• 한국재난정보학회:학술대회논문집
• /
• 한국재난정보학회 2017년 정기학술대회
• /
• pp.282-285
• /
• 2017

본 논문에서는 무인비행기를 활용하여 재철소에서 사용하고 있는 대량의 원재료인 고철의 체적을 산정하고 수량을 파악하여 기존의 재고량산정 방법의 문제를 개선하고 보다 효율적이며 객관적인 고철량을 파악하는 방법을 찾는데 목적이 있다. 고철량 산정에 있어 무게를 산정하기 위해서는 체적을 산정하여 비중값을 적용하여 산정한다. 본 연구에서는 무인비행기(UAV)를 이용하여 체적을 산정하고 정확성 검증을 위해 정형의 컨테이너 박스와 크기가 작은 휴지통을 촬영 분석하여 비교 검증한 후 고철의 체적 측정 시험을 시행하였다. 무인비행기는 고정익 드론을 사용하였으며 격자비행방식을 적용하여 촬영하였으며, 촬영 전 지상기준점을 구하고자하는 물제의 주변에 배치하고 측량하여 적용하였다. 분석결과 체적산정을 위한 검증시험에서는 측량한 치수 및 체적 값과 무인비행기분석 값이 유사하게 나타났다. 또한 제철소에서 검증한 고철의 무게와 체적을 기준으로 무인비행기를 이용한 체적 값을 비교한 결과 기존 방식에 비해 객관적이고 효율적인 값을 얻을 수 있는 것으로 판단된다.

• 전기학회논문지P
• /
• 제67권4호
• /
• pp.227-232
• /
• 2018

In this paper, we propose a faster object detection and tracking method using Deep Learning, UAV(unmanned aerial vehicle), Kalman filter and YOLO(You Only Look Once)v3 algorithms. The performance of the object tracking system is decided by the performance and the accuracy of object detecting and tracking algorithms. So we applied to the YOLOv3 algorithm which is the best detection algorithm now at our proposed detecting system and also used the Kalman Filter algorithm that uses a variable detection area as the tracking system. In the experiment result, we could find the proposed system is an excellent result more than a fixed area detection system.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2021년도 하계학술대회
• /
• pp.348-351
• /
• 2021

최근 자동화의 필요성이 증가함에 따라 얼굴 표정 인식 분야(face expression recognition)가 인공지능과 이미지 처리 분야에서 활발히 연구되고 있다. 본 논문에서는 기존 인공신경망에서 요구되었던 고성능 GPU 환경과 높은 연산량을 극복하고자 모델 경량화(Light weighted Model) 기법을 적용하여 드론 및 모바일 기기에서 적용될 수 있는 얼굴 표정 인식 신경망을 제안한다. 제안하는 방법은 미세한 얼굴의 표정 인식을 위한 방법으로, 입력 이미지의 receptive field 를 늘려 특징 맵의 표현력을 높이는 방법을 제안한다. 또한 효과적인 신경망의 경량화를 위하여, 파라미터의 연산량을 줄일 때 발생하는 문제점을 극복하기 위한 방법을 제시한다. 따라서 제안하는 네트워크를 적용하면 많은 연산량과 느린 연산속도로 인해 제한되었던 네트워크 환경을 극복할 수 있을 뿐만 아니라, UAV(Unmanned Aerial Vehicle, 무인항공기) 및 모바일 기기에서 신경망을 이용한 실시간 얼굴 표정 인식을 할 수 있다.

• 한국BIM학회 논문집
• /
• 제13권4호
• /
• pp.64-73
• /
• 2023

This study introduces a method of estimating the 3D coordinates of structural damage from the detection results of visual inspection provided in 2D image coordinates using sensing data of UAV and 3D shape information of BIM. This estimation process takes place in a virtual space and utilizes the BIM model, so it is possible to immediately identify which member of the structure the estimated location corresponds to. Difference from conventional structural damage localization methods that require 3D scanning or additional sensor attachment, it is a method that can be applied locally and rapidly. Measurement accuracy was calculated through the distance difference between the measured position measured by TLS (Terrestrial Laser Scanner) and the estimated position calculated by the method proposed in this study, which can determine the applicability of this study and the direction of future research.

• Smart Structures and Systems
• /
• 제33권5호
• /
• pp.349-358
• /
• 2024

Structural digital models can be effectively established by spatially obtaining digital images using an unmanned aerial vehicle (UAV). One of the main purposes of the structural digital modeling is computer vision-based exterior damage detection of a target structure. To investigate micro-scale damage from the digital model, high-resolution digital images obtained with a close-up vision survey is typically required. However, serial image synthesis such as image stitching may cumulate stitching errors as the number of scanned images increases. Therefore, in this paper, a novel loop closure-based digital image stitching technique is proposed and experimentally validated using the close-up surveyed digital images acquired from an in-situ dam structure located in South Korea. The test results reveal that the proposed technique outperforms a non-loop closure-based image stitching technique, which can cause serious distortions, such as ghosting and vanishing phenomena.

