• 반도체디스플레이기술학회지
• /
• 제19권4호
• /
• pp.135-138
• /
• 2020

This paper suggests a method of automatic clustering to search of relevant digital photos using geo-coded information. The provided scheme labels photo images with their corresponding global positioning system coordinates and date/time at the moment of capture, and the labels are used as clustering metadata of the images when they are in the use of retrieval. Experimental results show that geo-location information can improve the accuracy of image retrieval, and the information embedded within the images are effective and precise on the image clustering.

• 한국농공학회논문집
• /
• 제64권1호
• /
• pp.15-26
• /
• 2022

3D open-field farm model developed from UAV (Unmanned Aerial Vehicle) data could make crop monitoring easier, also could be an important dataset for various fields like remote sensing or precision agriculture. It is essential to separate crops from the non-crop area because labeling in a manual way is extremely laborious and not appropriate for continuous monitoring. We, therefore, made a 3D open-field farm model based on UAV images and developed a crop segmentation model using a supervised machine learning algorithm. We compared performances from various models using different data features like color or geographic coordinates, and two supervised learning algorithms which are SVM (Support Vector Machine) and KNN (K-Nearest Neighbors). The best approach was trained with 2-dimensional data, ExGR (Excess of Green minus Excess of Red) and z coordinate value, using KNN algorithm, whose accuracy, precision, recall, F1 score was 97.85, 96.51, 88.54, 92.35% respectively. Also, we compared our model performance with similar previous work. Our approach showed slightly better accuracy, and it detected the actual crop better than the previous approach, while it also classified actual non-crop points (e.g. weeds) as crops.

• 한국측량학회지
• /
• 제38권1호
• /
• pp.11-21
• /
• 2020

본 연구는 위성기준점 안테나 보호를 위해 설치한 레이돔이 GNSS (Global Navigation Satellite System) 안테나 위상중심변동과 정밀 기선해석으로 추정한 동적 좌표에 미치는 영향을 분석하였다. 국내 위성기준점에 설치된 Trimble과 Leica 계열 안테나를 대상으로 레이돔 미설치(NONE)를 포함해 SCIS, SCIT, TZGD에 대한 IGS(International GNSS Services) 변동모형으로부터 위성 신호 입사 방향에 따른 위상중심 변동 보정량을 계산해 그 차이를 비교하였다. 그 결과 NONE을 기준으로 레이돔을 적용한 변동 보정량 차이는 수평 방향에서는 1mm 내외로 제한적이었지만 높이 방향은 수 밀리미터에서부터 최대 7mm까지 나타났다. 비교 대상 레이돔 중 SCIT가 높이 방향 위상중심 변동에 가장 큰 영향을 미쳤으며, 레이돔 미설치와 비교한 GPS (Global Positioning System) L1과 L2 신호의 보정량 차이 방향이 반대되는 특징을 보였다. 위성기준점 7개소 관측데이터의 기선해석에 각기 다른 레이돔 변동모형 적용으로 동적 좌표를 추정·비교한 결과 최근 위성기준점에 설치한 SCIS가 비교 대상 레이돔 중 가장 큰 영향인 평균 3.4mm 편의를 나타내었다. 반면, IGS 모형 비교에서 레이돔 미설치 대비 높이 방향에 가장 큰 보정량 차이를 나타낸 SCIT 모형은 타원체고 추정에 상대적으로 낮은 평균 1.4mm 편의 경향을 보였다.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제49권6호
• /
• pp.307-315
• /
• 2000

For the autonomy of a mobile robot it is first needed to know its position and orientation. Various methods of estimating the position of a robot have been developed. However, it is still difficult to localize the robot without any initial position or orientation. In this paper we present the method how to make the colored map and how to calculate the position and direction of a robot using the angle data of an omnidirectional image. The wall of the map is rendered with the corresponding color images and the color histograms of images and the coordinates of feature points are stored in the map. Then a mobile robot gets the color omnidirectional image at arbitrary position and orientation, segments it and recognizes objects by multiple color indexing. Using the information of recognized objects robot can have enough feature points and localize itself.

• 제어로봇시스템학회논문지
• /
• 제18권6호
• /
• pp.571-578
• /
• 2012

In the paper, we proposed a ring type structured light image based embedded ranging sensor for a mobile robot. Since the proposed ranging sensor obtains omnidirectional object distance, it is useful for autonomous navigation of a mobile robot. By matching the local omnidirectional distance map with a given global object map, it is possible to get position and heading angle of mobile robot in the global coordinates. Experiments for matching and navigation were carried out to verify the performance of the proposed ranging sensor.

