• 한국측량학회지
• /
• 제21권1호
• /
• pp.37-44
• /
• 2003

본 연구는 l/5,000 수치지도 Ver 2.0을 이용하여 1/25,000 수치지도를 제작하기 위한 일반화처리공정을 개발하였다. 공간 및 속성정보를 포함하고 있는 수치지도 Ver 2.0은 기존의 수치지도 보다 많은 정보량을 포함하고 있기때문에 1/25,000 지청지물코드에 포함되지 않는 Layer를 삭제하고, 자료처리를 8대 지형·지물별로 분류하여 각각에 대해 처리한 후, merge 하는 과정으로 이루어지도록 적합한 작업공정을 도출하였다. 따라서, 본 연구에서 개발한 일반화 작업공정을 이용하므로서 향후 최적 자동일반화시스템을 개발할 수 있을 것이고, 소축척 수치지도 및 주제도 제작에 기여할 수 있을 것이다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• pp.321-324
• /
• 2005

In these days, the management and visualization of 3D geo-spatial information is regarded as one of an important issue in GiS and remote sensing fields. 3D GIS is considered with the database issues such as handling and managing of 3D geometry/topology attributes, whereas 3D visualization is basically concerned with 3D computer graphics. This study focused on the design and implementation for the OpenGL API-based rendering system for the complex types of 3D geo-spatial features. In this approach 3D features can be separately processed with the functions of authoring and manipulation of terrain segments, building segments, road segments, and other geo-based things with texture mapping. Using this implementation, it is possible to the generation of an integrated scene with these complex types of 3D features. This integrated rendering system based on the feature-based 3D-GIS model can be extended and effectively applied to urban environment analysis, 3D virtual simulation and fly-by navigation in urban planning. Furthermore, we expect that 3D-GIS visualization application based on OpenGL API can be easily extended into a real-time mobile 3D-GIS system, soon after the release of OpenGLIES which stands for OpenGL for embedded system, though this topic is beyond the scope of this implementation.

• 로봇학회논문지
• /
• 제7권2호
• /
• pp.120-128
• /
• 2012

The loop closure problem is one of the most challenging issues in the vision-based simultaneous localization and mapping community. It requires the robot to recognize a previously visited place from current camera measurements. While the loop closure often relies on visual bag-of-words based on point features in the previous works, however, in this paper we propose a line-based method to solve the loop closure in the corridor environments. We used both the floor line and the anchored vanishing point as the loop closing feature, and a two-step loop closure algorithm was devised to detect a known place and perform the global pose correction. We propose an anchored vanishing point as a novel loop closure feature, as it includes position information and represents the vanishing points in bi-direction. In our system, the accumulated heading error is reduced using an observation of a previously registered anchored vanishing points firstly, and the observation of known floor lines allows for further pose correction. Experimental results show that our method is very efficient in a structured indoor environment as a suitable loop closure solution.

• 한국통신학회논문지
• /
• 제18권1호
• /
• pp.32-38
• /
• 1993

본 논문에서는 문자 인식을 위한 효율적인 대분류 방법을 제안하였다. 기존의 대분류 방법은 입력된 문자를 인식 대상문자마다 미리 작성된 표준 특징벡터와 유사와 계산에 의해 인식 후보문자들을 선정하는 것이었으나, 제안한 대분류 방식은 유사한 문자들을 같은 그룹으로 모아서 그 그룹에 속한 문자들의 평균 값을 대표값으로 사용하는 것이다. 문자의 영역을 몇개의 소영역으로 분할하고, 각 소영역에 해당되는 부분벡터로 ISODATA 알고리즘을 이용하여 적당한 수의 그룹을 형성한다. 입력분자의 부분정보에 해당되는 소영역의 부분특징벡터와 대응되는 그룹들과의 거리를 계산한 후, 부분과의 거리 값을 최종적으로 다시 모아서 전체 거리 정보로 이용한다. 이러한 대분류 방법은 일반적인 방법에 비해 처리속도 면에서의 향상과 분류면에서의 확실성을 갖게 되었다.

• 한국정밀공학회지
• /
• 제30권2호
• /
• pp.177-184
• /
• 2013

This paper proposes an enhanced Simultaneous Localization and Mapping (SLAM) algorithm based on matching laser image and Extended Kalman Filter (EKF). In general, laser information is one of the most efficient data for localization of mobile robots and is more accurate than encoder data. For localization of a mobile robot, moving distance information of a robot is often obtained by encoders and distance information from the robot to landmarks is estimated by various sensors. Though encoder has high resolution, it is difficult to estimate current position of a robot precisely because of encoder error caused by slip and backlash of wheels. In this paper, the position and angle of the robot are estimated by comparing laser images obtained from laser scanner with high accuracy. In addition, Speeded Up Robust Features (SURF) is used for extracting feature points at previous laser image and current laser image by comparing feature points. As a result, the moving distance and heading angle are obtained based on information of available points. The experimental results using the proposed laser slam algorithm show effectiveness for the SLAM of robot.

