeping and path planning are based on lane detection. Camera is used for lane detection but there are severe limitations such as narrow field of view and effect of illumination. On the other hands, Lidar sensor has the merits of having large field of view and being little influenced by illumination because it uses intensity information. Existing researches that use methods such as Hough transform, histogram hardly handle multiple lanes in the co-occuring situation of lanes and road marking. In this paper, we propose a method based on RANSAC and regularization which provides a stable and precise detection result in the co-occuring situation of lanes and road marking in highway scenarios. This is performed by precise lane point extraction using circular model RANSAC and regularization aided least square fitting. Through quantitative evaluation, we verify that the proposed algorithm is capable of multi lane detection with high accuracy in real-time on our own acquired road data.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.8
• /
• pp.1-8
• /
• 2020

Air ducts installed for ventilation inside buildings accumulate contaminants during their service life. Robots are installed to clean the air duct at low cost, but they are still not fully automated and depend on manpower. In this study, an intersection detection algorithm for autonomous driving was applied to an air duct cleaning robot. Autonomous driving of the robot was achieved by calculating the distance and angle between the extracted point and the center point through the intersection detection algorithm from the camera image mounted on the robot. The training data consisted of CAD images of the duct interior as well as the cross-point coordinates and angles between the two boundary lines. The deep learning-based CNN model was applied as a detection algorithm. For training, the cross-point coordinates were obtained from CAD images. The accuracy was determined based on the differences in the actual and predicted areas and distances. A cleaning robot prototype was designed, consisting of a frame, a Raspberry Pi computer, a control unit and a drive unit. The algorithm was validated by video imagery of the robot in operation. The algorithm can be applied to vehicles operating in similar environments.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.6
• /
• pp.124-136
• /
• 2019

Autonomous driving at intersections requires assistance by exchanging traffic information between traffic objects due to the intersection of various vehicles and complicated driving environment. For this reason, traffic information exchange between adjacent intersections is required, but the node ID representing the intersection in the Korean standard node link system have limitations in updating intersections and identifying location information of intersections through IDs due to the configuration system including serial numbers. In this paper, we designed a coordinate-based intersection ID configuration system created by processing and merging two-dimensional coordinates of intersections to include location information in the intersection ID. In order to verify the applicability of the proposed intersection ID, we applied a new intersection ID to domestic intersections and confirmed that there are no duplicate values. Coordinate-based intersection ID reduces data size by 60% compared to existing node ID, and enables spatial queries such as searching for nearby intersections and extracting intersections in specific areas in the form of boxes without GIS tools. Therefore, coordinate-based intersection ID is expected to be more scalable and utilized than existing node ID.

• Journal of Korean Society for Geospatial Information Science
• /
• v.25 no.2
• /
• pp.21-29
• /
• 2017

For the efficient and stable operation of autonomous vehicles or advanced driver assistance systems being actively studied nowadays, it is important to determine the positions of the vehicle accurately and economically. A satellite based navigation system is mainly used for positioning, but it has a limitation in signal blockage areas. To overcome this limitation, sensor fusion methods including additional sensors such as an inertial navigation system have been mainly proposed but the high sensor cost has been a problem. In this work, we develop a vehicle position estimation algorithm using in-vehicle sensors and a low-cost imaging sensor without any expensive additional sensor. We determine the vehicle positions using the velocity and yaw-rate of a car from the in-vehicle sensors and the position and attitude of the camera based on the single photo resection process. For the evaluation, we built a prototype system, acquired test data using the system, and estimated the trajectory. The proposed algorithm shows the accuracy of about 40% higher than an in-vehicle sensor only method.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.229-229
• /
• 2023

강화학습은 에이전트(agent)가 주어진 환경(environment)과의 상호작용을 통해서 상태(state)를 변화시켜가며 최대의 보상(reward)을 얻을 수 있도록 최적의 행동(action)을 학습하는 기계학습법을 의미한다. 최근 알파고와 같은 게임뿐만 아니라 자율주행 자동차, 로봇 제어 등 다양한 분야에서 널리 사용되고 있다. 상수도관망 분야의 경우에도 펌프 운영, 밸브 운영, 센서 최적 위치 선정 등 여러 문제에 적용되었으나, 설계에 강화학습을 적용한 연구는 없었다. 설계의 경우, 관망의 크기가 커짐에 따라 알고리즘의 탐색 공간의 크기가 증가하여 기존의 최적화 알고리즘을 이용하는 것에는 한계가 존재한다. 따라서 본 연구는 강화학습을 이용하여 상수도관망의 구성요소와 환경요인 간의 복잡한 상호작용을 고려하는 설계 방법론을 제안한다. 모델의 에이전트를 딥 강화학습(Deep Reinforcement Learning)으로 구성하여, 상태 및 행동 공간이 커 발생하는 고차원성 문제를 해결하였다. 또한, 해당 모델의 상태 및 보상으로 절점에서의 압력 및 수요량과 설계비용을 고려하여 적절한 수량과 수압의 용수 공급이 가능한 경제적인 관망을 설계하도록 하였다. 모델의 행동은 실제로 공학자가 설계하듯이 절점마다 하나씩 차례대로 다른 절점과의 연결 여부를 결정하는 것으로, 이를 통해 관망의 레이아웃(layout)과 관경을 결정한다. 본 연구에서 제안한 방법론을 규모가 큰 그리드 네트워크에 적용하여 모델을 검증하였으며, 고려해야 할 변수의 개수가 많음에도 불구하고 목적에 부합하는 관망을 설계할 수 있었다. 모델 학습과정 동안 에피소드의 평균 길이와 보상의 크기 등의 변화를 비교하여, 제안한 모델의 학습 능력을 평가 및 보완하였다. 향후 강화학습 모델을 통해 신뢰성(reliability) 또는 탄력성(resilience)과 같은 시스템의 성능까지 고려한 설계가 가능할 것으로 기대한다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.2
• /
• pp.325-336
• /
• 2023

With the development of autonomous driving technology, the number of external contact sensors mounted on vehicles is increasing, and the importance is also rising. The vehicular ultrasonic sensor uses the LIN protocol in the form of a bus topology and reports a status message about its surroundings through the vehicle's internal network. Since ultrasonic sensors are vulnerable to various threats due to poor security protocols, physical testing on actual vehicle is needed. Therefore, this paper developed a LIN-CAN co-analysis testbed with a jig for location-specific distance test to examine the operational relation between LIN and CAN caused by ultrasonic sensors.