• 한국지리정보학회지
• /
• 제26권4호
• /
• pp.237-250
• /
• 2023

본 연구에서는 UAV기반 항공사진측량에 의해 정사사진 및 DEM을 생성하고 이를 침수흔적도 제작을 위한 정밀조사에 적용하고자 하였다. 2012년 9월 제6호 태풍 산바(Sanba)의 영향으로 제방붕괴 및 내수침수 피해가 발생한 구미시 고아읍 농경지를 연구대상지역으로 선정하였다. UAV사진측량 성과의 최적 정확도를 얻기 위해 연구지역에 19점의 GCP 최적 배치상태에서 Pix4Dmapper 소프트웨어를 이용한 영상처리를 통하여 점군 데이터, DEM 및 정사영상을 생성하였다. loudCompare의 CSF Filtering를 적용하여 지면요소와 비지면요소로 point cloud를 분리한 후 GRASS GIS 소프트웨어에서 비지면요소만을 사용하여 최종적으로 보정된 DEM을 생성하였다. 최종 생성된 DEM으로부터 추출한 침수위 및 침수심 데이터와 한국국토정보공사(LX)의 공공데이터 포털사이트를 통하여 제공된 2012년 당시 같은 지역에 대한 기존 자료의 침수위 및 침수심 데이터를 비교하여 제시하였다.

• 환경영향평가
• /
• 제20권3호
• /
• pp.349-356
• /
• 2011

This research is aim to analyze of changing landscape and according to phenological cycle from image information of coastal environment obtained by multi-media were analyzed by camera and satellite image. The digital camera and satellite image were used for tidal flat vegetation monitoring during the construction of Sihwa lake. The vegetation type and phenological cycle of Sihwa tidal flat have been changed with the Sihwa lake ecosystem. The environment changes of Sihwa tidal flat area and ecological change were analyzed by field work digital camera images and satellite images. The airborne, UAV and satellite images were classified with the changed elements of coastal ecological environment and tidal flat vegetation monitoring carried out the changed area and shape of vegetation distribution with time series images.

• 한국방재학회:학술대회논문집
• /
• 한국방재학회 2007년도 정기총회 및 학술발표대회
• /
• pp.418-421
• /
• 2007

Application이나 3D 모델로 구현된 맵 관련 위성영상, UAV 영상을 통해 현장감 있는 정보를 정확하게 얻는 것은 중요하다. 방재관련 업계에서는 3D 모델링에 근거한 재해지역 주변의 정확한 3차원 지형공간정보 취득의 필요성을 인식하고 있다. 본 논문에서는 GIS 기술을 활용하여 3D 모형을 생성하고, 각종 영상들을 로딩하고 처리하는 부분에 있어서의 방법을 제시하였다. 그리고 대상지역의 수치고도모형과 지형지물을 위해 수치 지형도를 사용하였다. 결과는 3D 모델링 기반의 간단한 application의 구현이다. 제시한 방법은 방재 관련업계의 종사자들에게 더 나은 방법을 제시하기에 활용 가능하다.

• 한국농공학회논문집
• /
• 제59권6호
• /
• pp.39-50
• /
• 2017

Growth monitoring of highland Kimchi cabbage is very important to respond the fluctuations in supply and demand from middle of August to early September in Korea. For evaluating Kimchi cabbage growth, it needs to classify the transplanting period of Kimchi cabbage, preferentially. This study was conducted to estimate the transplanting period of highland Kimchi cabbage from 2015 to 2016 in the main production area of highland Kimchi cabbage, Anbandegi, Maebongsan, and Gwinemi. Correlation between NDVI (Normalized Difference Vegetation Index) from UAV images and days after transplanting of Kimchi cabbage was high in early transplanting period. But because the growth curve of Kimchi cabbage showed S-type, joint use of multi-temporal linear regression equation for estimation of transplanting period was more suitable. Using application of these equations at Anbandegi, Maebongsan, and Gwinemi, we made the map of transplanting periods of highland Kimchi cabbage. Generally, highland Kimchi cabbage is harvested in sixty days later since transplanting. As a result, we could estimate the harvest time and area of highland Kimchi cabbage.

• 국제초고층학회논문집
• /
• 제9권4호
• /
• pp.351-360
• /
• 2020

Monitoring civil structures periodically is necessary for ensuring the fitness of the structures. Cracks on inner and outer surfaces of the building plays a vital role in indicating the health of the building. Conventionally, human visual inspection techniques were carried up to human reachable altitudes. Monitoring of high rise infrastructures cannot be done using this primitive method. Also, there is a necessity for more accurate prediction of cracks on building surfaces for ensuring the health and safety of the building. The proposed research focused on developing an efficient crack classification model using Transfer Learning enabled EfficientNet (TL-EN) architecture. Though many other pre-trained models were available for crack classification, they rely on more number of training parameters for better accuracy. The TL-EN model attained an accuracy of 0.99 with less number of parameters on large dataset. A bench marked METU dataset with 40000 images were used to test and validate the proposed model. The surfaces of high rise buildings were investigated using vision enabled Unmanned Arial Vehicles (UAV). These UAV is fabricated with TL-EN model schema for capturing and analyzing the real time streaming video of building surfaces.

