• Journal of Cadastre & Land InformatiX
• /
• v.47 no.2
• /
• pp.79-90
• /
• 2017

Urban environment represent one of the most dynamic regions on earth. As in other countries, forests, green areas, agricultural lands are rapidly changing into residential or industrial areas in South Korea. Monitoring such rapid changes in land use requires rapid data acquisition, and satellite imagery can be an effective method to this demand. In general, SAR(Synthetic Aperture Radar) satellites acquire images with an active system, so the brightness of the image is determined by the surface roughness. Therefore, the water areas appears dark due to low reflection intensity, In the residential area where the artificial structures are distributed, the brightness value is higher than other areas due to the strong reflection intensity. If we use these characteristics of SAR images, settlement areas can be extracted efficiently. In this study, extraction of settlement areas was performed using TerraSAR-X of German high-resolution X-band SAR satellite and KOMPSAT-5 of South Korea, and object-oriented image classification method using the image segmentation technique is applied for extraction. In addition, to improve the accuracy of image segmentation, the speckle divergence was first calculated to adjust the reflection intensity of settlement areas. In order to evaluate the accuracy of the two satellite images, settlement areas are classified by applying a pixel-based K-means image classification method. As a result, in the case of TerraSAR-X, the accuracy of the object-oriented image classification technique was 88.5%, that of the pixel-based image classification was 75.9%, and that of KOMPSAT-5 was 87.3% and 74.4%, respectively.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_1
• /
• pp.1573-1587
• /
• 2021

A Drone image is an ultra-high-resolution image that is several or tens of times higher in spatial resolution than a satellite or aerial image. Therefore, drone image-based remote sensing is different from traditional remote sensing in terms of the level of object to be extracted from the image and the amount of data to be processed. In addition, the optimal scale and size of data used for model training is different depending on the characteristics of the applied deep learning model. However, moststudies do not consider the size of the object to be found in the image, the spatial resolution of the image that reflects the scale, and in many cases, the data specification used in the model is applied as it is before. In this study, the effect ofspatial resolution and image size of drone image on the accuracy and training time of the semantic segmentation deep learning model of six wintering vegetables was quantitatively analyzed through experiments. As a result of the experiment, it was found that the average accuracy of dividing six wintering vegetablesincreases asthe spatial resolution increases, but the increase rate and convergence section are different for each crop, and there is a big difference in accuracy and time depending on the size of the image at the same resolution. In particular, it wasfound that the optimal resolution and image size were different from each crop. The research results can be utilized as data for getting the efficiency of drone images acquisition and production of training data when developing a winter vegetable segmentation model using drone images.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.53 no.6
• /
• pp.7-16
• /
• 2011

This study discussed the applicability of satellite SAR (Synthetic Aperture Radar) imagery with regard to reservoir monitoring, and tried the extraction of reservoir storage from multi-temporal C-band RADARSAT-1 SAR backscattering images of Yedang and Goongpyeong agricultural reservoirs, acquired from May to October 2005. SAR technology has been advanced as a complementary and alternative approach to optical remote sensing and in-situ measurement. Water bodies in SAR imagery represent low brightness induced by low backscattering, and reservoir storage can be derived from the backscatter contrast with the level-area-volume relationship of each reservoir. The threshold segmentation over the routine preprocessing of SAR images such as speckle reduction and low-pass filtering concluded a significant correlation between the SAR-derived reservoir storage and the observation record in spite of the considerable disagreement. The result showed up critical limitations for adopting SAR data to reservoir monitoring as follows: the inappropriate specifications of SAR data, the unreliable rating curve of reservoir, the lack of climatic information such as wind and precipitation, the interruption of inside and neighboring land cover, and so on. Furthermore, better accuracy of SAR-based reservoir monitoring could be expected through different alternatives such as multi-sensor image fusion, water level measurement with altimeters or interferometry, etc.

