• Journal of Broadcast Engineering
• /
• v.25 no.6
• /
• pp.944-953
• /
• 2020

Object detection plays a crucial role in a self-driving system. With the advances of image recognition based on deep convolutional neural networks, researches on object detection have been actively explored. In this paper, we proposed a lightweight model of the mask R-CNN, which has been most widely used for object detection, to efficiently predict location and shape of various objects on the road environment. Furthermore, feature maps are adaptively re-calibrated to improve the detection performance by applying an attention module to the neural network layer that plays different roles within the mask R-CNN. Various experimental results for real driving scenes demonstrate that the proposed method is able to maintain the high detection performance with significantly reduced network parameters.

• Journal of IKEEE
• /
• v.25 no.2
• /
• pp.243-251
• /
• 2021

In this paper, we propose a measurement technique of indoor location based on markerless applicable to AR. The proposed technique has the following originality. The first is to extract feature points and use them to generate local patches to enable faster computation by learning and using only local patches that are more useful than the surroundings without learning the entire image. Second, learning is performed through deep learning using the convolution neural network structure to improve accuracy by reducing the error rate. Third, unlike the existing feature point matching technique, it enables indoor location measurement including left and right movement. Fourth, since the indoor location is newly measured every frame, errors occurring in the front side during movement are prevented from accumulating. Therefore, it has the advantage that the error between the final arrival point and the predicted indoor location does not increase even if the moving distance increases. As a result of the experiment conducted to evaluate the time required and accuracy of the measurement technique of indoor location based on markerless applicable to AR proposed in this paper, the difference between the actual indoor location and the measured indoor location is an average of 12.8cm and a maximum of 21.2cm. As measured, the indoor location measurement accuracy was better than that of the existing IEEE paper. In addition, it was determined that it was possible to measure the user's indoor location in real time by displaying the measured result at 20 frames per second.

• The Korean Journal of Applied Statistics
• /
• v.34 no.3
• /
• pp.449-460
• /
• 2021

ASVspoof 2017 deals with detection of replay attacks and aims to classify real human voices and fake voices. The spoofed voice refers to the voice that reproduces the original voice by different types of microphones and speakers. data augmentation research on image data has been actively conducted, and several studies have been conducted to attempt data augmentation on voice. However, there are not many attempts to augment data for voice replay attacks, so this paper explores how audio modification through data augmentation techniques affects the detection of replay attacks. A total of 7 data augmentation techniques were applied, and among them, dynamic value change (DVC) and pitch techniques helped improve performance. DVC and pitch showed an improvement of about 8% of the base model EER, and DVC in particular showed noticeable improvement in accuracy in some environments among 57 replay configurations. The greatest increase was achieved in RC53, and DVC led to an approximately 45% improvement in base model accuracy. The high-end recording and playback devices that were previously difficult to detect were well identified. Based on this study, we found that the DVC and pitch data augmentation techniques are helpful in improving performance in the voice spoofing detection problem.

• Journal of the Korea Convergence Society
• /
• v.12 no.8
• /
• pp.295-300
• /
• 2021

Due to the modern appearance management craze to deliver a positive image to others, beauty has been subdivided and diversified based on science and technology, and has established itself as a professional technical profession. As the national technical qualification for makeup cosmetologists is separated from cosmetologists (integrated), it is necessary to analyze the correlation with the job attitude of make-up cosmetologists at industrial sites along with verification of the effectiveness of the practical test task. Therefore, in this study, the first task, wedding (romantic), wedding (classic), hanbok, natural makeup, etc., to investigate the job efficacy and job satisfaction perceived by makeup beauticians due to beauty makeup procedures, such as wedding (romantic), wedding (classic), and after establishing a hypothesis. As a result of the study, it was found that wedding classic makeup and wedding romantic makeup treatment induce job efficacy and job satisfaction, respectively, in makeup artists. This suggests that high saturation and intense color expression have a positive effect on job attitude due to the nature of makeup work. Therefore, based on the results of this study, it is judged that future efforts are needed to update the practical makeup tasks that have doubled the effectiveness and to improve the job attitude of makeup beauticians.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.318-331
• /
• 2022

With the recent development of hardware computing devices and software based frameworks, machine tasks using deep learning networks are expected to be utilized in various industrial fields and personal IoT devices. However, in order to overcome the limitations of high cost device for utilizing the deep learning network and that the user may not receive the results requested when only the machine task results are transmitted from the server, Collaborative Intelligence (CI) proposed the transmission of feature maps as a solution. In this paper, an efficient compression method for feature maps with vast data sizes to support the CI paradigm was analyzed and presented through experiments. This method increases redundancy by applying feature map reordering to improve compression efficiency in traditional video codecs, and proposes a feature map method that improves compression efficiency and maintains the performance of machine tasks by simultaneously utilizing image compression format and video compression format. As a result of the experiment, the proposed method shows 14.29% gain in BD-rate of BPP and mAP compared to the feature compression anchor of MPEG-VCM.

• The Journal of the Korea Contents Association
• /
• v.22 no.3
• /
• pp.152-164
• /
• 2022

This thesis explores the relationship between Dominic Cooke's film (2017) and classical music. To analyze the relationship, researchers applied precedent research to the study. The relationship between the final scene of the movie King's Speech (2010) and the volume and instrumental changes of the Beethoven Symphony is analyzed by David Bashwiner, and Soohwan Ahn analyzed semantic association between the hotel conversation scene in a and Debussy's Arabesque. In addition, the study of application of Schumann's Träumerei to films was used as a methodology to find out how extra-musical information build meaningful sonority. Mozart's K.593, Haydn's Op.77 No.1, and Schubert's D.810 were used in the movie . This study analyzed the functions of Mozart, Haydn, and Schubert's music in . In order to express the relationship between the characters and their inner intentions, this film utilized the relationship between instruments, musical information and non-musical information of the pieces. Through this study, it is analyzed that the information of classical music functions and the core information of the plot of the movie combine together to improve the understanding of narrative.

