• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.10
• /
• pp.303-308
• /
• 2020

The ReLU(Rectified Linear Unit) function has been dominantly used as a standard activation function in most deep artificial neural network models since it was proposed. Later, Leaky ReLU, Swish, and Mish activation functions were presented to replace ReLU, which showed improved performance over existing ReLU function in image classification task. Therefore, we recognized the need to experiment with whether performance improvements could be achieved by replacing the RELU with other activation functions in the super resolution task. In this paper, the performance was compared by changing the activation functions in EDSR model, which showed stable performance in the super resolution task. As a result, in experiments conducted with changing the activation function of EDSR, when the resolution was converted to double, the existing activation function, ReLU, showed similar or higher performance than the other activation functions used in the experiment. When the resolution was converted to four times, Leaky ReLU and Swish function showed slightly improved performance over ReLU. PSNR and SSIM, which can quantitatively evaluate the quality of images, were able to identify average performance improvements of 0.06%, 0.05% when using Leaky ReLU, and average performance improvements of 0.06% and 0.03% when using Swish. When the resolution is converted to eight times, the Mish function shows a slight average performance improvement over the ReLU. Using Mish, PSNR and SSIM were able to identify an average of 0.06% and 0.02% performance improvement over the RELU. In conclusion, Leaky ReLU and Swish showed improved performance compared to ReLU for super resolution that converts resolution four times and Mish showed improved performance compared to ReLU for super resolution that converts resolution eight times. In future study, we should conduct comparative experiments to replace activation functions with Leaky ReLU, Swish and Mish to improve performance in other super resolution models.

• Journal of Korean Society of Forest Science
• /
• v.80 no.1
• /
• pp.32-41
• /
• 1991

This study is focusted to the national park of Korean typical mountain Chi-ri, its visual resources of forests, and practiced inspectind course by way of hypothesis and tests, to show visual resource management objectively, and that of quantitative basic data. spatial image structure measured by Semantic Differential(S.D.) Scale was shown through factor analysis algorithm for the analyzing psychological amount and examined the flowing out of decisive factor and the objective importance related mutual factors by appling the measurement of visual quality. Also, it has been investigated the differences between the degrees of expectation which is used before and of satisfaction which is used, by appling instrumental expectation theory. And showed patterns of investigation area through factor analyzing algorithm. As a national Park, visual factors that have natural landscape harmonized forest, sky, surface of the water, curious stones and rocks, temples should be escalate their values affirmatively so as to be the scenery of pointed direction and enjoyable, and it is needs the techniques visual resource management and its controlling technique to make artificial structures more intentional planning and systemical setting. Manmade distinctive quality in the spatials that affect complementally or harmonizingly, should be received considering relations between the distifution and joining which in line with various visual presenting massive factors. More than that, it is needed united basic standard to the beauty of arrangements which contain visual continuity considered balance between nature and human work, simplicity of structural types, assimilation, emphasis, unification of different factors and pro rata.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.43 no.4
• /
• pp.15-26
• /
• 2015