• Journal of Satellite, Information and Communications
• /
• v.11 no.2
• /
• pp.14-17
• /
• 2016

This paper describes the implementation of automatic number-braille converter based on image processing for the blind people. The algorithm is consists of four main steps. First step is binary image conversion of the input image obtained by the camera. the second step is segmentation operation by means of dilation and labelling of the character. Next step is calculation of cross-correlation between segmented text image and pre-defined text-pattern image. The final step is generation of brail output which is relevant to input image. The computer simulation result was showing 91.8% correct conversion rate for arabian numbers which is printed in A4-sheet and practical possibility was also confirmed by using implemented automatic number-braille converter based on DSP image processing board.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.5
• /
• pp.3045-3050
• /
• 2013

Purpose: Hepatic resection is arguably the preferred treatment for huge hepatocellular carcinoma (H-HCC). Estimating the remnant liver volume is therefore essential. This study aimed to evaluate the feasibility of using computer-assisted volumetric analysis for this purpose. Methods: The study involved 40 patients with H-HCC. Laboratory examinations were conducted, and a contrast CT-scan revealed that 30 cases out of the participating 40 had single-lesion tumors. The remaining 10 had less than three satellite tumors. With the consensus of the team, two physicians conducted computer-assisted 3D segmentation of the liver, tumor, and vessels in each case. Volume was automatically computed from each segmented/labeled anatomical field. To estimate the resection volume, virtual lobectomy was applied to the main tumor. A margin greater than 1 cm was applied to the satellite tumors. Resectability was predicted by computing a ratio of functional liver resection (R) as (Vresected-Vtumor)/(Vtotal-Vtumor) x 100%, applying a threshold of 50% and 60% for cirrhotic and non-cirrhotic cases, respectively. This estimation was then compared with surgical findings. Results: Out of the 22 patients who had undergone hepatectomies, only one had an R that exceeded the threshold. Among the remaining 18 patients with non-resectable H-HCC, 12 had Rs that exceeded the specified ratio and the remaining 6 had Rs that were < 50%. Four of the patients who had Rs less than 50% underwent incomplete surgery due to operative findings of more extensive satellite tumors, vascular invasion, or metastasis. The other two cases did not undergo surgery because of the high risk involved in removing the tumor. Overall, the ratio of functional liver resection for estimating resectability correlated well with the other surgical findings. Conclusion: Efficient pre-operative resectability assessment of H-HCC using computer-assisted volumetric analysis is feasible.

• Journal of Korean Society for Geospatial Information Science
• /
• v.20 no.1
• /
• pp.83-91
• /
• 2012

Crown density, which is defined as the proportion of the forest floor concealed by tree crown, is important and useful information in various fields. Previous methods of measuring crown density have estimated crown density by interpreting aerial photographs or through a ground survey. These are time-consuming, labor-intensive, expensive and inconsistent approaches, as they involve a great deal of subjectivity and rely on the experience of the interpreter. In this study, the crown density of a forest in Korea was estimated using KOMPSAT-2 high-resolution satellite images. Using the image segmentation technique and stand information of the digital forest map, the forest area was divided into zones. The crown density for each segment was determined using the discriminant analysis method and the forest ratio method. The results showed that the accuracy of the discriminant analysis method was about 60%, while the accuracy of the forest ratio method was about 85%. The probability of extraction of candidate to update was verified by comparing the result with the digital forest map.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_2
• /
• pp.1591-1604
• /
• 2020

This study is a study on classifying land cover by applying high-resolution satellite images to deep learning algorithms and verifying the performance of algorithms for each spatial object. For this, the Fully Convolutional Network-based algorithm was selected, and a dataset was constructed using Kompasat-3 satellite images, land cover maps, and forest maps. By applying the constructed data set to the algorithm, each optimal hyperparameter was calculated. Final classification was performed after hyperparameter optimization, and the overall accuracy of DeeplabV3+ was calculated the highest at 81.7%. However, when looking at the accuracy of each category, SegNet showed the best performance in roads and buildings, and U-Net showed the highest accuracy in hardwood trees and discussion items. In the case of Deeplab V3+, it performed better than the other two models in fields, facility cultivation, and grassland. Through the results, the limitations of applying one algorithm for land cover classification were confirmed, and if an appropriate algorithm for each spatial object is applied in the future, it is expected that high quality land cover classification results can be produced.

