• 대한원격탐사학회지
• /
• 제39권2호
• /
• pp.183-192
• /
• 2023

위성영상 및 항공사진과 같은 원격탐사 자료들은 영상판독과 영상처리 기법을 통하여 영상 내의 객체를 탐지하고 추출하는 데에 사용될 수 있다. 특히, 원격탐사 자료의 해상도가 향상되고, 딥러닝(deep learning) 모델 등과 같은 기술의 발전으로 인하여 관심객체를 자동으로 추출하여 지도갱신 및 지형 모니터링 등에 활용될 수 있는 가능성이 증대되고 있다. 이를 위해, 본 연구에서는 의미론적 분할에 사용되는 대표적인 딥러닝 모델인 fully convolutional densely connected convolutional network (FC-DenseNet)을 기반으로 하여 항공정사영상 내 존재하는 비닐하우스를 추출하고, 이에 대한 결과를 정량적으로 평가하였다. 농림축산식품부의 팜맵(farm map)을 이용하여 담양, 밀양지역의 비닐하우스에 대한 레이블링을 수행하여 훈련자료를 생성하고, 훈련자료를 이용하여 FC-DenseNet의 훈련을 수행하였다. 원격탐사자료에 딥러닝 모델을 효과적으로 이용하기 위하여, 각 밴드별 특성이 유지되도록 instance norm을 이용하여 정규화과정을 수행하였으며, attention module을 추가하여 각 밴드별 가중치를 효과적으로 산정하였다. 실험결과, 딥러닝 모델을 이용하여 영상 내 존재하는 비닐하우스 지역을 효과적으로 추출할 수 있음을 확인하였으며 팜맵, 토지피복지도 등의 갱신에 활용될 수 있을 것으로 판단하였다.

• 한국측량학회지
• /
• 제24권1호
• /
• pp.57-64
• /
• 2006

최근 영상과 수치지도론 이용하여 빌딩의 고도 추출 연구가 활발히 진행되고 있다. 본 연구는 단영상과 수치지도를 이용하여 건물의 고도값을 추출을 목표로 하였다. 이를 위하여 항공사진측량학적 방법론을 기본으로 하고 이에 monoplotting 방법을 활용하여 지상좌표와 영상좌표의 상관관계를 적용하여 단 영상에서의 건물 고도값을 추출할 수 있었으며 정착도를 비교하기 위하여 1:5000 항공사진을 이용하여 추출한 고도값을 기준으로 비교분석 하였다. 그 결과 IKONOS 단영상과 수치지도를 이용하여 건물의 고도값을 일정 범위내의 값으로 복원할 수 있음을 알 수 있었다.

• 대한원격탐사학회지
• /
• 제19권3호
• /
• pp.255-261
• /
• 2003

Recently, the enormous increase in the volume of remotely sensed data is being acquired by an ever-growing number of earth observation satellites. The combining of diversely sourced imagery together is an important requirement in many applications such as data fusion, city modeling and object recognition. Aerial triangulation is a procedure to reconstruct object space from imagery. However, since the different kinds of imagery have their own sensor model, characteristics, and resolution, the previous approach in aerial triangulation (or georeferencing) is purformed on a sensor model separately. This study evaluated the advantages of aerial triangulation of large number of images from multi-sensors simultaneously. The incorporated multi-sensors are frame, push broom, and whisky broom cameras. The limits and problems of push-broom or whisky broom sensor models can be compensated by combined triangulation with other sensors The reconstructed object space from multi-sensor triangulation is more accurate than that from a single model. Experiments conducted in this study show the more accurately reconstructed object space from multi-sensor triangulation.

