• Korean Journal of Remote Sensing
• /
• v.38 no.5_1
• /
• pp.535-543
• /
• 2022

A drone is used to diagnose crop growth and to provide information through images in the agriculture field. In the case of using high spatial resolution drone images, growth information for each object can be produced. However, accurate object detection is required and adjacent objects should be efficiently classified. The purpose of this study is to develop a Chinese cabbage object detection algorithm using multispectral reflectance images observed from drone and computer vision techniques. Drone images were captured between 7 and 15 days after planting a Chinese cabbage from 2018 to 2020 years. The thresholds of object detection algorithm were set based on 2019 year, and the algorithm was evaluated based on images in 2018 and 2019 years. The vegetation area was classified using the characteristics of spectral reflectance. Then, morphology techniques such as dilatation, erosion, and image segmentation by considering the size of the object were applied to improve the object detection accuracy in the vegetation area. The precision of the developed object detection algorithm was over 95.19%, and the recall and accuracy were over 95.4% and 93.68%, respectively. The F1-Score of the algorithm was over 0.967 for 2 years. The location information about the center of the Chinese cabbage object extracted using the developed algorithm will be used as data to provide decision-making information during the growing season of crops.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.2
• /
• pp.77-82
• /
• 2023

The Ministry of Agriculture, Food and Rural Affairs established the FarmMap, an digital map of agricultural land. In this study, using deep learning, we suggest the application of farm map reading to farmland such as paddy fields, fields, ginseng, fruit trees, facilities, and uncultivated land. The farm map is used as spatial information for planting status and drone operation by digitizing agricultural land in the real world using aerial and satellite images. A reading manual has been prepared and updated every year by demarcating the boundaries of agricultural land and reading the attributes. Human reading of agricultural land differs depending on reading ability and experience, and reading errors are difficult to verify in reality because of budget limitations. The farmmap has location information and class information of the corresponding object in the image of 5 types of farmland properties, so the suitable AI technique was tested with ResNet50, an instance segmentation model. The results of attribute reading of agricultural land using deep learning and attribute reading by humans were compared. If technology is developed by focusing on attribute reading that shows different results in the future, it is expected that it will play a big role in reducing attribute errors and improving the accuracy of digital map of agricultural land.

• Sim-seong Yeon-gu
• /
• v.39 no.1
• /
• pp.61-91
• /
• 2024

Alchemy is the process of producing worthless substances into the best substances through chemical opus(work). On the surface, many of the alchemist's experiments can be depicted as work on transforming substances, but in reality, the alchemist's result is a product of the Unconscious. This study aims to explain the three phases of alchemy, Nigredo, Albedo, and Rubedo, through Michael Mayer's alchemical text, Atalanta Fugiens, and understand the transformation process by utilizing images that appeared from clients' sand play therapy. This study first described why alchemy, as the foundation for the psychology of the Unconscious, is important in sand play that deals with images. Next, Nigredo (blackening), the first phase of the alchemical process, is briefly described, and how the contents of Nigredo, such as chaos, dissolution, separation, division, corruption, death, and calcination, appear in sand play therapy. Next, the second phase, albedo (whitening), is described, and how the images of water and fire, which are representative images of albedo in the form of purification, sublimation, distillation, separation, descension, and coagulation, are revealed in sand play. Lastly, the phase of rubedo (reddening) in alchemy is described, and how the form of union (mandala or central image) in rubedo, which appears in the form of conjunction and rebirth, is revealed in sand play. The symbols revealed in alchemy are very valuable in amplifying the images that appeared in sand play therapy or dream analysis. In particular, the procedures found in alchemical opus are helpful in understanding the transformation process of personality.

• Journal of Intelligence and Information Systems
• /
• v.12 no.1
• /
• pp.17-31
• /
• 2006

In this paper, passport recognition and face verification methods which can automatically recognize passport codes and discriminate forgery passports to improve efficiency and systematic control of immigration management are proposed. Adjusting the slant is very important for recognition of characters and face verification since slanted passport images can bring various unwanted effects to the recognition of individual codes and faces. Therefore, after smearing the passport image, the longest extracted string of characters is selected. The angle adjustment can be conducted by using the slant of the straight and horizontal line that connects the center of thickness between left and right parts of the string. Extracting passport codes is done by Sobel operator, horizontal smearing, and 8-neighborhood contour tracking algorithm. The string of codes can be transformed into binary format by applying repeating binary method to the area of the extracted passport code strings. The string codes are restored by applying CDM mask to the binary string area and individual codes are extracted by 8-neighborhood contour tracking algerian. The proposed RBF network is applied to the middle layer of RBF network by using the fuzzy logic connection operator and proposing the enhanced fuzzy ART algorithm that dynamically controls the vigilance parameter. The face is authenticated by measuring the similarity between the feature vector of the facial image from the passport and feature vector of the facial image from the database that is constructed with PCA algorithm. After several tests using a forged passport and the passport with slanted images, the proposed method was proven to be effective in recognizing passport codes and verifying facial images.