• 한국CDE학회논문집
• /
• 제7권4호
• /
• pp.240-247
• /
• 2002

Most commercial CAD systems provide parametric modeling functions, and by using these capabilities designers can edit a CAD model in order to create design variants. It is necessary to transfer parametric information during a CAD model exchange to modify the model inside the receiving system. However, it is not possible to exchange parametric information of CAD models based on the cur-rent version of STEP. The designer intents which are contained in the parametric information can be lost during the STEP transfer of CAD models. This paper introduces a hybrid CAB model translator, which also uses the feature tree of commercial CAD systems in addition to the macro file to allow transfer of parametric information. The macro-parametric approach is to exchange CAD models by using the macro file, which contains the history of user commands. To exchange CAD models using the macro-parametric approach, the modeling commands of several commercial CAD systems are analyzed. Those commands are classified and a set of standard modeling commands has been defined. As a neutral fie format, a set of standard modeling commands has been defined. Mapping relations between the standard modeling commands set and the native modeling commands set of commercial CAD systems are defined. The scope of the current version is limited to parts modeling and assemblies are excluded.

• 대한원격탐사학회지
• /
• 제8권2호
• /
• pp.105-123
• /
• 1992

A study was made on the feature extraction for non-metallic one deposits and their related geology using the Remote Sensing and Airborne Radiometric data. The area chosen is around the Haenam area, where dickite and Quarzite mines are distributed in. The geology of the area consists mainly of Cretaceous volcanics and PreCambrian metamorphic. The methods applied are study on the reflectance characteristics of minerals and rocks sampled in the study area, and the feature extraction extraction of histogram normalized images for Landsat TM and Airborne Radiometric data, and finally evaluation of applicability of some useful pattern recognition techniques for regional lithological mapping. As a result, reflectances of non-metallic minerals are much higher than rock samples in the area. However, low grade dickites are slightly higher than rock samples, probably due to their greyish colour and also their textural features which may scatter the reflectance and may be capable of capturing much hychoryl ions. The reflectances of rock samples may depend on the degree of whiteness of samples. The outcrops or mine dumps in the study area were most effectively extracted on the histogram normalized image of TM Band 1, 2 and 3, due to their high reflectivity. The Masking technique using the above bands may be the most effective and the natural colour composite may provide some success as well. The colour composite image of PCA may also be effective in extracting geological features, and airborne radiometric data may be useful to some degree as an complementary tool.

• 한국기계가공학회지
• /
• 제18권8호
• /
• pp.98-103
• /
• 2019

A more accurate method of feature point extraction and matching for three-dimensional reconstruction using low-resolution images of crops is proposed herein. This method is important in basic computer vision. In addition to three-dimensional reconstruction from exact matching, map-making and camera location information such as simultaneous localization and mapping can be calculated. The results of this study suggest applicable methods for low-resolution images that produce accurate results. This is expected to contribute to a system that measures crop growth condition.

• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제8권7호
• /
• pp.159-166
• /
• 2019

상용화된 많은 SSD와 달리 DRAM-less SSD는 원가절감, 전력소모량 감소 등의 이유로 DRAM을 가지고 있지 않다. 따라서 DRAM의 부재로 인해 입출력 성능이 저하될 가능성이 존재하며, 이는 호스트의 메모리 일부를 SSD 컨트롤러가 사용할 수 있는 NVMe 인터페이스의 HMB 기능을 통해 개선할 여지가 있다. 본 논문에서는 현재 상용화된 여러 DRAM-less SSD가 DRAM을 가지고 있는 동급 SSD에 비해 실제로 입출력 성능이 떨어지지만 HMB 기능을 사용해 일부 개선하고 있으며, 이는 SSD 컨트롤러가 호스트의 메모리를 매핑테이블 캐시로 주로 사용하고 있기 때문이라는 점을 다양한 실험을 통해 증명한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권1호
• /
• pp.147-165
• /
• 2021

In this work, we empirically evaluated the efficiency of the recent EfficientNetB0 model to identify and diagnose malaria parasite infections in blood smears. The dataset used was collected and classified by relevant experts from the Lister Hill National Centre for Biomedical Communications (LHNCBC). We prepared our samples with minimal image transformations as opposed to others, as we focused more on the feature extraction capability of the EfficientNetB0 baseline model. We applied transfer learning to increase the initial feature sets and reduced the training time to train our model. We then fine-tuned it to work with our proposed layers and re-trained the entire model to learn from our prepared dataset. The highest overall accuracy attained from our evaluated results was 94.70% from fifty epochs and followed by 94.68% within just ten. Additional visualization and analysis using the Gradient-weighted Class Activation Mapping (Grad-CAM) algorithm visualized how effectively our fine-tuned EfficientNetB0 detected infections better than other recent state-of-the-art DCNN models. This study, therefore, concludes that when fine-tuned, the recent EfficientNetB0 will generate highly accurate deep learning solutions for the identification of malaria parasites in blood smears without the need for stringent pre-processing, optimization, or data augmentation of images.