• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.2
• /
• pp.231-238
• /
• 2023

Since there is a limit to the physically visible horizon that sensors for autonomous driving can perceive, complementary utilization of digital map data such as a Local Dynamic Map (LDM) along the probable route of an Autonomous Vehicle (AV) is proposed for safe and efficient driving. Although the amount of digital map data may be insignificant compared to the amount of information collected from the sensors of an AV, efficient management of map data is inevitable for the efficient information processing of AVs. The objective of this study is to analyze the efficiency of information use and information processing time of AV according to the expansion of the active section of LDM-based static road and traffic information. To carry out this objective, a microscopic simulator model, VISSIM and VISSIM COM, was employed, and an area of about 9 km × 13 km was selected in the Busan Metropolitan Area, which includes heterogeneous traffic flows (i.e., uninterrupted and interrupted flows) as well as various road geometries. In addition, the LDM information used in AVs refers to the real high-definition map (HDM) built on the basis of ISO 22726-1. As a result of the analysis, as the electronic horizon area increases, while short links are intensively recognized on interrupted urban roads and the sum of link lengths increases as well, the number of recognized links is relatively small on uninterrupted traffic road but the sum of link lengths is large due to a small number of long links. Therefore, this study showed that an efficient range of electronic horizon for HDM data collection, processing, and management are set as 600 m on interrupted urban roads considering the 12 links corresponding to three downstream intersections and 700 m on uninterrupted traffic road associated with the 10 km sum of link lengths, respectively.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.05a
• /
• pp.141-146
• /
• 2003

본 논문에서는 문자열 영역 추출을 위한 3배 축소 명함 영상, 개별 문자 추출을 위한 2배 축소 명함 영상, 정확한 인식을 위한 원본 영상으로 명함 영상을 분리하고, 분리된 영상들을 대상으로 각 영상 크기에 적합한 처리를 수행하고 각각의 결과들을 이용하여 정확한 문자를 추출할 수 있는 방법을 제안한다 그리고 추출된 개별 문자들의 인식을 위해서 ART1을 적용한 개선된 RBF 네트워크를 제안하여 적용한다 제안된 명함 추출 방법은 원 영상을 각각의 처리 방법에 적합하도록 하기 위해서 다해상도로 분리한다. 문자열의 추출은 문자들의 간격을 축소 시켜서 블록을 추출하기 쉬운 적절한 최소 크기의 영상에서 수행하고, 개별 문자의 추출은 문자들의 간격을 분리할 수 있는 적절한 영상의 크기에서 수행한다 개별 문자 인식은 문자의 형태학적 특성을 잘 나타내기 위해서 원본 영상에 적용한다 본 논문에서 제안한 추출 방법은 문자를 정확히 추출할 수 있으며 병렬 처리가 가능하여 처리시간을 단축할 수 있는 장점을 가진다. 그리고 정확히 추출된 개별 문자들을 개선된 R8F 네트워크를 이용하여 인식률을 향상시킨다. 제안된 명함 추출 및 인식 방법의 성능을 확인하기 위해서 실제 영문 명함 영상을 대상으로 실험한 결과, 기존의 방법보다 명함 추출 및 인식에서 우수한 성능이 있음을 확인하였다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.08a
• /
• pp.60-64
• /
• 1998

음성인식 시스템의 실용화 과정에서 훈련환경과 테스트 환경의 불일치로 인한 인식성능의 저하는 반드시 극복되어야 할 문제이다. 본 논문에서는 잡음 tR인 입력음성의 비음성구간에서 잡음레벨을 추정하여 음성 스펙트럼에서 추정된 잡음레벨을 빼는 스펙트럼 차감법고 스펙트럼 영역에서 미리 정해진 마스킹 레벨보다 낮은 에너지 값을 마스킹 레벨로 올려주는 잡음 마스킹을 함께 사용함으로써 훈련 환경과 테스트환경의 불일치를 줄이는 방법을 제안한다. 그리고 복수의 마스킹 레벨에 대한 모델들을 미리 만들어 두고 추정된 잡음 레벨에 따라 적합한 마스킹 레벨의 보델을 사용하여 인식을 수해？는 다중 모델 방법을 적용하였다. 자동차 소음환경에서 두 가지 마스킹 레벨에 대한 모델을 이용한 화자독립고립단어 인식 실험을 통하여 본 논문에서 제안한 방식은 정차중 무시동 환경에서 95.8%, 정차중 시동 환경에서 95.6%, 한적한 도로환경에서 92.8%, 복잡한 시내도로 환경에서 89.6%, 고속도로 환경에서 74.4%의 인식성능을 나타내었으며, 평균 90.7%의 성능을 얻을 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.924-926
• /
• 2017

