• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10b
• /
• pp.85-87
• /
• 2004

유클리드 거리에 기반하여 유사한 시퀀스 검색을 하는 기법들은 각 시퀀스에서 특징을 추출하여 차원을 감소시킨 후, R-tree 같은 다차원 인덱싱 기법을 사용하여 검색을 수행한다. 본 논문에서는 시계열 데이터 베이스에서의 유사 검색 성능 향상을 위한 새로운 특징 추출 기법인 Polar Wavelet 기법을 제안한다. 이 기법은 유사 검색 시 후보 시퀀스의 개수를 줄임으로써 검색 성능을 향상시킬 수 있고, 특징 추출을 위해 시퀀스의 길이를 2$^n$으로 만들 필요가 없는 장점을 갖고 있다.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.9
• /
• pp.3029-3036
• /
• 2000

Image segmentation is one of the important processes in the image information extraction for computer vision systems. The fuzzy clustering methods have been extensively used in the image segmentation because it extracts feature information of the region. Most of fuzzy clustering methods have used the Fuzzy C-means(FCM) algorithm. This algorithm can be misclassified about the different size of cluster because the degree of membership depends on highly the distance between data and the centroids of the clusters. This paper proposes a fuzzy clustering algorithm using the Average Intracluster Distance that classifies data uniformly without regard to the size of data sets. The Average Intracluster Distance takes an average of the vector set belong to each cluster and increases in exact proportion to its size and density. The experimental results demonstrate that the proposed approach has the g

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.6
• /
• pp.81-89
• /
• 2004

In this paper, we compare face recognition rate by PCA algorithm using distance change and embedded data being input left side and right side image in stereo images. The proposed method detects face region from RGB color space to YCbCr color space. Also, The extracted face image's scale up/down according to distance change and extracts more robust face region. The proposed method through an experiment could establish standard distance (100cm) in distance about 30∼200cm, and get 99.05% (100cm) as an average recognition result by scale change. The definition of super state is specification region in normalized size (92${\times}$112), and the embedded data extracts the inner factor of defined super state, achieved face recognition through PCA algorithm. The orignal images can receive specification data in limited image's size (92${\times}$112) because embedded data to do learning not that do all learning, in image of 92${\times}$112 size averagely 99.05%, shows face recognition rate of test 1 99.05%, test 2 98.93%, test 3 98.54%, test 4 97.85%. Therefore, the proposed method through an experiment showed that if apply distance change rate could get high recognition rate, and the processing speed improved as well as reduce face information.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.06a
• /
• pp.319-320
• /
• 2022

본 논문에서는 '지능형 해상교통정보 서비스'로 축적된 선박 위치데이터를 가공하여 선박의 조우상황 데이터를 추출하고 분석하였다. 선박의 위치, 침로, 속력을 통해 TCPA, DCPA와 선박간 거리를 계산함으로써 선박의 충돌위험 인지 후 회피 상황에서 보이는 데이터의 형태와 분포를 분석하였다. 추후 상대방위와 SOG가 TCPA 변화량에 미치는 영향에 대한 연구가 진행되면, 실제 사용자의 충돌위험 판단과 근접한 충돌위험도 분석 모델로 활용할 수 있을 것으로 보인다.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2011.04a
• /
• pp.565-568
• /
• 2011

NURBS는 매개변수를 이용하여 3차원에서 곡면을 표현한 방법으로서 노트벡터, 조정점, 가중치로 구성된다. 레벨셋은 공간을 음함수로 정의된 장으로 형성하여 음함수의 일정한 값을 추적하여 곡면을 표현한 방법이다. 본 논문에서는 스캔 데이터를 NURBS 형태로 추출한 뒤 이를 정밀한 레벨셋 모델로 변환하였다. 레벨셋 모델을 구성하기 위해서 형성된 음함수는 부호를 갖는 거리함수를 사용하였고, 거리함수를 정밀하게 나타내기 위해 Newton 순환법을 이용하였다. 변환된 레벨셋 모델을 이용하여 형상의 몰핑을 수행하였다. 몰핑은 초기 형상을 목표 형상으로 변화시켜 나가는 과정으로서 레벨셋 모델을 이용한 몰핑은 용이성과 질적인 측면에서 우수하다. 수치 예제에서는 스캔 데이터의 레벨셋 모델 변환과 변환된 형상이 자연스럽게 목표형상으로 변화하는지를 확인한다.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.12
• /
• pp.77-86
• /
• 2015

