• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.6
• /
• pp.671-679
• /
• 2020

In order to increase the food self-sufficiency rate, monitoring and analysis of crop conditions in the cultivated area is important, and the existing measurement methods in which agricultural personnel perform measurement and sampling analysis in the field are time-consuming and labor-intensive for this reason inefficient. In order to overcome this limitation, it is necessary to develop an efficient method for monitoring crop information in a small area where many exist. In this study, RGB images acquired from unmanned aerial vehicles and vegetation index calculated using RGB image were applied as deep learning input data to classify complex upland crops in small farmland. As a result of each input data classification, the classification using RGB images showed an overall accuracy of 80.23% and a Kappa coefficient of 0.65, In the case of using the RGB image and vegetation index, the additional data of 3 vegetation indices (ExG, ExR, VDVI) were total accuracy 89.51%, Kappa coefficient was 0.80, and 6 vegetation indices (ExG, ExR, VDVI, RGRI, NRGDI, ExGR) showed 90.35% and Kappa coefficient of 0.82. As a result, the accuracy of the data to which the vegetation index was added was relatively high compared to the method using only RGB images, and the data to which the vegetation index was added showed a significant improvement in accuracy in classifying complex crops.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.29 no.1
• /
• pp.157-165
• /
• 2011

This study is to be used as a fundamental material of rural amenity resources researches, such as excavating, establishing and modifying national agricultural landscape resources, so as to efficiently manage them. It is carried out with targeting traditional Darangyi-Rice terrace which has design factors of agricultural landscape resources. We have set up the standard range with practicable similar standard(Marginal Farmland and Less Favored Areas and etc), those of Japan, and the results of analyzing the characteristics of Darangyi-Rice terrace already known. As a result of the field investigation, it has been revealed that a great deal of Darangyi-Rice terrace are being used for not corresponding purposes, or damaged and disappeared. For preserving and well-managing Darangyi-Rice terrace as a rural landscape resource which has rural design factors, it should be advanced detailed and accurate studies on present conditions and changes of Darangyi-Rice terrace, with researches on significances, values, utilities and economical efficiency of Darangyi-Rice terrace by regions. In addition, we utilized various spatial imagery data in the researching process. Consequently, it is concluded that if high resolution imagery data is used, it can establish rather minute and accurate large-scale DB, and monitor elaborate changes as well. It is therefore thought that its application can be higher as actualizing DB hereafter.

• 한국사회정책
• /
• v.24 no.2
• /
• pp.181-215
• /
• 2017

The study found that the origins of modern Korean welfare regime are closely related to the political and economic order of the U.S. military rule between 1945 and 1948. The creation of developmental state in 1960s and 1970s can not be imagined from the standpoint of the U.S. military rule. The U.S. military government dismantled the labor movement and the farmers' movement, and dealt a devastating blow to leftist political forces. Through this process, the U.S. military government turned the political landscape of the Republic of Korea, which was dominated by left-wing political forces in August 1945, completely transformed into the political landscape dominated by right-wing political forces. Moreover, it would not have been possible without the physical force of the US military government to transplant American capitalism instead of the social (democratic) state that the majority of the Korean people wanted. Through farmland reform, the traditional landowning classes were broken down, the revolutionary farmers turned into conservative peasants, and the distribution of factories owned by the Japanese led to the birth of a new capitalist class that was subordinated to the state. From the viewpoint of the welfare regime, the most significant meaning of the US military government is that it laid the foundations for the developmental state in the 1960s and 1970s in Korea.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.12
• /
• pp.595-602
• /
• 2020

This study analyzes the plan to increase the social value of the KRC (Korea Rural Community Corporation). For this aim, this study examines the current status of participation in the KRC business and the social value, targeting the farmers among the external stakeholders and derived the main characteristics and important projects of the KRC using network analysis. As a result of network analysis, the rural water management business was found to be the most important business in most regions (Rural Water Development Business 0.805, Agricultural and Fishery Production Base Maintenance Business 0.758, Farmland Banking Business 0.762, Regional Development Business 0.643). On the other hand, in the case of Jeju, the agricultural production base improvement business and the regional development project were found to be the most important projects of KRC due to the unique characteristics of the region. The results of this kind of analysis differ in the importance between KRC business by region, and it is necessary to carefully review the local conditions in order to enhance social value through KRC business in the future. However, since the value of degree centrality between each business is different for each region, efforts to increase the value of KRC's social value, while accounting for local conditions, are needed.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_2
• /
• pp.1579-1590
• /
• 2020