• Smart Structures and Systems
• /
• 제33권2호
• /
• pp.105-118
• /
• 2024

In order to realize tiny bridge crack discovery by UAV-based machine vision, a novel method combining deep learning and tensor voting is proposed. Firstly, the grid images of crack are detected and descripted based on SE-ResNet50 to generate feature points. Then, the probability significance map of crack image is calculated by tensor voting with feature points, which can define the direction and region of crack. Further, the crack detection anchor box is formed by non-maximum suppression from the probability significance map, which can improve the robustness of tiny crack detection. Finally, a case study is carried out to demonstrate the effectiveness of the proposed method in the Xiangjiang-River bridge inspection. Compared with the original tensor voting algorithm, the proposed method has higher accuracy in the situation of only 1-2 pixels width crack and the existence of edge blur, crack discontinuity, which is suitable for UAV-based bridge crack discovery.

• Journal of Biosystems Engineering
• /
• 제43권2호
• /
• pp.138-147
• /
• 2018

Purpose: A narrowband hyperspectral imaging sensor of high-dimensional spectral bands is advantageous for identifying the reflectance by selecting the significant spectral bands for predicting crop yield over the broadband multispectral imaging sensor for each wavelength range of the crop canopy. The images acquired by each imaging sensor were used to develop the models for predicting the Chinese cabbage yield. Methods: The models for predicting the Chinese cabbage (Brassica campestris L.) yield, with multispectral images based on unmanned aerial vehicle (UAV), were developed by simple linear regression (SLR) using vegetation indices, and forward stepwise multiple linear regression (MLR) using four spectral bands. The model with hyperspectral images based on the ground were developed using forward stepwise MLR from the significant spectral bands selected by dimension reduction methods based on a partial least squares regression (PLSR) model of high precision and accuracy. Results: The SLR model by the multispectral image cannot predict the yield well because of its low sensitivity in high fresh weight. Despite improved sensitivity in high fresh weight of the MLR model, its precision and accuracy was unsuitable for predicting the yield as its $R^2$ is 0.697, root-mean-square error (RMSE) is 1170 g/plant, relative error (RE) is 67.1%. When selecting the significant spectral bands for predicting the yield using hyperspectral images, the MLR model using four spectral bands show high precision and accuracy, with 0.891 for $R^2$, 616 g/plant for the RMSE, and 35.3% for the RE. Conclusions: Little difference was observed in the precision and accuracy of the PLSR model of 0.896 for $R^2$, 576.7 g/plant for the RMSE, and 33.1% for the RE, compared with the MLR model. If the multispectral imaging sensor composed of the significant spectral bands is produced, the crop yield of a wide area can be predicted using a UAV.

• International Journal of Aeronautical and Space Sciences
• /
• 제8권2호
• /
• pp.54-66
• /
• 2007

Traffic and emergency monitoring systems are essential constituents of Intelligent Transportation System (ITS) technologies, but the lack of traffic monitoring has become a primary weakness in providing prompt emergency services. Demonstrated in numerous military applications, unmanned aerial vehicles (UAVs) have great potentials as a part of ITS infrastructure for providing quick and real-time aerial video images of large surface area to the ground. Despite of obvious advantages of UAVs for traffic monitoring and many other civil applications, it is rare to encounter success stories of UAVs in civil application including transportation. The objective of this paper is to report the outcomes of research supported by the state agency in US to investigate the feasibility of integrating UAVs into urban highway traffic monitoring as a part of ITS infrastructure. These include current technical and regulatory issues, and possible suggestions for a future UAV system in civil applications.

• Journal of Forest and Environmental Science
• /
• 제34권2호
• /
• pp.142-144
• /
• 2018

This paper discusses the development of semi-automatic search program for crown delineation in stand level. The crown of an individual tree was delineated by applying the Watershed (WS) and Valley Following (VF) algorithms. Unmanned Aerial Vehicle (UAV) images were used in the semi-automatic search program to delineate the crown area. The overall accuracy and Khat were used in accuracy assessment. WS algorithm's model showed the overall accuracy and Khat index of 0.80 and 0.59, respectively, in Plot 1. However, the overall accuracy and Khat of VF algorithm's model were 0.78 and 0.51, respectively, in Plot 2.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2010년 춘계학술발표회 논문집
• /
• pp.249-250
• /
• 2010

The study aims to propose a method that shall rapidly acquire 3D spatial information of the frequently changing city areas by using the low altitude aerial images taken by the UAV. The artificial 3D model of the artificial structures was constructed using the aerial image data photographed at the test area, calibration data of the non-metric camera and the results of the ground control point survey. Also, the digital surface model was created for areas that were changed due to a number of civil works. Through the above studies, the possibilities of constructing a 3D virtual city model, renewal of 3D GIS database, abstraction of changed information in geographic features and on-demand updating of the digital map were suggested.