본 논문에서는 좁고 곡률이 큰 도로에서의 자율 주행을 위한 AVM 시스템 기반의 알고리즘을 제안한다. 기존의 전방을 주시하는 모노/스테레오 카메라를 이용한 차선 인식 방법을 이용한 자율주행 알고리즘은 모노/스테레오 카메라의 제한된 FOV (Field of View)로 인해 좁고 곡률이 큰 도로에서의 자율 주행에 한계가 있다. 제안하는 알고리즘은 AVM 시스템을 기반으로 하여 이 한계를 극복하고자 한다. AVM 시스템에서 얻은 영상을 차선의 색상 정보를 이용해 차선의 영역을 이진화 한다. 이진화 영상으로부터, 차량의 뒷바퀴 주변의 관심영역을 시작으로 재귀적 탐색법을 이용하여 좌, 우 차선을 검출한다. 검출된 좌, 우 차선의 중앙선을 차량의 경로로 삼고 조향각을 산출해 낸다. 제한하는 알고리즘을 실제 차량에 적용시킨 실험을 수행하였고, 운전면허 시험장의 코스를 차선의 이탈없이 주행 가능함을 실험적으로 확인하였다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.13 no.6
• /
• pp.1-9
• /
• 2014

Recently, a study is conducting to image collection and auto detection of attribute information using mobile mapping system. The road sign attribute information detection is difficult because of various size and placement, interference of other facilities like trees. In this study, a text detection method that does not rely on a Korean character template is required to successfully detect the target text when a variety of differently sized texts are present near the target texts. To overcome this, the method of incremental right-to-left blob projection (IRBP) was suggested as a solution; the potential and improvement of the method was also assessed. To assess the performance improvement of the IRBP that was developed, the IRBP method was compared to the existing method that uses Korean templates through the 60 videos of street signs that were used. It was verified that text detection can be improved with the IRBP method.

• Geophysics and Geophysical Exploration
• /
• v.19 no.1
• /
• pp.20-28
• /
• 2016

Recently many sinkholes have appeared in urban areas of Korea, threatening public safety. To predict the occurrence of sinkholes, it is necessary to investigate the existence of cavity under urban roads. Ground-penetrating radar (GPR) has been recognized as an effective means for detecting underground cavity in urban areas. In order to improve the understanding of the governing physical processes associated with GPR wave propagation, and interpret underground cavity effectively, a theoretical approach using numerical modeling is required. We have developed an algorithm employing a three-dimensional (3D) staggered-grid finite-difference time-domain (FDTD) method. This approach allows us to model the full electromagnetic wavefield associated with GPR surveys. We examined the GPR response for a simple cavity model, and the modeling results showed that our 3D FDTD modeling algorithm is useful to assess the underground cavity under urban roads.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.11 no.3
• /
• pp.75-81
• /
• 2011

Protein molecules are combined with another ones which have similar shapes at pocket positions. The pocket positions can be good references to describe the shapes of protein molecules. Harris corner detector is commonly used to detect feature points of 2 or 3D objects. Feature points can be found on the pocket areas and the points which have high derivatives. Generally speaking, the densities of feature points are relatively high at pocket areas because the shapes of pockets are concave. The pocket areas can be decided by the subdivision of voxel cubes which include feature points. The Euclidean distances between feature points and the central coordinate of the decided pocket area are calculated and sorted. The graph of sorted distances describes the shape of a protein molecule and the distribution of feature points. Therefore, it can be used to classify protein molecules by their shapes. Even though the shapes of protein molecules have been distorted with noises, they can be recognized with the accuracy more than 95 %. The accurate shape recognition provides the information to predict the binding properties of protein molecules.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.2
• /
• pp.406-412
• /
• 2006

In this paper, we propose OHT(optimized nough Transform) algorithm for the lane extraction. Input image is changed into 256 gray revel image. Gray level image is separated into background region and road region by using limited horizontal projection value. In separated road area, we apply OHT algorithm. OHT algorithm is characterized as follows. First, the number of candidate pixels is reduced using the outline orientation of the lane. Second, each range of the left and right lane is defined by limited ${\theta}$ Experimental results show that the proposed method is better than Hough Transform.

• Journal of the Institute of Convergence Signal Processing
• /
• v.2 no.4
• /
• pp.31-37
• /
• 2001

License plate recognition system for an exclusive bus-lane is made of 5 core parts which are vehicle detection, image acquisition individual character extraction, character recognition and data transmission. Among them, the accuracy of license plate extraction can bring effect significantly to the accuracy of a whole system recognition rate also the more exact extraction of license plate is required in various weather and environment conditions. Therefore in this paper we propose a plat extraction algorithm that makes pyramid structure to reduced the extraction processing time binarizes plate's template region using adaptive thresholding extracts candidate region containing plate, and verifies a final region using plate character distribution characteristics among the candidates. Experimenal results were exactly extracted the license plate region by using proposed method to the image obtained in an exclusive bus-lane with various weather and environment conditions.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.1
• /
• pp.93-101
• /
• 2021

In this paper, a vehicle license plate detection scheme is proposed that uses the spatial attention areas to detect accurately the license plates in various real-road situations. First, the previous WPOD-NET was analyzed, and its detection accuracy is evaluated as lower due to the unnecessary noises in the wide detection candidate areas. To resolve this problem, a vehicle license plate detection model is proposed that uses the candidate area of the license plate as a spatial attention areas. And we compared its performance to that of the WPOD-NET, together with the case of using the optimal spatial attention areas using the ground truth data. The experimental results show that the proposed model has about 20% higher detection accuracy than the original WPOD-NET since the proposed scheme uses tight detection candidate areas.