The Daegu Metropolitan Transit Corporation Advisory Committee has chosen 5 styles of bridge-pier designs, including coating, graphic, planting, billboard and safety-facility style, based on the results of landscape simulations from a previous study. This study was conducted to investigate citizen's preferences and emotional images for each style of bridge-pier design, by aiming at the pilot urban landscape improvement section from Daebong Bridge in Suseong Gu to the crossroads near Dongseong Elementary School in Daegu Metropolitan City. The questionnaire was drawn up regarding the urban landscape improvement plans applied to the research area, and the questions were about citizens' perception of bridge-pier structures generated by constructing a light rail transit, important factors to consider when designing bridge piers, preferences for each style of bridge-pier design and emotional impact. 60.4% of the survey participants were found to perceive bridge-pier structures as unattractive, so it was necessary to improve them aesthetically. Regarding visual factors of bridge-pier designs, color was most important at 5.81, followed by form at 5.57. Regarding aesthetic component factors, harmony was most important at 6.07, followed by amenity at 6.00. In the survey participants' preference for each bridge-pier design, the graphic style was preferred most at 4.14, followed by the planting style. In emotional adjectives used for each bridge-pier design, the coating style, the safety-facility style and the non-treatment style showed similar results, and all of these styles were evaluated as artificial, lifeless and desolate. The graphic style and the billboard style showed different tendencies, depending on visual factors and aesthetic component factors applied to the graphic design used for these two bridge-pier styles. Since natural materials were used for the planting style, however, it showed high preference for such emotional images as natural and lively. The emotional adjective 'amiable' was found to affect citizens' preferences for each bridge-pier aesthetic improvement plan most, and it was also analyzed to have an effect on all the styles of bridge-pier designs. To improve the landscape of a light rail transit being constructed inside the urban area, this study quantitatively extracted citizens' preferences and emotional adjective for every style of bridge-pier design applied to the pilot urban landscape improvement section, and it is expected that the results of this study will be used as basic data to improve the landscape of bridge piers.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.28 no.3
• /
• pp.122-130
• /
• 2010

The Study takes the rivers in Zhouzhuang - traditional Chinese Kangnam watery landscape as the object. The purpose of this study is to grasp the relationships between visual characteristics and the preference. The following is the research process: Firstly, the theoretical study of Zhouzhuang, the traditional Kangnam region in China, is conducted, the watery landscape is taken pictures, and 22 photos are selected. Secondly, in order to grasp the visual preference and landscape characteristics of the watery landscape in Zhouzhuang, 22 pictures and 25 pairs of adjectives are adopted for the questionnaire survey. Thirdly, in order to have a better understanding on the physical properties and effects of physical quantity on the preference, the occupation ratios of buildings and sculptures, natural elements, footpaths, bank revetments and other landscape elements are calculated, and the mean analysis, dispersion analysis and regression analysis are conducted. In order to grasp the landscape characteristics and preference factors, 25 pairs of adjectives are used to conduct the factor analysis. In order to grasp the effects of characteristics of visual factors on the preference, the dispersion analysis and regression analysis are carried out. The results are as follows: From the results of the landscape preference analysis, in the No.22 photo with the top preference, 11 pairs of adjectives, namely, "harmonious-disharmonious", "beautiful-ugly", "rural-urban", "soft-rough", "stable-instable", "romantic-realistic", "cheerful-gloomy", "brilliant-simple", "natural-artificial", "familiar-strange", and "clean-dirty" have positive effects on watery landscape. It can be viewed as the relatively important factor in the visual preference. In terms of the results of visual physical quantity analysis of traditional Chinese Kangnam watery landscape, the landscape with high occupation ratio of buildings and sculptures has positive effects on visual preference. The results of analysis of visual physical quantity and preference show that the preference degree increases as the occupation ratio of footpath area increases. The analysis results of visual characteristics of traditional Chinese Kangnam watery landscape identify four factors, namely psychological factor, cultural factor, condition factor and physical factor. It can be concluded from the results of analysis of the relationships between visual preference and visual characteristics that the return coefficient B of the psychological factor is +0.936. It can significantly affect the watery landscape, so it can be identified as the most important factor among the visual preference factors of Chinese Kangnam watery landscape.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.38 no.2
• /
• pp.14-30
• /
• 2020