• 한국GIS학회:학술대회논문집
• /
• 한국GIS학회 2006년도 GIS/RS 공동춘계학술대회
• /
• pp.138-145
• /
• 2006

최근 영상과 수치지도를 이용하여 빌딩의 고도 추출 연구가 활발히 진행되고 있다. 본 연구는 단영상과 수치지도를 이용하여 건물의 고도 값을 추출을 목표로 하였다. 이를 위하여 항공사진측량학적 방법론을 기본으로 하고 이에 monoplotting 방법을 활용하여 지상좌표와 영상좌표의 상관관계를 적용하여 단 영상에서의 건물 고도 값을 추출할 수 있었으며 정확도를 비교하기 위하여 1:5000 항공사진을 이용하여 추출한 고도 값을 기준으로 비교 분석하였다. 그 결과 IKONOS 단영상과 수치지도를 이용하여 건물의 고도 값을 일정 범위내의 값으로 복원할 수 있음을 알 수 있었다.

• 대한원격탐사학회지
• /
• 제26권3호
• /
• pp.325-333
• /
• 2010

Image registration involves overlapping images of an identical region and assigning the data into one coordinate system. Image registration has proved important in remote sensing, enabling registered satellite imagery to be used in various applications such as image fusion, change detection and the generation of digital maps. The image descriptor, which extracts matching points from each image, is necessary for automatic registration of remotely sensed data. Using contrast enhancement algorithms such as histogram equalization and image stretching, the normalized data are applied to the image descriptor. Drawing on the different spectral characteristics of high resolution satellite imagery based on sensor type and acquisition date, the applied normalization method can be used to change the results of matching interest point descriptors. In this paper, the matching points by scale invariant feature transformation (SIFT) are extracted using various contrast enhancement algorithms and injection of Gaussian noise. The results of the extracted matching points are compared with the number of correct matching points and matching rates for each point.

• 대한원격탐사학회지
• /
• 제27권6호
• /
• pp.703-715
• /
• 2011

Forests have been considered one of the most important ecosystems on the earth, affecting the lives and environment. The sustainable forest management requires accurate and timely information of forest and tree parameters. Appropriately interpreted remotely sensed imagery can provide quantitative data for deriving forest information temporally and spatially. Especially, analysis of individual tree detection and crown delineation is significant issue, because individual trees are basic units for forest management. Individual trees in aerial imagery have reflectance characteristics according to tree species, crown shape and hierarchical status. This study suggested a method that identified individual trees and delineated crown boundaries through adopting gradient method algorithm to amplified greenness data using red and green band of aerial imagery. The amplification of specific band value improved possibility of detecting individual trees, and gradient method algorithm was performed to apply to identify individual tree tops. Additionally, tree crown boundaries were explored using spectral intensity pattern created by geometric characteristic of tree crown shape. Finally, accuracy of result derived from this method was evaluated by comparing with the reference data about individual tree location, number and crown boundary acquired by visual interpretation. The accuracy ($\hat{K}$) of suggested method to identify individual trees was 0.89 and adequate window size for delineating crown boundaries was $19{\times}19$ window size (maximum crown size: 9.4m) with accuracy ($\hat{K}$) at 0.80.

• 대한원격탐사학회지
• /
• 제18권2호
• /
• pp.117-125
• /
• 2002

연속적으로 상대적으로 짧은 간격으로 관측된 시계열 원격탐사 자료는 관측환경의 악화와 감지 시스템의 기계적 고장과 같은 관측 장애요인에 의해 많은 미관측 및 악성 자료를 가지게 된다. 본 연구는 adaptive 재구축 시스템을 이용하여 동적합성에 의해 미관측 및 악성 자료를 복구하는 문제를 다루고 있다. 제안된 재구축 방법은 관측 대상의 물리적 특성에서의 시간적 변화와 공간적 연속 특성에 근거한 영상처리 기법이며, adaptive 시스템은 관측 값과 지엽적 시간적 경향에 의해 추정된 예측 티의 가중치 합에 의해 합성영상을 생성하는 동적합성을 수행한다. 제안된 동적합성기술의 adaptive 재구축 시스템은 한반도를 관측한 1999년도와 2000년도 2년간의 NOAA AVHRR의 NDVI자료의 재구축에 적용되었다. 실험결과는 재구축된 시리즈는 미관측 및 악성 자료를 포함하고 있는 실제의 관측 영상 시리즈를 위하여 추정된 완전한 자료 값을 갖는 영상 시리즈로 사용될 수 있음을 보여주고 있다. 추가적으로 제안 시스템은 해당 시간에서의 시간적 변화량을 나타내는 gradient 영상을 생성하고, 이러한 영상들의 연속 시리즈에서 관측 대상의 시계열 변화 특성이 관측 자료 값의 영상 시리즈보다 더욱 분명히 나타나고 있다.

