• The Journal of Korea Robotics Society
• /
• v.18 no.1
• /
• pp.66-71
• /
• 2023

As cameras have become primary sensors for mobile robots, vision based Simultaneous Localization and Mapping (SLAM) has achieved impressive results with the recent development of computer vision and deep learning. However, vision information has a disadvantage in that a lot of information disappears in a low-light environment. To overcome the problem, we propose an image enhancement method to perform visual SLAM in a low-light environment. Using the deep generative adversarial models and modified gamma correction, the quality of low-light images were improved. The proposed method is less sharp than the existing method, but it can be applied to ORB-SLAM in real time by dramatically reducing the amount of computation. The experimental results were able to prove the validity of the proposed method by applying to public Dataset TUM and VIVID++.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.11
• /
• pp.2965-2980
• /
• 1999

There are several models and the corresponding diagrams to express software system in many kinds of viewpoints, but these are supposed to be integrated and implemented into only one system. Therefore, the software modelers should have the models ensuring the consistency between information in software development life cycle. To support the robust models for modelers using OO modeling methods, i.e. UML, and CASE tools, the meta models of the software architecture and the consistency rules between the models are suggested in this thesis. Finally, the rules are implemented in the OO CASE tool, DEBUTO(Design By UML Tool). It supports UML1.1 notations and has visual modeling editors that enable users make their own software model.

• Proceedings of the Korean Institute of Landscape Architecture Conference
• /
• 2007.10b
• /
• pp.89-93
• /
• 2007

In the Japanese garden, a unique planting design has been used to improve visual harmony with the surrounding landscape by planting plants around the objects that are not harmonious with surrounding landscape. In this study, physiopsychological effects of plants caused by a traditional planting skill used in Japanese garden was verified in terms of visual relaxation using eye movement recording and semantic differential method. A total of fourteen Japanese volunteers(seven male and seven female) who have normal vision(aged $21{\sim}28$) participated as subjects. Experiment was carried out in the sealed room of Chiba University in Japan. Four different types of scenery models were presented which were created by combination of the three landscape factors of the surrounding background, the object that disturbs visual harmony, and the trees planted for improving visual harmony with the surrounding landscape. In the results, significantly more gaze fixations were measured on the trees than on the object and higher values in positive feelings were recorded for the stimuli with proper planting combination. Our results indicated that proper tree planting can cause physiopsychological relaxation by improving visual harmony with the surrounding landscape and provided new evidence for supporting scientific validity of the traditional planting skills.

• International journal of advanced smart convergence
• /
• v.13 no.2
• /
• pp.136-141
• /
• 2024

Chang'an (Chinese: 长安三万里), also known as 30,000 Miles from Chang'an, is a 2023 Chinese 3D animated historical drama film directed by Xie Junwei and Zou Jing.This thesis aims to explore the visual expression of traditional culture in the 3D animated film Chang'an as an example to reveal the reasons for the success of this type of film. The study analyses in detail the design of the character models and costumes, as well as the use of the traditional landscape painting technique of 'white space' in the composition of the screen from the visual aspect. Through the analysis of character design and screen composition, the thesis concludes that the success of Chang'an lies in its elaborate visual design and clever use of traditional culture, which makes it a 3D animation film with both artistic and commercial values. Finally, the thesis concludes that the production of a successful 3D animation film needs to combine the visual elements of 3D animation with traditional culture in order to win audience recognition and achieve commercial success.

• Korean Journal of Cognitive Science
• /
• v.26 no.4
• /
• pp.453-481
• /
• 2015

The presnt study reviewed two contrasting models, fixed-resolution slot versus flexible-resource hypotheses, for the representational characteristics of visual working memory (VWM), and emphasized the necessary efforts for resolving their conflicting arguments. To accomplish this goal, the review explored the background hypotheses of the object-based versus parallel independent storage models, and introduced theoretical bases for their contrasting claims. The review then evaluated validity of empirical evidence provided in the studies to support each model, and attempted an understanding of their neurophysiological background. The study further emphasized the necessity of theoretical and methodological reconsiderations to resolve their conflict as well as the necessity of obtaining converging pieces of evidence to accomplish the resolution.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.7
• /
• pp.109-118
• /
• 1999

A graphic software is one of the most important components of the vehicle simulator. To increase a visual reality of the simulator, the graphic software should require several technologies such as three-dimensional graphics, graphic modeling of the vehicle and the environment, drivers biomechanical models, and real-time data processing. This study presents a real time graphic driving simulator of a construction vehicle. The graphic simulator contains the three models of the construction vehicle, the human, and the environment, and employes a neural network approach to decrease an on-line dynamic computation. An excavator model is represented using an object-oriented paradigm and contains the detailed information about a real-size vehicle. The human model is introduced for objective visual evaluations of the developed excavator model. Since the environment model plays an important role in a real-time simulator, a block-based approach is implemented and a text format is utilized for easier construction of environment. The simulation results are illustrated in order to demonstrate the applicability of developed models and the neural network approach.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.1080-1099
• /
• 2019