• The Journal of Korean Academy of Prosthodontics
• /
• v.52 no.2
• /
• pp.97-104
• /
• 2014

This study was aimed to compare the radiopacity of four kinds of currently available resin based implant cements using digital radiography. Materials and Methods: Four resin-based implant cements((Estemp $Implant^{TM}$ (Spident, Incheon, Korea), $Premier^{(R)}$Implant (Premier, Pennsylvania, USA), $Cem-Implant^{TM}$ (B.J.M lab, Or-yehuda, Israel), $InterCem^{TM}$ (SCI-PHARM, California, USA)) and control group (Elite Cement $100^{TM}$ (GC, Tokyo, Japan) ) were mixed and cured according to the manufacturer's instructions on the custom made split-type metal mold. A total of 150 specimens of each cement were prepared and each specimen (purity over 99%) was placed side-by-side with an aluminum step wedge for image taking with Intraoral X-ray unit (Esx, Vatech, Korea) and digital X-ray sensor (EzSensor, Vatech, Korea). For the evaluation of aluminum wedge equivalent thickness (mm Al), ImageJ 1.47 m (Wayne Rasband, National Institutes of Health, USA) and Color inspector 3D ver 2.0 (Interaktive Visualisierung von Farbraumen, Berlin, Germany) programs were used. Result: Among the 5 cements, Elite cement $100^{TM}$ (control group) showed the highest radio-opacity in all thickness. In the experimental group, $InterCem^{TM}$ had the highest radio-opacity followed by $Premier^{(R)}$ Implant $Cement^{TM}$, $Cem-Implant^{TM}$ and Estemp $Implant^{TM}$. In addition, $InterCem^{TM}$ showed radio-opacity that met the ISO No. 4049 standard in all the tested specimen thickness. Cem-Implant on 0.5 mm thickness showed radiopacity that met the ISO No. 4049 standard. Conclusion: Among the implant resin-based cements tested in the study, $Premier^{(R)}$ Implant Cement and Estemp $Implant^{TM}$ did not show appropriate radio-opacity. Only $InterCem^{TM}$ and $Cem-Implant^{TM}$ 0.5 mm specimen had the proper radiopacity and met the experiment standard.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.32 no.2
• /
• pp.270-277
• /
• 2005

The purpose of this study was to clarify the palatal volume and anterior palatal slope of the children with class II div.1 malocclusion and normal occlusion in mixed dentition(Hellman dental age III A) using three-dimensional laser scanner. Samples were consisted of 31 children with skeletal class II div.1 malocclusion in mixed dentition and 29 children with normal occlusion and profile among the contestants in 2000-2004 Healthy Dentition Contest in Seoul. Totally 60 maxillary study model were taken. Each cast was scanned by three-dimensional laser scanner (Breuckmann opto-TOP HE, INUS, Korea) and shaped into the three-dimension image by Rapidform 2004 program(INUS, Korea). And the palatal volume and anterior palatal slope of each cast were calculated by Rapidform 2004 program(INUS, Korea). The values were statistically compared and evaluated by independent samples t-test with 95% of significance level. The results were as follows: 1. Palatal volume was significantly lesser in children with class II div.1 malocclusion than that of normal occlusion in mixed dentition(p<0.05). 2. No significant difference in the anterior palatal slope and palatal height was found between the children with class II div.1 malocclusion and normal occlusion in mixed dentition(p>0.05). 3. Palatal length was significantly greater in children with class II div.1 malocclusion than that of normal occlusion in mixed dentition(p<0.01). 4. Intercanine and intermolar width were significantly lesser in children with class II div.1 malocclusion than those of normal occlusion in mixed dentition(respectively p<0.05 and p<0.01).

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.31 no.4
• /
• pp.1-21
• /
• 2013

This study has researched the characteristics and elements of the chuibyong, a sort of trellis in the Joseon Dynasty through the old pictorial data. The results were as follows; First, as a result of the analysis for the 25 pictorial data in the Joseon Dynasty, the chuibyongs have usually functioned as screening the facility to protect the private life and dividing the spaces of the site, but it was internally regarded as the props which symbolized the dignity and elegance of high class. Especially, not only the faunas such as crane and deer, and the floras such as Pinus densiflora, Musa basjoo, bamboo species and Paulownia coreana, but also various garden elements including oddly shaped stone, pond and pavilion were shown in the surrounding area of the chuibyong, and they were considered as a series of combination that was needed in the ideal garden for the literati. Secondly, the chuibyong was recognized as the ideological object which was typical of the literati culture in the story derived from an ancient event of China. Such image has been reflected intactly in the garden culture, and the chuibyong has been used(considered) as the important scenery of the season to imitate and reenact the Chinese Classical Garden in the narrative painting. Thirdly, in terms of the shape and function, the chuibyong in the paintings in the Joseon Dynasty basically had the function of the shielding and spatial division. Fourthly, the height of the chuibyung was similar to the one of fence which exceeds the person's height or Youngbyek(影壁) which is installed in the front and the rear of the main gate in China, and the various shape's chuibyung was properly set up in many spaces. Lastly, the making of the chuibyong in Joseon Dynasty was related to the trend of the writer's culture which was popular nationally in Ming dynasty rather than the particular functions or the location conditions. Especially, the symbol expression of the chuibyong showed on 'Elegant Gathering in the Western Garden' which was brought from China was recreated in the mansion of the upper class in Hanyang city as the center, and the primary mode for the expression of the wealth and writer's spirit through the chuibyong was transformed into the high-quality's garden element which could be created in the royal palace or the mansion of the upper class. Also, the use of the chuibyung was changed by spreading into the residential style for common people after the mid-nineteenth century, and it means that the chuibyung was developed into Korean styles.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.24 no.3
• /
• pp.83-98
• /
• 2021

