• 대한원격탐사학회지
• /
• 제39권6_3호
• /
• pp.1771-1777
• /
• 2023

최근 딥러닝의 발전으로 의미론적 분할을 통한 토지피복 분류 방법들이 제안되고 있다. 그러나 기존의 딥러닝 기반 모델들은 영상 정보만을 이용하기 때문에 시공간적 일관성을 담보할 수 없는 한계점이 있다. 이에 본 연구에서는 좌표 정보를 활용한 토지피복 분류 모델을 제안한다. 먼저 암시적 신경 표현 기법인 다중해상도 해시 인코더를 위경도 좌표계로 확장한 좌표 해시 인코더를 통해 좌표의 특징을 추출하였다. 다음으로 추출된 좌표 특징을 다양한 단계의 U-net 디코더와 결합하는 아키텍처를 제안하였다. 실험 결과, 제안 방법이 약 32% 향상된 분류 정확도를 보였고, 시공간적 일관성이 향상됨을 확인하였다.

• 대한원격탐사학회지
• /
• 제22권1호
• /
• pp.75-85
• /
• 2006

This paper has dealt with a data fusion for the problem of land-cover classification using multisensor imagery. Dempster-Shafer evidence theory has been employed to combine the information extracted from the multiple data of same site. The Dempster-Shafer's approach has two important advantages for remote sensing application: one is that it enables to consider a compound class which consists of several land-cover types and the other is that the incompleteness of each sensor data due to cloud-cover can be modeled for the fusion process. The image classification based on the Dempster-Shafer theory usually assumes that each sensor is represented by a single channel. The evidential approach to image classification, which utilizes a mass function obtained under the assumption of class-independent beta distribution, has been discussed for the multiple sets of mutichannel data acquired from different sensors. The proposed method has applied to the KOMPSAT-1 EOC panchromatic imagery and LANDSAT ETM+ data, which were acquired over Yongin/Nuengpyung area of Korean peninsula. The experiment has shown that it is greatly effective on the applications in which it is hard to find homogeneous regions represented by a single land-cover type in training process.

• Spatial Information Research
• /
• 제20권5호
• /
• pp.25-35
• /
• 2012

본 연구에서는 공간정보 자료원에 따른 수질특성의 영향을 비교하였다. 먼저, 비점오염부하량 평가에 영향을 미치는 토지피복별 기대평균농도(EMC)를 효과적으로 계산하기 위해, 영상분류를 통해 대청댐유역의 토지피복도를 구축하였으며, 이를 환경부 대분류 자료와 비교한 결과 88.76%의 높은 정확도를 확보하였다. 또한 토양도와 영상분류에 의한 토지피복도를 공간 중첩하여 유출곡선지수와 직접유출을 계산하였으며, 분석 결과 석천과 대청댐 유역이 가장 높게 나타났다. 그리고 직접유출과 기대평균농도를 조합하여 계산한 BOD에 대한 비점오염부하량은 삼가천합류점과 소옥천하류 유역이 높게 나타났으며, TN과 TP에 대한 비점오염부하량에서는 삼가천합류점과 봉황천하류 유역이 높게 나타났다. 영상분류에 의한 비점오염부하량의 효용성 평가를 위해 환경부 토지피복도에 의한 비점오염부하량과 상호 비교한 결과, 대청댐상류 유역에서 BOD, TN, TP에 대한 오염부하량의 오차가 각각 10.64%, 11.70%, 20.00%로 가장 크게 나타났다. 따라서 유역내 수질특성을 효과적으로 모의하기 위해서는 논과 밭이 포함된 공간정보를 활용하는 것이 비점오염부하량 평가에 바람직하다고 본다.