A better tradeoff between robustness and invisibility will be realized by using the just noticeable (JND) model into the quantization-based watermarking scheme. The JND model is usually used to describe the perception characteristics of human visual systems (HVS). According to the research of cognitive science, HVS can adaptively extract the structure features of an image. However, the existing JND models in the watermarking scheme do not consider the structure features. Therefore, a novel JND model is proposed, which includes three aspects: contrast sensitivity function, luminance adaptation, and contrast masking (CM). In this model, the CM effect is modeled by analyzing the direction features and texture complexity, which meets the human visual perception characteristics and matches well with the spread transform dither modulation (STDM) watermarking framework by employing a new method to measure edge intensity. Compared with the other existing JND models, the proposed JND model based on structural regularity is more efficient and applicable in the STDM watermarking scheme. In terms of the experimental results, the proposed scheme performs better than the other watermarking scheme based on the existing JND models.

• Journal of Korean Association for Spatial Structures
• /
• v.22 no.2
• /
• pp.19-27
• /
• 2022

Visual inspection methods have limitations, such as reflecting the subjective opinions of workers. Moreover, additional equipment is required when inspecting the high-rise buildings because the height is limited during the inspection. Various methods have been studied to detect concrete cracks due to the disadvantage of existing visual inspection. In this study, a crack detection technology was proposed, and the technology was objectively and accurately through AI. In this study, an efficient method was proposed that automatically detects concrete cracks by using a Convolutional Neural Network(CNN) with the Orthomosaic image, modeled with the help of UAV. The concrete cracks were predicted by three different CNN models: AlexNet, ResNet50, and ResNeXt. The models were verified by accuracy, recall, and F1 Score. The ResNeXt model had the high performance among the three models. Also, this study confirmed the reliability of the model designed by applying it to the experiment.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.37 no.1
• /
• pp.78-86
• /
• 2009

Recently, there seems to besome problems in the urban visual landscape as a result of continuous economic growth and industrial development. At the same time, the public has begun to be aware of the importance of visual resources, and the necessity for visual landscape conservation and improvement. Therefore, the development of evaluative indicators for systematic visual landscape planning and design is urgent. The purpose ofthis study is to discover evaluative models and indicators for the diagnosis of urban visual landscapes. This study included the selection of 18 physical indicators(statistical data) by literature reviews, adoption of field and questionnaire surveys at 12 autonomous districts in Seoul and surrounding major mountain valleys and river streams(i.e. Mt. Nam and Han-River). The content of the questionnaire is scenic beauty. Moreover, the linear regression analysis between the scenic beauty mean scores and the physical indicator scores figure out the scenic beauty prediction model. As this study suggests, the most important indicators in urban visual landscapes are 'Greens', 'Park' and 'the number of apartment buildings(higher than 20 stories).' Based on the results, greens and parks should be priority elements to considerin urban landscape planning and design. Moreover, since the number of apartment buildings that are higher than 20 stories has a negative correlation with the scenic beauty score, it can be used as basic data for landscape planning. For the scenic beauty prediction models and evaluative indicators suggest a direction of urban management, each indicator becomes basic data for visual landscape planning and design. In following studies, if physical indicators and case studies are added, the scenic beauty prediction models and evaluative indicators could be more synthetic and systematic. Moreover, the development of physical indicators in three dimensions(3D)(i.e. results from visual district analysis, view surface analysis) could be expected to obtain more general and varied results.

• Journal of the HCI Society of Korea
• /
• v.1 no.2
• /
• pp.51-58
• /
• 2006

Information visualization, generally speaking, consists of three steps: transform from raw data to data model, visual mapping from data model to visual structure, and transform from visual structure to information model. In this paper, we propose a visual mapping method from spatiotemporal table information, which is related to events in large-scale building, to 3D map metaphor. The process has also three steps as follows. First, after analyzing the table attributes, we carefully define a context to fully represent the table-information. Second, we choose meaningful attribute sets from the context. Third, each meaningful attribute set is mapped to one well defined visual structure. Our method has several advantages. First, users can intuitively achieve non-spatial information through the 3D map which is a powerful spatial metaphor. Second, this system shows various visual mapping method applicable to other data models in the form of table, especially GIS. After describing the whole concept of our visual mapping, we will show the results of implementation for several requests.