• Korean Journal of Remote Sensing
• /
• v.38 no.3
• /
• pp.225-236
• /
• 2022

Urbanization due to population growth and regional development can cause various environmental problems, such as the urban heat island phenomenon. A planned city is considered an appropriate study site to analyze changes in urban climate caused by rapid urbanization in a short-term period. In this study, changes in land cover and surface heat island phenomenon were analyzed according to the development plan in Sejong City from 2013 to 2020 using Landsat-8 Operational Land Imager/Thermal Infrared Sensor (OLI/TIRS) satellite imagery. The surface temperature was calculated in consideration of the thermal infrared band value provided by the satellite image and the emissivity, and based on this the surface heat island effect intensity and Urban Thermal Field Variance Index (UTFVI) change analysis were performed. The level-2 land cover map provided by the Ministry of Environment was used to confirm the change in land cover as the development progressed and the difference in the surface heat island intensity by each land cover. As a result of the analysis, it was confirmed that the urbanized area increased by 15% and the vegetation decreased by more than 28%. Expansion and intensification of the heat island phenomenon due to urban development were observed, and it was confirmed that the ecological level of the area where the heat island phenomenon occurred was very low. Therefore, It can suggest the need for a policy to improve the residential environment according to the quantitative change of the thermal environment due to rapid urbanization.

• Journal of the Korean Institute of Rural Architecture
• /
• v.24 no.1
• /
• pp.9-17
• /
• 2022

Rural spaces are increasingly valuable as areas for introducing renewable energy infrastructure to achieve carbon neutrality. Rural areas are the living grounds of rural residents, and the balance of conservation and development for rural areas is important for the introduction of reasonable facilities. In order to maintain a balance between development and preservation and to introduce reasonable renewable energy facilities, it is necessary to develop a current status survey and an effective survey method to utilize a space capable of introducing renewable energy facilities such as idle land and vacant houses. Therefore, this study was conducted to verify the readability using an unmanned aerial vehicle, and the main results are as follows. The detection of photovoltaic power generation facilities using unmanned aerial vehicles was effective in analyzing the location and area of photovoltaic panels located on the roofs of buildings, and it was possible to calculate the expected power generation by region through the area calculation of photovoltaic panels. The vacant house detection can be used to select an investigation target for an vacant house condition survey as it can identify damage to buildings that are expected to be empty houses, management status, and electricity supply facilities through aerial photos. It is judged that the unmanned aerial vehicle detection capability can be utilized as a method to improve the efficiency of investigation and supplement the data related to solar power generation facilities and vacant houses provided by public institutions. Although this study detected the status of solar power generation facilities and vacant houses through high-resolution aerial image analysis, as a follow-up study, automatic measurement methods using the temperature difference of solar power generation facilities and general characteristics of vacant houses that can be read from the air were investigated. If the deriving research is carried out, it is judged that it will be possible to contribute to the improvement of the accuracy of the detection result using the unmanned aerial vehicle and the expansion of the application range.

• Journal of the Korea Society for Simulation
• /
• v.31 no.1
• /
• pp.11-18
• /
• 2022

Recently, research to classify human activity using imagery has been actively conducted for the purpose of crime prevention and facility safety in public places and facilities. In order to improve the performance of human activity classification, most studies have applied deep learning based-transfer learning. However, despite the increase in the number of backbone network models that are the basis of deep learning as well as the diversification of architectures, research on finding a backbone network model suitable for the purpose of operation is insufficient due to the atmosphere of using a certain model. Thus, this study applies the transfer learning into recently developed deep learning backborn network models to build an intelligent system that classifies human activity using imagery. For this, 12 types of active and high-contact human activities based on sports, not basic human behaviors, were determined and 7,200 images were collected. After 20 epochs of transfer learning were equally applied to five backbone network models, we quantitatively analyzed them to find the best backbone network model for human activity classification in terms of learning process and resultant performance. As a result, XceptionNet model demonstrated 0.99 and 0.91 in training and validation accuracy, 0.96 and 0.91 in Top 2 accuracy and average precision, 1,566 sec in train process time and 260.4MB in model memory size. It was confirmed that the performance of XceptionNet was higher than that of other models.

• The Journal of Korean Academy of Prosthodontics
• /
• v.60 no.3
• /
• pp.276-282
• /
• 2022

Close communication between clinicians and dental technicians is an important factor in providing successful prostheses. The exchange of opinions with laboratories has mainly been in the form of written prescriptions and a photos, but it has been reported that information transmission may be limited. Currently, as digital technology-based prosthesis fabrication is common, 3D image objects can be stored on the web and can be easily viewed through a mobile web browser. In this article, we introduce cases where the design of the prosthesis was improved by designing the prosthesis using CAD software and reviewing the prosthesis designed with the clinical side through a web viewer. Through this protocol, it was possible to improve the occlusal surface and crown contour, the opposing teeth condition, the size of the gingival embrasure, and the shape of pontic. The process of sharing, discussing, and modifying the prosthesis design with the clinician and technician through a web viewer contributes to reflecting the diversity of oral conditions and individualized needs, thereby helping to make functional and esthetic prostheses.