• Journal of Digital Contents Society
• /
• v.19 no.4
• /
• pp.605-613
• /
• 2018

In this paper, we propose a system to walk around the world with virtual reality technology. Although the virtual reality users are interested in the virtual travel contents, the conventional virtual travel contents have limited space for experiencing and lack of interactivity. In order to solve the problem of lack of realism and limited space, which is a disadvantage of existing contents, this system created a virtual space using Google Street View image. Users can have realistic experience with real street images, and travel a vast area of the world provided by Google Street View image. Also, a virtual reality headset and a treadmill equipment are used so that the user can actually walk in the virtual space, which maxmizes user interactivity and immersion. We expect this system contributes to the leisure activities of virtual reality users by allowing natural walking trip from famous tourist spots to even mountain roads and alleys.

• Korean Institute of Interior Design Journal
• /
• v.22 no.4
• /
• pp.70-77
• /
• 2013

This study has analysed the composition elements in a cafe space where visual transfer-elements are filled and the perceptual characteristics of facade designs with the purpose of drawing any important elements to advertisement and their related items for uniqueness of designs. For the analysis of the perception process shown in the consecutive situations of observing and visiting cafes, the cafe facade was grouped and stereotyped for the analysis of perceptual characteristics and significant composition elements for better designing of cafes through survey with representative facades as subjects. The conclusions from this study are the followings. First, for the uniqueness specific to cafes to be integrated into facade, memory was chosen first as the most significant advertisement factor followed by interest as with male and attention as with female. The memory has much to do with furniture and finishing material of Clause (4), Chapter 4.1 and the types having effects on perception of Clause (1) and the atmosphere having effect on that of Clause (2) were found to be major factors to attention and interest. Second, it was found out that women preferred horizontally stable partition and men clearly divided facades. The factor of shape was observed first among the constituents of facade followed by color. There was no difference with 'shape' between men and women and color was found to be a space constituent having a lot of effects on women. Third, the memory of experience from visiting a cafe was very likely to offer the motivation of visiting it again, on which furniture had the most effect followed by finishing material and color. Such elevation elements as facade and logo were found not to have effect on the memory or the re-visit. Any intention of visiting again seemed to be influenced by such comprehensive images as atmosphere rather than by any concrete facade, furniture, or appliance. From the above viewpoint, facade design should have any uniqueness or impressive feature as well as the effect of making passers-by drop in and attracting them into the shop. The analysis of attributes of facade constituents revealed that the abstract images in addition to the configuration of facade had much to do with interest or behavior.

• Current Research on Agriculture and Life Sciences
• /
• v.31 no.4
• /
• pp.256-264
• /
• 2013

This study presents a greening plan for the under space of elevated rail tracks to reducing landscape impairment and improve the streetscape. This study focuses on a section of the Daegu Metro line number 3 that includes a concentration of high-rise apartments and commercial areas. First, different types of planting were categorized for the under space of the elevated rail track, and then images of each planting type were created using a 3D simulation tool to evaluate the visual characteristics. The landscape images and related adjectives were assessed using a survey. As a result, rows of flower trees received the highest evaluation, and 'harmony' was identified as the most important factor affecting the railscape preference. These results can be important data for establishing an efficient greening plan for the under space of elevated rail tracks.

• The Journal of Korean Institute of Information Technology
• /
• v.16 no.12
• /
• pp.13-24
• /
• 2018

Recently, light pollution has become a serious environment issue caused by excessive uses of artificial light. Central and local governments have made efforts to manage light pollution and mitigate light pollution damages. Developing methods to diagnose light pollution is critical to effectively monitor light pollution conditions in Seoul. This study develops a methodology to create a map that presents the status of light pollution in Seoul, using International Space Station(ISS) night-time images. Through the map, we evaluated the areas that show high levels of light intensity and found out local characteristics of light intensity; Commercial area, office building concentrated area, and large sports facilities. The result of study provides basic understanding to present a new way for monitoring light pollution in urban sites.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.1
• /
• pp.65-70
• /
• 2023

In this paper, we propose a CCTV storage space securing model using YOLO v3. CCTV is installed and operated in various parts of society for disasters, disasters and safety such as crime prevention, fire prevention, and monitoring, and the number of CCTV is increasing and the quality of the video quality is improving. Due to this, as the number and size of image files increase, it is difficult to cope with the existing storage space. In order to solve this problem, we propose a model that detects specific objects in CCTV images using YOLO v3 library and deletes unnecessary frames by saving only the corresponding frames, thereby securing storage space by reducing the size of the image file, and thereby Periodic images can be stored and managed. After applying the proposed model, it was confirmed that the average image file size was reduced by 94.9%, and it was confirmed that the storage period was increased by about 20 times compared to before the application of the proposed model.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.1
• /
• pp.47-55
• /
• 2024