• Korean Journal of Remote Sensing
• /
• v.39 no.3
• /
• pp.269-282
• /
• 2023

The purpose of this study was to construct land cover maps using a deep learning model and to select the optimal deep learning model for land cover classification by adjusting the dataset such as input image size and Stride application. Two types of deep learning models, the U-net model and the DeeplabV3+ model with an Encoder-Decoder network, were utilized. Also, the combination of the two deep learning models, which is an Ensemble model, was used in this study. The dataset utilized RapidEye satellite images as input images and the label images used Raster images based on the six categories of the land use of Intergovernmental Panel on Climate Change as true value. This study focused on the problem of the quality improvement of the dataset to enhance the accuracy of deep learning model and constructed twelve land cover maps using the combination of three deep learning models (U-net, DeeplabV3+, and Ensemble), two input image sizes (64 × 64 pixel and 256 × 256 pixel), and two Stride application rates (50% and 100%). The evaluation of the accuracy of the label images and the deep learning-based land cover maps showed that the U-net and DeeplabV3+ models had high accuracy, with overall accuracy values of approximately 87.9% and 89.8%, and kappa coefficients of over 72%. In addition, applying the Ensemble and Stride to the deep learning models resulted in a maximum increase of approximately 3% in accuracy and an improvement in the issue of boundary inconsistency, which is a problem associated with Semantic Segmentation based deep learning models.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.103-106
• /
• 2004

Extrapolation off the boundaries of scattered data is an intrinsic feature of interpolation. However, extrapolation causes serious problems in stereo-vision and mapping, which has not been investigated carefully. In this paper, we present novel schemes to eliminate the extrapolation effects for the generation of a digital elevation model (DEM). As a first step, we devise point distribution criteria, namely COG (Center of Gravity) and ECI (Empty Center Index), and apply rigorous and robust elimination based on the criteria. Compared with other methods, the proposed schemes are computationally fast and applicable to a wide range of interpolation techniques.

• Proceedings of the KSRS Conference
• /
• 2009.03a
• /
• pp.207-212
• /
• 2009

고해상도 위성영상이 갖는 공간 객체의 복잡성과 다양성에 의해 기존 중 저해상도 영상에서 사용하던 분류 방식을 고해상도 영상에 그대로 적용하기에는 한계가 있다. 이러한 문제를 극복하기 위하여 영상은 공간적인 특성을 추가적으로 추출하여 분광정보와 결합하여 분류를 수행하는 방식의 연구가 진행되고 있다. 본 연구의 목적은 고해상도 영상의 분류정확도를 개선하기 위하여 새로운 공간 개체(spatial feature)인 SSI(Shape-Size Index)를 제안하는데 있다. SSI는 영역 확장(Region Growing) 기반의 영상 분할(Image Segmentation)을 수행한 후, 객체 내에 객체의 크기와 모양에 대한 고려를 모두 할 수 있는 공간 속성값을 할당하여 공간정보를 추출한다. 추출된 공간정보를 고해강도 영상의 다중분광 밴드와 결합하여 Support Vector Machine(SVM)을 이용한 분류를 수행하였다. 실험 결과, 제안한 기법의 분류 결과가 분광밴드만을 이용하여 분류를 수행한 결과뿐만 아니라 기존의 공간 개체 추출방식인 GLCM, PSI 기법을 이용한 분류 결과에 비해 높은 분류정확도를 도출함을 알 수 있었다.