• 지적과 국토정보
• /
• 제48권2호
• /
• pp.171-183
• /
• 2018

급속한 위성영상 공급확대에도 불구하고 자동화되지 못한 영상처리과정으로 인해 영상활용이 제약받는 경우가 많다. 본 연구에서는 감독영상분류를 위한 훈련지역 선택과정을 자동화함으로써 영상처리과정의 비용과 시간을 절감하는 방안을 제시하였다. 이를 위해 기존의 토지피복 정보를 활용하여 훈련관심영역을 추출하는 방법을 최신영상에 적용하여 토지피복분류를 실행한 후 분류정확도를 평가하였다. 원주시 도심지역을 대상지로 하여 토지유형을 시가지역과 농지/초지, 숲, 나대지 및 수계로 나누고 유형별 훈련관심영역을 환경부 중분류 토지피복지도를 활용하여 선택하였다. 관심영역 선택을 위해 먼저 토지피복지도 폴리곤 경계를 기준으로 negative buffer (-15m)를 적용하여 새로 폴리곤을 만들었고 너무 작은 폴리곤(<$2,000m^3$)과 큰 폴리곤(>$200,000m^3$)을 제외하였다. 선택된 폴리곤들의 밴드별 반사율 표준편차와 평균값 및 NDVI의 평균값을 계산하였다. 이 정보를 이용하여 먼저 표준편차가 적은 폴리곤 (폴리곤 내 반사율 값의 편차가 크지 않은 폴리곤)을 선택한 후 이들 중 반사율 평균값이 각 유형의 특징적인 분광특성을 반영할 수 있는 폴리곤을 관심영역으로 선택하였다. 2017년 Sentinel-2영상을 활용하여 토지피복유형을 분류한 결과 86.9%의 분류정확도($\hat{K}=0.81$)가 도출되었다. 본 연구에서 시도된 자동 관심영역 선택방법 적용한 결과 수동 디지타이징 과정을 생략하고도 높은 분류정확도를 도출 할 수 있었으며 이와 같은 방법을 통해 영상처리에 필요한 시간과 비용을 절약하여 급속히 증가하고 있는 영상을 효율적으로 활용할 수 있게 될 것으로 기대된다.

• 한국측량학회지
• /
• 제29권4호
• /
• pp.429-438
• /
• 2011

LiDAR technology is a combination of laser ranging, satellite positioning technology and digital image technology for study and determination with high accuracy of the true earth surface features in 3 D. Laser scanning data is typically a points cloud on the ground, including coordinates, altitude and intensity of laser from the object on the ground to the sensor (Wehr & Lohr, 1999). Data from laser scanning can produce products such as digital elevation model (DEM), digital surface model (DSM) and the intensity data. In Vietnam, the LiDAR technology has been applied since 2005. However, the application of LiDAR in Vietnam is mostly for topological mapping and DEM establishment using point cloud 3D coordinate. In this study, another application of LiDAR data are present. The study use the intensity image combine with some other data sets (elevation data, Panchromatic image, RGB image) in Bacgiang City to perform land cover classification using neural network method. The results show that it is possible to obtain land cover classes from LiDAR data. However, the highest accurate classification can be obtained using LiDAR data with other data set and the neural network classification is more appropriate approach to conventional method such as maximum likelyhood classification.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2015년도 학술발표회
• /
• pp.242-242
• /
• 2015

Monitoring the land cover changes in Nakdong River Basins using the multi-temporal remote sensing datasets is necessary for preserving properties in the river basins and monitoring the environmental changes in the river basins after the 4 major river restoration project. This research aims to monitor the land cover changes using the multi-temporal Landsat imageries and the airborne topographic LiDAR data. Firstly, the river basin boundaries are determined by using the LiDAR data, and the multiple river basin imageries are generated from the multi-temporal Landsat imageries by using the river basin boundaries. Next the classification method is employed to identify the multiple land covers in the generated river basin imageries. Finally, monitoring the land cover changes is implemented by comparing the differences of the same clusters in the multi-temporal river basin imageries.

• 농업과학연구
• /
• 제47권4호
• /
• pp.933-940
• /
• 2020

Land-use change matrix data is important for calculating the LULUCF (land use, land use change and forestry) sector of the national greenhouse gas inventory. In this study, land cover changes in 2004 and 2019 were compared using the Wall-to-Wall technique with a land cover map of Sejong City from the Ministry of Environment. Sejong City was classified into six land use classes according to the Intergovernmental Panel on Climate Change (IPCC) guidelines: Forest land, crop land, grassland, wetland, settlement and other land. The coordinate system of the land cover maps of 2004 and 2019 were harmonized and the land use was reclassified. The results indicate that during the 15 years from 2004 to 2019 forestlands and croplands decreased from 50.4% (234.2 ㎢) and 34.6% (161.0 ㎢) to 43.4% (201.7 ㎢) and 20.7% (96.2 ㎢), respectively, while Settlement and Other land area increased significantly from 8.9% (41.1 ㎢) and 1.4% (6.9 ㎢) to 35.6% (119.0 ㎢) and 6.5% (30.3 ㎢). 79.㎢ of cropland area (96.2 ㎢) in 2019 was maintained as cropland, and 8.8 ㎢, 1.7 ㎢, 0.5 ㎢, 5.4 ㎢, and 0.4 ㎢ were converted from forestland, grassland, wetland, and settlement, respectively. This research, however, is subject to several limitations. The uncertainty of the land use change matrix when using the wall-to-wall technique depends on the accuracy of the utilized land cover map. Also, the land cover maps have different resolutions and different classification criteria for each production period. Despite these limitations, creating a land use change matrix using the Wall-to-Wall technique with a Land cover map has great advantages of saving time and money.