In this paper, spatially-adaptive denormalization (SPADE) based U-Net is proposed to detect changes by using high-resolution satellite images. The proposed network is to preserve spatial information using SPADE. Change detection methods using high-resolution satellite images can be used to resolve various urban problems such as city planning and forecasting. For using pixel-based change detection, which is a conventional method such as Iteratively Reweighted-Multivariate Alteration Detection (IR-MAD), unchanged areas will be detected as changing areas because changes in pixels are sensitive to the state of the environment such as seasonal changes between images. Therefore, in this paper, to precisely detect the changes of the objects that consist of the city in time-series satellite images, the semantic spatial objects that consist of the city are defined, extracted through deep learning based image segmentation, and then analyzed the changes between areas to carry out change detection. The semantic objects for analyzing changes were defined as six classes: building, road, farmland, vinyl house, forest area, and waterside area. Each network model learned with KOMPSAT-3A satellite images performs a change detection for the time-series KOMPSAT-3 satellite images. For objective assessments for change detection, we use F1-score, kappa. We found that the proposed method gives a better performance compared to U-Net and UNet++ by achieving an average F1-score of 0.77, kappa of 77.29.

• Journal of Korean Society of Rural Planning
• /
• v.28 no.2
• /
• pp.71-85
• /
• 2022

The food self-sufficiency rate of agricultural products in Korea, excluding rice, is around 20%, and the government is promoting various policies including a Multiple-Purpose Utilization of Paddy Fields project, to increase the self-sufficiency rate of major grains. The project for Multiple-Purpose Utilization of Paddy Fields is being promoted as a part of a program to create farmland infrastructure to facilitate the cultivation of crops other than rice in rice paddies, and pilot projects were started in four regions in 2020. The purpose of this study is to analyze the economic effects of the pilot project for Multiple-Purpose Utilization of Paddy Fields, and to propose policies to increase the effectiveness of the project. In order to analyze the economic effect, we estimated the change in farm income generated by switching from rice to other crops, and measured the effect of welfare change using the Equilibrium Displacement Model (EDM). As a result of the analysis, social welfare is expected to increase when the pilot project for Multiple-Purpose Utilization of Paddy Fields is implemented, and the income of the beneficiary farmers is also expected to improve compared to that of single-cropping when double-cropping is implemented. However, it was found that the economic feasibility of the project differs depending on the crops converted. Juksan-myeon, Gimje-si, which is an area where soybean production was successful, was analyzed from the viewpoint of increasing the economic feasibility of the pilot project. Their success factors were analyzed into four major factors: infrastructure, farming methods, education, and collaboration with local agricultural organizations. If such a success story can be utilized in the future project implementation process, it can contribute to the improvement of farm household income and national economic welfare.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.67 no.2
• /
• pp.85-94
• /
• 2022

The mixed cropping system is a centuries-old cropping technique widely practiced in farmers' fields worldwide. Increased plant diversity enhances farmland biodiversity, which improves grain yield and quality. However, the effect of growing different rice cultivars simultaneously has rarely been investigated. In the present study, six glutinous rice cultivars were selected, and two mixture cultivation methods were determined according to plant height, grain yield, and color. Colored and glutinous rice are used for specific purposes by consumers because of their color and nutritive value. Six glutinous rice varieties, including aromatic and colored rice, were included in the combination interplanting trials. The results showed that, compared with the corresponding monocropping systems, almost all combinations of the mixed cropping systems had advantages in yield-related traits. Compared with monocropping systems, mixed cropping systems increased the number of panicles per plant and maturation rate by 20% and 10%, respectively. An increase of 18-20% grain yield was observed in mixed cropping plots compared with that in plots which grew only a single rice variety. Some rice varieties, such as green colored rice 'Nogwonchall' and black colored rice 'Chungpunghukhayangchall', exhibited 18-22% increased yield when they were planted in combinations. The high yields were primarily owing to improved light interception and reduced lodging, although other factors (for example, reduced severity of disease) may have also contributed.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_1
• /
• pp.597-608
• /
• 2022