It is difficult to extract small valve automatically in noisy 3D point cloud obtained from LIDAR because small object is affected by noise considerably. In this paper, we assume that the valve is a complex model consisting of torus, cylinder and plane represents handle, rib and center plane to extract a pose of the valve. And to extract the pose, we received additional input: center of the valve. We generated histogram of distance between the center and each points of point cloud, and obtain pose of valve by extracting parameters of handle, rib and center plane. Finally, the valve is reconstructed.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.6
• /
• pp.668-672
• /
• 2005

In this paper, a distance measuring system using a PSD sensor in proposed, which in suitable for low-cost localization sensor of a mobile robot. Because the distance-voltage output of PSD sensor has a non-linear property, the linearizing function is proposed through the experimental characteristics of the sensor. And the characteristics are tested and the distance-voltage data are measured in various colors and materials of object. The parameters of the proposed function are extracted by using the measured data. Finally, the performance and the accuracy of the developed system are verified according to the comparison of the distance by the proposed function with the real distance.

• Journal of Korea Multimedia Society
• /
• v.7 no.4
• /
• pp.474-483
• /
• 2004

In this paper, we present a new Practical implementation of a person verification system using the profile of 3-dimensional(3D) face images based on weighted Hausdorff distance(WHD) used depth information. The approach works on finding the nose tip have protrusion shape on the face using iterative selection method to use a fiducial feint and extract the profile image from vertical 3D data for the nose tip. Hausdorff distance(HD) is one of usually used measures for object matching. This works analyze the conventional HD and WHD, which the weighted factor is depth information. The Ll measure for comparing two feature vectors were used, because it is simple and robust. In the experimental results, the WHD method achieves recognition rate of 94.3% when the ranked threshold is 5.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.768-771
• /
• 2021

시계열 분석은 이전 시점들의 데이터를 기반으로 미래 시점의 데이터를 예측하는 기술을 제공하며, SARIMA는 이러한 시계열 분석에서 활용되는 통계 모델의 일종이다. 본 연구는 직접 수집한 실시간 위치 데이터에 SARIMA를 적용하여 개인의 이동 패턴을 추출하고 이를 예측에 활용하는 전반적인 프로세스를 제작하였다. 첫째, DB에 업로드된 위치 데이터를 비지도 학습의 일종인 EM-clustering을 활용해 핵심 방문 장소들로부터의 거리에 따라 군집화했다. 둘째, 해당 장소에 입장하고 퇴장하는 시간 간격에 SARIMA를 적용해 주기성을 추출했다. 마지막으로, 이 주기성들을 군집의 중요도에 따라 순차적으로 분석하여 유의미한 예측 결과를 도출해냈다.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.12
• /
• pp.191-199
• /
• 2023

In this paper, we propose a method to extract the features of five sensor-only facilities built as infrastructure for autonomous cooperative driving, which are from point cloud data acquired by LiDAR. In the case of image acquisition sensors installed in autonomous vehicles, the acquisition data is inconsistent due to the climatic environment and camera characteristics, so LiDAR sensor was applied to replace them. In addition, high-intensity reflectors were designed and attached to each facility to make it easier to distinguish it from other existing facilities with LiDAR. From the five sensor-only facilities developed and the point cloud data acquired by the data acquisition system, feature points were extracted based on the average reflective intensity of the high-intensity reflective paper attached to the facility, clustered by the DBSCAN method, and changed to two-dimensional coordinates by a projection method. The features of the facility at each distance consist of three-dimensional point coordinates, two-dimensional projected coordinates, and reflection intensity, and will be used as training data for a model for facility recognition to be developed in the future.