This study focuses on the fact that pictorial maps in the late Joseon Dynasty were conceptual diagrams with the place names perceived by the people at the time of their production. In this regard, targeting on five pictorial maps, the humanistic landscape characteristics of Pyongyang, which had cultural identities such as a historically old, commercial, and Pungnyu(appreciation for the arts) city, were derived as follows. First, the historic legitimacy of Pyongyang Castle was represented by ritual and religious facilities. They include 'Dangunjeon' and 'Gijagung' related to the nation founder, 'Munmujeong': the remains of Goguryeo, 'Sajikdan' & 'Pyongyanggangdan': the place of the national rites, Hyanggyo and Seowon: education & rite functions, Buddhism and Taoist facilities, 'Yongsindang', 'Sanshindang', and 'Jesindan': folk religion facilities. Gija-related facilities, which became symbols of Pyongyang due to the importance of Small-Sinocentrism and Gija dignity tendency, were distributed throughout Pyongyang Castle though, the facilities related to King Dongmyeong of Goguryeo and the spaces of religion praying for blessings are spread in Bukseong and on the riverside of Daedonggang each. Second, as a Pyongando Province's economic center, Pyongyang's commercial landscape was represented by logistics and transportation facilities. The Daedonggang River, which was in charge of transportation functions, had many decks such as 'Yangmyeongpo', 'Cheongryongpo' and 'Waeseongjin' and bridges, such as 'Yeongjegyo' and 'Gangdonggyo', which connected major transportation routes. The road network was created in Oeseong area to facilitate logistics transportation and management, and many warehouses named after the jurisdiction of Pyongyangbu were distributed near the roads and Provincial Offices of the main gates. In addition, it was characterized by the urban area systematically divided with hierarchical roads, 'Bukjangnim' of willow trees planted on the main entrance roads of Pyongyang Castle, a linear landscape created by 'Simnijangnim' consisting of mixed forests with elm trees. Third, Pungnyu City is realized by the distribution of amusement facilities. The riverside of Daedonggang adjacent to Naeseong exhibits characteristics of artificial landscape such as a canal leading to the inside of the castle, a docking facility with embankments, and a port with cargo ships anchored. However, Bukseong of the natural surroundings had numerous pavilions and platforms such as 'Bubyeongnu', 'Eulmildae', 'Choeseungdae', 'Jebyeokjeong' and engraved letters such as 'Cheongnyubyeok', 'Jangbangho'. 'Osunjeong', 'Byeogwolji', 'Banwolji' near 'Sachang', and 'Aeryeondang', built on the island of a square pond, created waterscape in Naeseong invisible from the Daedonggang, and for practical purposes, ponds and repeated willow vegetation landscape related to Gija were placed in the western rampart of Jungseong. In addition, 'Seonyeondong', a cemetery of Gisaeng, located near by Chilseongmun, was used as poem titles and themes by literary people, contributing to the creation of the Pungnyu image of Pyongyang.

• The Korean Journal of Nuclear Medicine
• /
• v.39 no.1
• /
• pp.57-68
• /
• 2005

Purpose: The objective of this study was to assess attenuation correction algorithms with the $^{137}Cs$ point source for the brain positron omission tomography (PET) imaging process. Materials & Methods: Four different types of phantoms were used in this study for testing various types of the attenuation correction techniques. Transmission data of a $^{137}Cs$ point source were acquired after infusing the emission source into phantoms and then the emission data were subsequently acquired in 3D acquisition mode. Scatter corrections were performed with a background tail-fitting algorithm. Emission data were then reconstructed using iterative reconstruction method with a measured (MAC), elliptical (ELAC), segmented (SAC) and remapping (RAC) attenuation correction, respectively. Reconstructed images were then both qualitatively and quantitatively assessed. In addition, reconstructed images of a normal subject were assessed by nuclear medicine physicians. Subtracted images were also compared. Results: ELEC, SAC, and RAC provided a uniform phantom image with less noise for a cylindrical phantom. In contrast, a decrease in intensity at the central portion of the attenuation map was noticed at the result of the MAC. Reconstructed images of Jaszack and Hoffan phantoms presented better quality with RAC and SAC. The attenuation of a skull on images of the normal subject was clearly noticed and the attenuation correction without considering the attenuation of the skull resulted in artificial defects on images of the brain. Conclusion: the complicated and improved attenuation correction methods were needed to obtain the better accuracy of the quantitative brain PET images.