• 제어로봇시스템학회논문지
• /
• 제20권12호
• /
• pp.1209-1216
• /
• 2014

This paper copes with control design for unmanned aerial vehicle transportation system. Moving pendulum dynamics of slung-load system is derived using two methods: Udwadia-Kalaba equation and Newtonian approach. PID controller is applied to Udwadia-Kalaba equation model for structural consistency and linear quadratic Gaussian / Loop Transfer Recovery (LQG/LTR) technique is employed for Newtonian model with minimal state-space realization. Characteristics of PID and LQG/LTR controller are compared, and two controllers are combined to compensate the drawbacks of each other. Numerical simulation is set for two cases and conducted to evaluate performance of designed controllers. The result proves that combination of LQG/LTR and PID control performs stable and robust.

• 한국군사과학기술학회지
• /
• 제18권3호
• /
• pp.226-233
• /
• 2015

Pose estimation is an important operation for many vision tasks. This paper presents a method of estimating the camera pose, using a known landmark for the purpose of autonomous vertical takeoff and landing(VTOL) unmanned aerial vehicle(UAV) landing. The proposed method uses a distinctive methodology to solve the pose estimation problem. We propose to combine extrinsic parameters from known and unknown 3-D(three-dimensional) feature points, and inertial estimation of camera 6-DOF(Degree Of Freedom) into one linear inhomogeneous equation. This allows us to use singular value decomposition(SVD) to neatly solve the given optimization problem. We present experimental results that demonstrate the ability of the proposed method to estimate camera 6DOF with the ease of implementation.

• 도시과학
• /
• 제8권1호
• /
• pp.7-14
• /
• 2019

Recently, interest in solar energy, which is the center of new government energy policy, is increasing. However, the focus is on mass production of solar power plants, and policies and related technologies for maintenance and management of existing installed PV modules are insufficient. In this study, we use UAV (Unmanned Aerial Vehicle) to acquire RGB and infrared images, apply it to the structure-from-motion (SfM) based image analysis tool, model the three- And the position of the hot spot was monitored and coordinates were detected. As a result, it is possible to provide basic spatial information for maintenance of solar module by monitoring and position detection of hot-spot suspected solar cells by superimposing infrared image and RGB image based on unmanned aerial vehicle.

• 한국환경복원기술학회지
• /
• 제24권6호
• /
• pp.89-96
• /
• 2021

In this study, a deep-learning image analysis model was established and validated for AI-based monitoring of the tidal flat ecosystem for marine protected creatures Ocypode stimpsoni and their habitat. The data in the study was constructed using an unmanned aerial vehicle, and the U-net model was applied for the deep learning model. The accuracy of deep learning model learning results was about 0.76 and about 0.8 each for the Ocypode stimpsoni and their burrow whose accuracy was higher. Analyzing the distribution of crabs and burrows by putting orthomosaic images of the entire study area to the learned deep learning model, it was confirmed that 1,943 Ocypode stimpsoni and 2,807 burrow were distributed in the study area. Through this study, the possibility of using the deep learning image analysis technology for monitoring the tidal ecosystem was confirmed. And it is expected that it can be used in the tidal ecosystem monitoring field by expanding the monitoring sites and target species in the future.

• 천문학회보
• /
• 제46권1호
• /
• pp.38.3-38.3
• /
• 2021

We are developing an optomechanical design of infrared telescope for the CubeSat and Unmanned Aerial Vehicle (UAV) which adapts the Linear Astigmatism Free- Three Mirror System in the confocal off-axis condition. The small entrance pupil (diameter of 40 mm) and the fast telescope (f-number of 1.9) can survey large areas. The telescope structure consists of three mirror modules and a sensor module, which are assembled on the base frame. The mirror structure has duplex layers to minimize a surface deformation and physical size of a mirror mount. All the optomechanical parts and three freeform mirrors are made from the same material, i.e., aluminum 6061-T6. The Coefficient of Thermal Expansion matching single material structure makes the imaging performance to be independent of the thermal expansion. We investigated structural characteristics against external loads through Finite Element Analysis. We confirmed the mirror surface distortion by the gravity and screw tightening, and the overall contraction/expansion following the external temperature environment change (from -30℃ to +30℃).