• Proceedings of the Korea Contents Association Conference
• /
• 2005.05a
• /
• pp.437-442
• /
• 2005

본 연구에서는 칼라정보와 주성분분석법(principal component analysis : PCA)를 이용한 차량 번호판 인식시스템을 구성하였다. 먼저 입력된 차량 영상에서 번호판의 형태적 특징과 녹색 칼라 정보를 이용하여 번호판 영역을 추출하였으며, 추출된 번호판내의 문자 및 숫자의 위치적 특징을 이용하여 번호판의 종류(구형, 신형, 최신형)를 구분하였다. 이렇게 추출되고 구분된 번호판은 문자의 상대적 위치정보와 수평 및 수직 투영 정보를 함께 이용하여 각각의 문자영역을 분리 추출하였다. 추출된 문자영역은 주성분분석법을 이용하여 고유벡터를 추출한 후 문자 인식에 사용하였다. 본 논문의 실험과정에서는 다양한 시간대 환경에서 촬영된 주행 중인 자동차 320대의 자가용 차량영상에 대하여 실험하였으며 높은 번호판 추출률과 번호판종류 구분률 그리고 문자 인식률을 얻을 수 있었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.943-945
• /
• 2005

교통 표지판은 안전하고 효율적인 주행을 위해 운전자에게 여러 가지 정보를 제공한다. 따라서 교통 표지판의 자동인식은 자동운전이나 안전운전 시스템 등에 중요하게 사용될 수 있다. 본 논문은 영상에서 나타난 여러 가지 도로시설물 중 교통 표지판을 인식하는 알고리즘을 제안한다. 제안된 알고리즘은 교통 표지판이 가지고 있는 색상, 밝기, 형태 등의 정보를 이용하여 교통 표지판을 자동으로 인식한다. 일반적인 영상처리에서는 RGB 색상 공간의 처리는 간단하지만 날씨나 조명 상태의 변화에 민감하므로 본 논문에서는 색상과 채도에서 컬러 인지력이 높은 HSI 공간을 활용하여 주변 환경의 영향을 줄였다. 또한 고속 인식을 위하여 영상 모멘트 템플릿 정합을 사용하여 신경 회로망을 구성하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.05a
• /
• pp.639-642
• /
• 2003

차량의 수가 급격히 증가함에 따라 보다 지능적인 번호판 자동인식체계가 요구된다. 따라서 본 논문은 주행하는 차량에서 기울어진 번호판을 포함한 효율적인 자동차 번호판 인식방법을 제안하였다. 실험결과로서 일반적인 환경에서 획득된 인식 비율은 약 99%의 높은 성공률을 나타내었으며, 번호판이 차량에 비례하여 많이 기울어지게 위치해 있을 경우에도 97%의 성공률을 나타내었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.925-927
• /
• 2022

본 논문에서는 자율주행을 통해 보도를 청소하는 동안 분실물을 인지할 수 있는 로봇 시스템을 개발하였다. 분실물의 종류는 딥러닝 모델에 의해 지정되고 학습되며 로봇은 이를 인식하여 저장한다. 보도 경계 및 장애물을 감지하기 위해 Image-Segmentation 기술을 사용하였으며, 물체 감지에 사용되는 depth 카메라(d435)를 사용하였다. 학습하기 위한 딥러닝 모델로 YOLOv5 를 사용하였으며, 그 결과 정해진 사물을 인식하는 데 평균 84%의 정확도를 보였다. 이 시스템을 로봇에 적용할 경우 예상되는 효과로는 정확한 보도 인식으로 로봇이 경로를 이탈하지 않도록 하는 것, 유실물품의 신속하고 안전한 인계 등이 있다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.2 s.308
• /
• pp.65-72
• /
• 2006

The traffic lights detection and recognition system is an essential module of the driver warning and assistance system. A method which is a color vision-based real time detection and recognition of traffic lights is presented in this paper This method has four main modules : traffic signals lights detection module, traffic lights boundary candidate determination module, boundary detection module and recognition module. In traffic signals lights detection module and boundary detection module, the color thresholding and the subtraction value of saturation and intensity in HSI color space and detection probability mask for lights detection are used to segment the image. In traffic lights boundary candidate determination module, the detection mask of traffic lights boundary is proposed. For the recognition module, the AND operator is applied to the results of two detection modules. The input data for this method is the color image sequence taken from a moving vehicle by a color video camera. The recorded image data was transformed by zooming function of the camera. And traffic lights detection and recognition experimental results was presented in this zoomed image sequence.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.6
• /
• pp.241-250
• /
• 2019

Road signs are guide facilities for road users, and the Ministry of Land, Infrastructure and Transport has established and operated a system to enhance the convenience of managing these road signs. The role of road signs will decrease in the future autonomous driving, but they will continue to be needed. For the accurate mechanical recognition of texts on road signs, automatic road sign recognition equipment has been developed and it has applied image-based text recognition technology. Yet there are many cases of misrecognition due to irregular specifications and external environmental factors such as manual manufacturing, illumination, light reflection, and rainfall. The purpose of this study is to derive location-based destination names for finding misrecognition errors that cannot be overcome by image analysis, and to improve the automatic recognition of road signs destination names by using Levenshtein similarity verification method based on phoneme separation.