• 대한원격탐사학회지
• /
• 제35권4호
• /
• pp.573-587
• /
• 2019

A multi-temporal approach using remotely sensed time series data obtained over multiple years is a very useful method for monitoring land covers and land-cover changes. While spectral-based methods at any particular time limits the application utility due to instability of the quality of data obtained at that time, the approach based on the temporal profile can produce more accurate results since data is analyzed from a long-term perspective rather than on one point in time. In this study, a multi-temporal approach applying a multi-periodic harmonic model is proposed for classification of remotely sensed data. A harmonic model characterizes the seasonal variation of a time series by four parameters: average level, frequency, phase, and amplitude. The availability of high-quality data is very important for multi-temporal analysis.An satellite image usually have many unobserved data and bad-quality data due to the influence of observation environment and sensing system, which impede the analysis and might possibly produce inaccurate results. Harmonic analysis is also very useful for real-time data reconstruction. Multi-periodic harmonic model is applied to the reconstructed data to classify land covers and monitor land-cover change by tracking the temporal profiles. The proposed method is tested with the MODIS and GOCI NDVI time series over the Korean Peninsula for 5 years from 2012 to 2016. The results show that the multi-periodic harmonic model has a great potential for classification of land-cover types and monitoring of land-cover changes through characterizing annual temporal dynamics.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume II
• /
• pp.852-855
• /
• 2006

There is an increasing need to use data from different sensors in order to maximize the chances of obtaining a cloud-free image and to meet timely requirements for information. However, the use of data from multiple sensor systems is depending on comprehensive relationships between sensors of different types. Indeed, a study of inter-sensor relationships is well advanced in the effective use of remotely sensed data from multiple sensors. This paper was concerned with relationships between sensors of different types for vegetation indices (VI). The study was conducted using IKONOS and Landsat-7 ETM+ images. IKONOS and Landsat-7 ETM+ image of the same or about the same dates were acquired. The Landsat-7 ETM+ images were resampled in order to make them coincide with the pixel sizes of IKONOS. Inter-relationships of vegetation indices between images were performed using at-satellite reflectance obtained by converting image digital number (DN). All images were applied to topographic normalization method in order to reduce topographic effect in digital imagery. Also, Inter-sensor model equations between two sensors were developed and applied to other study region. In the result, the relational equations can be used to compute or interpret VI of one sensor using the VI of another sensor.

• 한국측량학회지
• /
• 제25권6_1호
• /
• pp.517-528
• /
• 2007

Extraction of the coastal boundary is important because the boundary serves as a reference in the demarcation of maritime zones such as territorial sea, contiguous zone, and exclusive economic zone. Accurate nautical charts also depend on well established, accurate, consistent, and current coastline delineation. However, to identify the precise location of the coastal boundary is a difficult task due to tidal and wave motions. This paper presents an efficient way to extract coastlines by applying digital image processing techniques to Synthetic Aperture Radar (SAR) imagery. Over the past few years, satellite-based SAR and high resolution airborne SAR images have become available, and SAR has been evaluated as a new mapping technology. Using remotely sensed data gives benefits in several aspects, especially SAR is largely unaffected by weather constraints, is operational at night time over a large area, and provides high contrast between water and land areas. Various image processing techniques including region growing, texture-based image segmentation, local entropy method, and refinement with image pyramid were implemented to extract the coastline in this study. Finally, the results were compared with existing coastline data derived from aerial photographs.