• 대한원격탐사학회지
• /
• 제38권5_1호
• /
• pp.461-469
• /
• 2022

이 연구에서는 시계열 토지피복도를 제작하기 위해 분석자 개입 없이 준감독학습 기반 분류를 이용하는 새로운 훈련자료 추출 기법을 제안하였다. 준감독학습 기반 훈련자료 추출 기법은 먼저 분류 대상 영상과 유사한 토지피복 특성을 포함하는 과거 영상으로부터 획득한 초기 훈련자료를 이용하여 초기 분류를 수행한다. 이후, 분류의 불확실성 정보와 인접 화소의 분류 항목을 제약 조건으로 이용하는 준감독학습 기반 반복 분류를 이용하여 초기 분류 결과로부터 신뢰할 수 있는 훈련자료를 추출한다. 준감독학습 기반 훈련자료 추출기법의 적용 가능성은 농경지에서 unmanned aerial vehicle 영상을 이용하는 분류 실험을 통해 평가되었다. 제안한 준감독학습 기반 훈련자료 추출 기법에 의해 자동으로 추출된 새로운 훈련자료를 이용하는 것은 초기 분류 결과에서 나타난 오분류를 두드러지게 완화할 수 있었다. 특히, 인접 화소의 공간 문맥 정보를 고려함으로써 고립된 화소가 크게 감소하였다. 결과적으로, 제안 기법의 분류 정확도는 수동으로 추출한 훈련자료를 이용하는 분류 정확도와 유사하였다. 이러한 결과는 이 연구에서 제시한 준감독학습 기반 반복 분류가 시계열 토지피복도를 제작하기 위해 신뢰할 수 있는 훈련자료를 자동으로 추출하는데 효과적으로 적용될 수 있음을 나타낸다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume II
• /
• pp.555-558
• /
• 2006

In recent years, urban development has expanded rapidly in Nawabshah City of Pakistan. A major effect associated with this population trend is transformation of the landscape from natural cover types to increasingly impervious urban land. The core objective of this study are to provide time-series information to define and measure the urban land cover changes of Nawabshah, Pakistan between the years 1992 and 2002, and to examine related urbanization impacts on air quality of the study area. Two multi-temporal Landsat images acquired in 1992 and 2002 together with standard topographical maps to measure land cover changes were used in this study. The image processing and data manipulation were conducted using algorithms supplied with the ERDAS Imagine software. An unsupervised classification approach, which uses a minimum spectral distance to assign pixels to clusters, was used with the overall accuracy ranging from 84 percent to 92 percent. Land cover statistics demonstrate that during the study period (1992-2002) extensive transformation of barren and vegetated lands into urban land have taken place in Nawabshah City. Results revealed that land cover changes due to urbanization has not only contaminated the air quality of the study area but also raised the health concerns for the local residents.

• 한국환경복원기술학회지
• /
• 제10권2호
• /
• pp.97-104
• /
• 2007

A/R CDM(Afforestation/Reforestation Clean Development Mechanism) in Kyoto Mechanism means, either afforestation in the area used for other purposes more than 50 years or reforestation in the area used for other purposes on December 31st in 1989. South Korea has few sites due to the successful forestation in the past, but North Korea has not reforested the deforested lands since the mid-1970's. So these areas need to apply A/R CDM Project for restoration. The purposes of this study are to make a time series analysis in deforested areas and to estimate a feasibility of A/R CDM. To find the site satisfying A/R CDM business definition, land cover classification was applied using satellite images of the mid-1970's with good forestation, late 1980's including A/R CDM base year, and recent 2000's, and the chronological change was analyzed to categorize the possible sites. The North Korean topographical map of 1977 was used to verify land cover classification degree of 1970's, the land cover classification results made by the Ministry of Environment in 2000 were compared to verify the accuracy of 1980's results, and the land cover classification results in 2000's were verified by 2 site visits. The results of this study can be summarized as follows. The eligible A/R CDM sites are 605,156ha on the basis of the forestation change analysis in North Korea. Since the mid-1970's, 30.8% of the decreased forestation area of 1,966,306ha was classified into A/R CDM eligible sites. While other countries have the limited eligible sites, which has not been used for forestation since 1989 or which is being scattered, North Korea has large scale sites. Deforested sites are mainly around road and residential area, consequently give better accessibility for forestation than other countries. In conclusion, it is found that North Korea can provide efficient site for applying A/R COM Project to forestation restoring deforested land because of easy accessibility and existence of many possible sites due to artificial deforestation. Also, it is meaningful that the study suggests the application possibility of A/R COM Project to restore deforested land in North Korea and the related basic information through the chronological classification of the mid-1970's with good forestation, the late-1980's including A/R COM base year, and recent 2000's. It is expected that the study contributes to revitalization of A/R CDM Project and related research on North Korea forestation.