Urban green space is an important component for enhancing urban ecosystem health. Thus, identifying the spatial structure of urban green space is required to manage a healthy urban ecosystem. The Ministry of Environment has provided the level 3 land cover map(the highest (1m) spatial resolution map) with a total of 41 classes since 2010. However, specific urban green information such as street trees was identified just as grassland or even not classified them as a vegetated area in the map. Therefore, this study classified detailed urban green information(i.e., tree, shrub, and grass), not included in the existing level 3 land cover map, using two types of high-resolution(<1m) remote sensing data(i.e., airborne LiDAR and RGB ortho imagery) in Suwon, South Korea. U-Net, one of image segmentation deep learning approaches, was adopted to classify detailed urban green space. A total of three classification models(i.e., LRGB10, LRGB5, and RGB5) were proposed depending on the target number of classes and the types of input data. The average overall accuracies for test sites were 83.40% (LRGB10), 89.44%(LRGB5), and 74.76%(RGB5). Among three models, LRGB5, which uses both airborne LiDAR and RGB ortho imagery with 5 target classes(i.e., tree, shrub, grass, building, and the others), resulted in the best performance. The area ratio of total urban green space(based on trees, shrub, and grass information) for the entire Suwon was 45.61%(LRGB10), 43.47%(LRGB5), and 44.22%(RGB5). All models were able to provide additional 13.40% of urban tree information on average when compared to the existing level 3 land cover map. Moreover, these urban green classification results are expected to be utilized in various urban green studies or decision making processes, as it provides detailed information on urban green space.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_3
• /
• pp.1475-1490
• /
• 2021

Detecting oil spill area using statistical characteristics of SAR images has limitations in that classification algorithm is complicated and is greatly affected by outliers. To overcome these limitations, studies using neural networks to classify oil spills are recently investigated. However, the studies to evaluate whether the performance of model shows a consistent detection performance for various oil spill cases were insufficient. Therefore, in this study, two CNNs (Convolutional Neural Networks) with basic structures(Simple CNN and U-net) were used to discover whether there is a difference in detection performance according to the structure of CNN and distribution characteristics of oil spill. As a result, through the method proposed in this study, the Simple CNN with contracting path only detected oil spill with an F1 score of 86.24% and U-net, which has both contracting and expansive path showed an F1 score of 91.44%. Both models successfully detected oil spills, but detection performance of the U-net was higher than Simple CNN. Additionally, in order to compare the accuracy of models according to various oil spill cases, the cases were classified into four different categories according to the spatial distribution characteristics of the oil spill (presence of land near the oil spill area) and the clarity of border between oil and seawater. The Simple CNN had F1 score values of 85.71%, 87.43%, 86.50%, and 85.86% for each category, showing the maximum difference of 1.71%. In the case of U-net, the values for each category were 89.77%, 92.27%, 92.59%, and 92.66%, with the maximum difference of 2.90%. Such results indicate that neither model showed significant differences in detection performance by the characteristics of oil spill distribution. However, the difference in detection tendency was caused by the difference in the model structure and the oil spill distribution characteristics. In all four oil spill categories, the Simple CNN showed a tendency to overestimate the oil spill area and the U-net showed a tendency to underestimate it. These tendencies were emphasized when the border between oil and seawater was unclear.

• Tunnel and Underground Space
• /
• v.33 no.4
• /
• pp.281-298
• /
• 2023

Continuous research efforts are being devoted to unmanned mobile platforms for lunar exploration. There is an ongoing demand for real-time information processing to accurately determine the positioning and mapping of areas of interest on the lunar surface. To apply deep learning processing and analysis techniques to practical rovers, research on software integration and optimization is imperative. In this study, a foundational investigation has been conducted on real-time analysis of virtual lunar base construction site images, aimed at automatically quantifying spatial information of key objects. This study involved transitioning from an existing region-based object recognition algorithm to a boundary box-based algorithm, thus enhancing object recognition accuracy and inference speed. To facilitate extensive data-based object matching training, the Batch Hard Triplet Mining technique was introduced, and research was conducted to optimize both training and inference processes. Furthermore, an improved software system for object recognition and identical object matching was integrated, accompanied by the development of visualization software for the automatic matching of identical objects within input images. Leveraging satellite simulative captured video data for training objects and moving object-captured video data for inference, training and inference for identical object matching were successfully executed. The outcomes of this research suggest the feasibility of implementing 3D spatial information based on continuous-capture video data of mobile platforms and utilizing it for positioning objects within regions of interest. As a result, these findings are expected to contribute to the integration of an automated on-site system for video-based construction monitoring and control of significant target objects within future lunar base construction sites.