We spend a lot of time in indoor space, and the space has a huge impact on our lives. Interior design plays a significant role to make an indoor space attractive and functional. However, it should consider a lot of complex elements such as color, pattern, and material etc. With the increasing demand for interior design, there is a growing need for technologies that analyze these design elements accurately and efficiently. To address this need, this study suggests a deep learning-based design analysis system. The proposed system consists of a semantic segmentation model that classifies spatial components and an image classification model that classifies attributes such as color, pattern, and material from the segmented components. Semantic segmentation model was trained using a dataset of 30000 personal indoor interior images collected for research, and during inference, the model separate the input image pixel into 34 categories. And experiments were conducted with various backbones in order to obtain the optimal performance of the deep learning model for the collected interior dataset. Finally, the model achieved good performance of 89.05% and 0.5768 in terms of accuracy and mean intersection over union (mIoU). In classification part convolutional neural network (CNN) model which has recorded high performance in other image recognition tasks was used. To improve the performance of the classification model we suggests an approach that how to handle data that has data imbalance and vulnerable to light intensity. Using our methods, we achieve satisfactory results in classifying interior design component attributes. In this paper, we propose indoor space design analysis system that automatically analyzes and classifies the attributes of indoor images using a deep learning-based model. This analysis system, used as a core module in the A.I interior recommendation service, can help users pursuing self-interior design to complete their designs more easily and efficiently.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.3
• /
• pp.127-134
• /
• 2018

Electric transmission towers are facilities to transport electrical power from a plant to an electrical substation. The towers are connected using power lines that are installed with a proper sag by loosening the cable to lower the tension and to secure the sufficient clearance from the ground or nearby objects. The power line sag may extend over the tolerance due to the weather such as strong winds, temperature changes, and a heavy snowfall. Therefore the periodical mapping of the power lines is required but the poor accessibility to the power lines limit the work because most power lines are placed at the mountain area. In addition, the manual mapping of the power lines is also time-consuming either using the terrestrial surveying or the aerial surveying. Therefore we utilized multiple overlapping images acquired from a low-cost drone to automatically reconstruct the power lines in the object space. Two overlapping images are selected for epipolar image resampling, followed by the line extraction for the resampled images and the redundant images. The extracted lines from the epipolar images are matched together and reconstructed for the power lines primitive that are noisy because of the multiple line matches. They are filtered using the extracted line information from the redundant images for final power lines points. The experiment result showed that the proposed method successfully generated parabolic curves of power lines by interpolating the power lines points though the line extraction and reconstruction were not complete in some part due to the lack of the image contrast.

• Journal of Computing Science and Engineering
• /
• v.6 no.1
• /
• pp.1-11
• /
• 2012

Computed tomography (CT) images are widely used for the analysis of the temporal evaluation or monitoring of the progression of a disease. The follow-up examinations of CT scan images of the same patient require a 3D registration technique. In this paper, an automatic and robust registration is proposed for the rigid registration of 3D CT images. The proposed method involves two steps. Firstly, the two CT volumes are aligned based on their principal axes, and then, the alignment from the previous step is refined by the optimization of the similarity score of the image's voxel. Normalized cross correlation (NCC) is used as a similarity metric and a downhill simplex method is employed to find out the optimal score. The performance of the algorithm is evaluated on phantom images and knee synthetic CT images. By the extraction of the initial transformation parameters with principal axis of the binary volumes, the searching space to find out the parameters is reduced in the optimization step. Thus, the overall registration time is algorithmically decreased without the deterioration of the accuracy. The preliminary experimental results of the study demonstrate that the proposed method can be applied to rigid registration problems of real patient images.

• Journal of the Institute of Convergence Signal Processing
• /
• v.13 no.3
• /
• pp.119-129
• /
• 2012

In the medical field, the hardening of tissues is one of important informations used in diagnosis or understanding progress of disease, a quantitative measuring method of hardening is important for objective diagnosis. It has been proposed MRE(Magnetic Resonance Elastography) method that measures an index of hardening, viscoelastic properties in a noninvasive. Because the S/N ratio of MRE images go down when measuring viscoelastic properties from local wavelength and local damping factor of a propagating wave in MRE method, methods using multiple phase MRE images have been examined to decrease the effect of noise. We propose a method measuring viscoelastic properties after Fitting a function for multiple phase MRE images in this research. This proposed method has a advantage to set up arbitrarily the variation rate of a space direction of viscoelastic properties or the spatial resolution of measuring values according to changing of the noise included in images, though it applies viscoelastic wave for multiple phase MRE images. We confirmed the effectiveness of a proposed method by experiment using simulation images and experiment using silicone-gel phantom.

• Smart Media Journal
• /
• v.11 no.4
• /
• pp.30-37
• /
• 2022

Disease threatens plant growth and recognizing the type of disease is essential to making a remedy. In recent years, deep learning has witnessed a significant improvement for this task, however, a large volume of labeled images is one of the requirements to get decent performance. But annotated images are difficult and expensive to obtain in the agricultural field. Therefore, designing an efficient and effective strategy is one of the challenges in this area with few labeled data. Transfer learning, assuming taking knowledge from a source domain to a target domain, is borrowed to address this issue and observed comparable results. However, current transfer learning strategies can be regarded as a supervised method as it hypothesizes that there are many labeled images in a source domain. In contrast, unsupervised transfer learning, using only images in a source domain, gives more convenience as collecting images is much easier than annotating. In this paper, we leverage unsupervised transfer learning to perform plant disease recognition, by which we achieve a better performance than supervised transfer learning in many cases. Besides, a vision transformer with a bigger model capacity than convolution is utilized to have a better-pretrained feature space. With the vision transformer-based unsupervised transfer learning, we achieve better results than current works in two datasets. Especially, we obtain 97.3% accuracy with only 30 training images for each class in the Plant Village dataset. We hope that our work can encourage the community to pay attention to vision transformer-based unsupervised transfer learning in the agricultural field when with few labeled images.