• 제어로봇시스템학회논문지
• /
• 제15권2호
• /
• pp.132-138
• /
• 2009

In this paper, control of an omni-directional mobile robot is presented. Relying on encoder measurements to define the azimuth angle yields the dead-reckoned situation which the robot fails in localization. The azimuth angle error due to dead-reckoning is compensated and corrected by the magnetic compass sensor. Noise from the magnetic compass sensor has been filtered out. Kinematics and dynamics of the omni-directional mobile robot are derived based on the global coordinates and used for simulation studies. Experimental studies are also conducted to show the correction by the magnetic compass sensor.

• Journal of Astronomy and Space Sciences
• /
• 제35권4호
• /
• pp.287-293
• /
• 2018

This paper presents a satellite relative navigation strategy for formation flying, which chooses an appropriate navigation algorithm according to the operating environment. Not only global positioning system (GPS) measurements, but laser measurements can also be utilized to determine the relative positions of satellites. Laser data is used solely or together with GPS measurements. Numerical simulations were conducted to compare the relative navigation algorithm using only laser data and laser data combined with GPS data. If an accurate direction of laser pointing is estimated, the relative position of satellites can be determined using only laser measurements. If not, the combined algorithm has better performance, and is irrelevant to the precision of the relative angle data between two satellites in spherical coordinates. Within 10 km relative distance between satellites, relative navigation using double difference GPS data makes more precise relative position estimation results. If the simulation results are applied to the relative navigation strategy, the proper algorithm can be chosen, and the relative position of satellites can be estimated precisely in changing mission environments.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2022년도 제66차 하계학술대회논문집 30권2호
• /
• pp.229-230
• /
• 2022

본 논문에서는 CNN Object Detection과 더불어 3D 카메라 기반 디지털 좌표 인식 기술을 제안한다. 이 기술은 3D Depth Camera인 Intel 사의 Realsense D455를 이용해 대상을 감지하고 분류하며 대상의 위치를 파악한다. 또한 이 기술은 기존의 Depth Camera 내장 거리와는 다르게 좌표를 인식하여 좌표간의 거리까지 계산이 가능하다. 또한 Tensorflow SSD 구조와의 메모리 공유를 통해 시스템의 자원 낭비를 줄이며, 속도를 높이는 멀티쓰레드를 탑재했다. 본 기술을 통해 좌표간의 거리를 계산함으로써 스포츠, 심리, 놀이, 산업 등 다양한 환경에서 활용할 수 있다.

• 한국지구과학회지
• /
• 제39권1호
• /
• pp.46-52
• /
• 2018

이 논문은 자체 개발된 드론을 이용하여 사진측량기술을 적용하여 3차원 수치지표면모델(DSM)개발 연구를 수행하였다. 이 DSM을 개발하기 위하여 제주도 지역을 선정하여 24장의 사진을 개발된 드론으로 직접 촬영을 수행하였다. 촬영된 사진의 정확한 3차원 좌표를 부여하기 위하여, 10개의 지표기준점(GCP)점을 선정하여 상대측위 지구위치시스템(DGPS)측량을 실시하였다. 사진의 정확도를 평가하기 위하여 3개의 GCP점을 선정하여 사진상의 좌표와 지상점의 좌표의 정확도를 비교하였다. 사진좌표계과 지상좌표계의 정확도를 평가한 결과 수평오차는 8.8-14.7 cm로 나타났으며, 연직오차는 12.4 cm로 나타났다. 이 정확도는 국토지리정보원(NGII)이 인정하는 1/1,000 수치지도의 정확도를 가지는 측량결과이다. 이 연구를 통하여 본 연구에서 개발된 드론과 사진측량기법이 제주지역에서 우리가 원하는 DSM자료를 얻는데 유용한 기술임을 알 수 있었다.

• 디지털산업정보학회논문지
• /
• 제12권2호
• /
• pp.15-24
• /
• 2016

GPS(Global Positioning System) location tracking is a method for taking the precise coordinates after the coordinates are obtained by a GPS receiver, and displaying them on the map. In this paper with WAVE(Wireless Access for Vehicular Environment) simulation, we show that various services such as vehicle tracking service, real-time road conditions service and logistics can go tracking service, control and operation services according to the vehicle position and the traveling direction by using the GPS position data. A vehicle tracking system using GPS is automatically able to manage multiple RCP when exchanging data between RMA and the RCP, and it provides rapid requests and responses. To verify that multiple sessions between RMA and RM, as well as multiple sessions between RMA and RCP are able to be implemented, we take RMA as a RCP application on an OBU, until the RMA is receiving data response from corresponding RM. As a result of this experiment, we show that the response speeds of single session between RMA and RM using 1, 2, 3, and 4 kbyte unit data are similar, 62.32ms, 62.65ms, 63.02ms, and 63.48ms, respectively. Likewise, those of 128 muliple sessions using 1, 2, 3, and 4 kbyte unit data are not much more time difference, 298.08ms, 302.21ms, 322.85ms, and 329.62ms, respectively.