• Journal of Auto-vehicle Safety Association
• /
• v.11 no.2
• /
• pp.35-43
• /
• 2019

This paper describes the improved environment recognition algorithms using some type of sensors like LiDAR and cameras. Additionally, integrated control algorithm for an autonomous vehicle is included. The integrated algorithm was based on C++ environment and supported the stability of the whole driving control algorithms. As to the improved vision algorithms, lane tracing and traffic sign recognition were mainly operated with three cameras. There are two algorithms developed for lane tracing, Improved Lane Tracing (ILT) and Histogram Extension (HIX). Two independent algorithms were combined into one algorithm - Enhanced Lane Tracing with Histogram Extension (ELIX). As for the enhanced traffic sign recognition algorithm, integrated Mutual Validation Procedure (MVP) by using three algorithms - Cascade, Reinforced DSIFT SVM and YOLO was developed. Comparing to the results for those, it is convincing that the precision of traffic sign recognition is substantially increased. With the LiDAR sensor, static and dynamic obstacle detection and obstacle avoidance algorithms were focused. Therefore, improved environment recognition algorithms, which are higher accuracy and faster processing speed than ones of the previous algorithms, were proposed. Moreover, by optimizing with integrated control algorithm, the memory issue of irregular system shutdown was prevented. Therefore, the maneuvering stability of the autonomous vehicle in severe environment were enhanced.

• KIPS Transactions on Computer and Communication Systems
• /
• v.2 no.10
• /
• pp.427-436
• /
• 2013

In this paper, a method of moving path control of an automatic guided vehicle in an indoor environment through recognition of marker images using vision sensors is presented. The existing AGV moving control system using infrared-ray sensors and landmarks have faced at two critical problems. Since there are many windows in a crematorium, they are going to let in too much sunlight in the main hall which is the moving area of AGVs. Sunlight affects the correct recognition of landmarks due to refraction and/or reflection of sunlight. The second one is that a crematorium has a narrow indoor environment compared to typical industrial fields. Particularly when an AVG changes its direction to enter the designated furnace the information provided by guided sensors cannot be utilized to estimate its location because the rotating space is too narrow to get them. To resolve the occurrences of such circumstances that cannot access sensing data in a WSN environment, a relative distance from marker to an AGV will be used as fingerprinting used for location estimation. Compared to the existing fingerprinting method which uses RSS, our proposed method may result in a higher reliable estimation of location. Our experimental results show that the proposed method proves the correctness and applicability. In addition, our proposed approach will be applied to the AGV system in the crematorium so that it can transport a dead body safely from the loading place to its rightful destination.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.2
• /
• pp.61-69
• /
• 2022

As the delivery industry grew around the restaurant industry along with the COVID-19 situation, the number of delivery workers increased significantly. Along with that, new forms of delivery using personal mobility (PM) also emerged and two-wheeled or PM-related accidents are steadily increasing. This study manufactures a PM's driving analysis device to establish a safe delivery monitoring environment. This system was constructed to process data collected from the driving analysis device and through a cloud server, which would recognize and record special situations (acceleration/deceleration, speed bump) that could occur during the PM's driving situation. As a result, the angular speed, acceleration, and geomagnetic values collected from the IMU in the device were able to determine whether to drive, drive on the sidewalk, and drive on the speed bump. This technology was able to achieve approximately 1600 times more driving information storage efficiency than conventional image-based recording devices.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.3
• /
• pp.411-422
• /
• 2021

The autonomous driving system mounted on the unmanned vehicle recognizes the external environment through several sensors and derives the optimum control value through it. Recently, studies on physical level attacks that maliciously manipulate sensor data by performing signal-injection attacks have been published. signal-injection attacks are performed at the physical level and are difficult to detect at the software level because the sensor measures erroneous data by applying physical manipulations to the surrounding environment. In order to detect a signal-injection attack, it is necessary to verify the dependability of the data measured by the sensor. As so far, various methods have been proposed to attempt physical level attacks against sensors mounted on autonomous driving systems. However, it is still insufficient that methods for defending and detecting the physical level attacks. In this paper, we demonstrate signal-injection attacks targeting MEMS sensors that are widely used in unmanned vehicles, and propose a method to detect the attack. We present a signal-injection detection model to analyze the accuracy of the proposed method, and verify its effectiveness in a laboratory environment.