• FLOWER RESEARCH JOURNAL
• /
• v.18 no.2
• /
• pp.125-135
• /
• 2010

To discover the main characteristics of Korean traditional flower arrangement, they were compared with different articles and old paintings used in royal court ceremonies. The primary research involved principle of design. The times periods used were the Joseon Dynasty era of Korea, the Ming era of China, and the Edo eras of Japan. The result, which shows both the similarities and differences, of the research is summarized as follows. The similarities were that they all respect the features of nature, and their image expresses their creator's thinking. There was one technique, called 'Suje', in which a part of the stem is coming out from one branch. Also, each three eras preferred flowering trees and ornamental trees more than annuals or foliage plants. one of the differences was that korea used a simple number of materials. The work had volume and appeared mild by using a soft curved line which was repetitive and massive. The Joseon Dynasty era advanced a sense of beauty with artistic symmetry and balance. The work seemed soft and natural because of the little change in blank space, with almost no angle of line. The form had a characteristic preference of being taller than the typical Japanese arrangement. It appeared simple, calm, and rustic by using only one kind of material. In contrast, the Chinese style was gorgeous and displayed volume in a non-symmetrical tripodal form, which incorporated various colors and materials. Also, they avoided processing the materials in order to emphasize the original beauty of nature. Chinese flower arts did not become formalized because they did not consider the formality seriously the formal. The Japanese style was also gorgeous because it incorporated various materials and angles. It included an extreme technique in which an artificial line divided the blank space delicately. The line was both strong and delicate in an established form. The restriction of the main branch gave a light feeling, as well as more strain as in a balance sense. The Japanese eras emphasized more the use of line and a sense of blank space.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.89-106
• /
• 2022

Recently, the amount of video data collected from smartphones, CCTVs, black boxes, and high-definition cameras has increased rapidly. According to the increasing video data, the requirements for analysis and utilization are increasing. Due to the lack of skilled manpower to analyze videos in many industries, machine learning and artificial intelligence are actively used to assist manpower. In this situation, the demand for various computer vision technologies such as object detection and tracking, action detection, emotion detection, and Re-ID also increased rapidly. However, the object detection and tracking technology has many difficulties that degrade performance, such as re-appearance after the object's departure from the video recording location, and occlusion. Accordingly, action and emotion detection models based on object detection and tracking models also have difficulties in extracting data for each object. In addition, deep learning architectures consist of various models suffer from performance degradation due to bottlenects and lack of optimization. In this study, we propose an video analysis system consists of YOLOv5 based DeepSORT object tracking model, SlowFast based action recognition model, Torchreid based Re-ID model, and AWS Rekognition which is emotion recognition service. Proposed model uses single-linkage hierarchical clustering based Re-ID and some processing method which maximize hardware throughput. It has higher accuracy than the performance of the re-identification model using simple metrics, near real-time processing performance, and prevents tracking failure due to object departure and re-emergence, occlusion, etc. By continuously linking the action and facial emotion detection results of each object to the same object, it is possible to efficiently analyze videos. The re-identification model extracts a feature vector from the bounding box of object image detected by the object tracking model for each frame, and applies the single-linkage hierarchical clustering from the past frame using the extracted feature vectors to identify the same object that failed to track. Through the above process, it is possible to re-track the same object that has failed to tracking in the case of re-appearance or occlusion after leaving the video location. As a result, action and facial emotion detection results of the newly recognized object due to the tracking fails can be linked to those of the object that appeared in the past. On the other hand, as a way to improve processing performance, we introduce Bounding Box Queue by Object and Feature Queue method that can reduce RAM memory requirements while maximizing GPU memory throughput. Also we introduce the IoF(Intersection over Face) algorithm that allows facial emotion recognized through AWS Rekognition to be linked with object tracking information. The academic significance of this study is that the two-stage re-identification model can have real-time performance even in a high-cost environment that performs action and facial emotion detection according to processing techniques without reducing the accuracy by using simple metrics to achieve real-time performance. The practical implication of this study is that in various industrial fields that require action and facial emotion detection but have many difficulties due to the fails in object tracking can analyze videos effectively through proposed model. Proposed model which has high accuracy of retrace and processing performance can be used in various fields such as intelligent monitoring, observation services and behavioral or psychological analysis services where the integration of tracking information and extracted metadata creates greate industrial and business value. In the future, in order to measure the object tracking performance more precisely, there is a need to conduct an experiment using the MOT Challenge dataset, which is data used by many international conferences. We will investigate the problem that the IoF algorithm cannot solve to develop an additional complementary algorithm. In addition, we plan to conduct additional research to apply this model to various fields' dataset related to intelligent video analysis.

• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.193-205
• /
• 2023

A large amount of floating debris from land-based sources during heavy rainfall has negative social, economic, and environmental impacts, but there is a lack of monitoring systems for floating debris accumulation areas and amounts. With the recent development of artificial intelligence technology, there is a need to quickly and efficiently study large areas of water systems using drone imagery and deep learning-based object detection models. In this study, we acquired various images as well as drone images and trained with You Only Look Once (YOLO)v5s and the recently developed YOLO7 and YOLOv8s to compare the performance of each model to propose an efficient detection technique for land-based floating debris. The qualitative performance evaluation of each model showed that all three models are good at detecting floating debris under normal circumstances, but the YOLOv8s model missed or duplicated objects when the image was overexposed or the water surface was highly reflective of sunlight. The quantitative performance evaluation showed that YOLOv7 had the best performance with a mean Average Precision (intersection over union, IoU 0.5) of 0.940, which was better than YOLOv5s (0.922) and YOLOv8s (0.922). As a result of generating distortion in the color and high-frequency components to compare the performance of models according to data quality, the performance degradation of the YOLOv8s model was the most obvious, and the YOLOv7 model showed the lowest performance degradation. This study confirms that the YOLOv7 model is more robust than the YOLOv5s and YOLOv8s models in detecting land-based floating debris. The deep learning-based floating debris detection technique proposed in this study can identify the spatial distribution of floating debris by category, which can contribute to the planning of future cleanup work.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2023.04a
• /
• pp.7-7
• /
• 2023

Currently, the main technologies of various fourth industries are big data, the Internet of Things, artificial intelligence, blockchain, mixed reality (MR), and drones. In particular, "digital twin," which has recently become a global technological trend, is a concept of a virtual model that is expressed equally in physical objects and computers. By creating and simulating a Digital twin of software-virtualized assets instead of real physical assets, accurate information about the characteristics of real farming (current state, agricultural productivity, agricultural work scenarios, etc.) can be obtained. This study aims to streamline agricultural work through automatic water management, remote growth forecasting, drone control, and pest forecasting through the operation of an integrated control system by constructing digital twin data on the main production area of the nojinot industry and designing and building a smart farm complex. In addition, it aims to distribute digital environmental control agriculture in Korea that can reduce labor and improve crop productivity by minimizing environmental load through the use of appropriate amounts of fertilizers and pesticides through big data analysis. These open-field agricultural technologies can reduce labor through digital farming and cultivation management, optimize water use and prevent soil pollution in preparation for climate change, and quantitative growth management of open-field crops by securing digital data for the national cultivation environment. It is also a way to directly implement carbon-neutral RED++ activities by improving agricultural productivity. The analysis and prediction of growth status through the acquisition of the acquired high-precision and high-definition image-based crop growth data are very effective in digital farming work management. The Southern Crop Department of the National Institute of Food Science conducted research and development on various types of open-field agricultural smart farms such as underground point and underground drainage. In particular, from this year, commercialization is underway in earnest through the establishment of smart farm facilities and technology distribution for agricultural technology complexes across the country. In this study, we would like to describe the case of establishing the agricultural field that combines digital twin technology and open-field agricultural smart farm technology and future utilization plans.