Remotely sensed data have been used in various fields, such as disasters, agriculture, urban planning, and the military. Recently, the demand for the multitemporal dataset with the high-spatial-resolution has increased. This manuscript proposed an automatic image matching algorithm using a deep learning technique to utilize a multitemporal remotely sensed dataset. The proposed deep learning model was based on High Resolution Net (HRNet), widely used in image segmentation. In this manuscript, denseblock was added to calculate the correlation map between images effectively and to increase learning efficiency. The training of the proposed model was performed using the multitemporal orthophotos of the National Geographic Information Institute (NGII). In order to evaluate the performance of image matching using a deep learning model, a comparative evaluation was performed. As a result of the experiment, the average horizontal error of the proposed algorithm based on 80% of the image matching rate was 3 pixels. At the same time, that of the Zero Normalized Cross-Correlation (ZNCC) was 25 pixels. In particular, it was confirmed that the proposed method is effective even in mountainous and farmland areas where the image changes according to vegetation growth. Therefore, it is expected that the proposed deep learning algorithm can perform relative image registration and image matching of a multitemporal remote sensed dataset.

• The Journal of Korean-Japanese National Studies
• /
• no.34
• /
• pp.77-123
• /
• 2018

The liberated korea has the estimated population 16 million in 1945, and added 2.5 million just after an year. The korean repatriates returned by way of 2 main routes. The returnees, Wol-Nam-Min(former residents in north korea), and repatriates from Manchuria came into south korea over the 38th division line. The other repatriates from japanese islands and pacific areas came into Busan port and the vicinity. The repatriates who returned from the China and the Japanese islands made up about 80% of the total added population. However, the influx of overseas repatriates who explosively increased between 1945 and 1946, declined abruptly in April of 1946, and at last illegal re-emigration group to Manchuria and Japan Appeared, who had repatriated from those areas. This study deals with the "re-migration phenomenon of 1946" in korea, mainly focuses on 1) the motivation for those who decided to remigrate, their prospects of resettlement in Manchuria and post war japan after re-migration, 2) the structural problems of the Korean society in 1946-1947, and 3) the social recognition for the people who letf for Manchuria and Japan. This study proved the cause and background of re-migration phenomenon. The Manchuria case, the local authorities wanted farmers and peasants who could cultivate the abandoned land which had been originally pioneered and reclaimed by korean poor peasants, who repatriated to korean peninsula. On the other hand, the korean repatriates had a hard time in tenanting farmland, and so much difficulty in getting farming tools including fertilizer. That's why they left korea for Manchuria again. The Japanese case, the korean repatriates had a tough life owing to the restriction of properties left in japan, while the inflation and food shortage in korea got worse and worst. Accordingly, many koreans tried illegal entrance into post war japan. This study is a part of clarifying the universality and specificity of post war repatriation and migration issues developed in the south Korea. Through this study, we can find how difficult it is for newly liberated areas to accommodate repatriates and make them ordinary nationals in harmonic way with successful social integration. and we can observe the social aspect and administrative ability of newly liberated south korea in detail, Because the present korea has faced with so many problems connected with immigration workers and re-setting with korean communities abroad, we should introspect these historical experience of our own.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.51 no.2
• /
• pp.131-142
• /
• 2023

Solar power facilities to reduce carbon emissions are continuously being installed in forests, farmland, city, and on water. However, research on visual preferences and the psychological impact on observers after installing solar power facilities is insufficient. Therefore, in this study, shooting was conducted according to the viewing distance of the near, middle, and distant views of Hapcheon Dam, Korea's largest floating photovoltaic power plant. The acquired images were edited using Photoshop to compare the presence or absence of floating photovoltaic power generation facilities. In addition, psychological changes and visual preferences were analyzed through an EEG test and questionnaire among 50 participants. The results are summarized, as follows. First, the installation of water photovoltaic power generation facilities has a passive impact on the subjects' psychological changes and visual preference. Second, the psychological changes due to the installation of water photovoltaic power generation facilities were judged to affect almost all research subjects, regardless of nationality, gender, or universisty major. Third, the visual preference for installing the water photovoltaic power generation facility is low, which can be interpreted as the water photovoltaic power generation facility negatively affecting the "friendliness" and "naturalness" of the landscape. In addition, this change in visual preference was found to differ depending on the gender and universiity major of the subjects. Fourth, the psychological change and visual preference of the floating photovoltaic power generation facility according to the viewing distance, found that the close range had a higher effect than the middle and distant ranges.