• Journal of Communication Design
• /
• v.65
• /
• pp.170-181
• /
• 2018

Currently, urban identity is a corporate management strategy of the past, and it includes the unique history and cultural heritage of the region, and it is expected to enhance competitiveness and locality. In response, the city's identity design of 31 municipalities in Gyeonggi Province is moving away from the past, building a futuristic, concise and modern image, and building differentiated identity using geometric artificial motifs. However, despite the presence of urban identity in the past, Symbolmark's boundaries and benchmarks are becoming increasingly ambiguous as it replaces CI or acts as CI and BI by developing new BIs instead of renewals. Moreover, there are cases where the slogan containing vision is used as BI, which requires professional CIP management by presenting the status analysis and direction of municipal governments in Gyeonggi Province. Thus, in this study, the theoretical background analysis and academic study of 31 municipalities in Gyeonggi Province were conducted, and the final analysis space was analyzed by schematizing how the essential meaning of symbolism is expressed and interpreted.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.3
• /
• pp.141-148
• /
• 2021

This paper presents a method to detect zebra-crossing using deep learning which combines SegNet and ResNet. For the blind, a safe crossing system is important to know exactly where the zebra-crossings are. Zebra-crossing detection by deep learning can be a good solution to this problem and robotic vision-based assistive technologies sprung up over the past few years, which focused on specific scene objects using monocular detectors. These traditional methods have achieved significant results with relatively long processing times, and enhanced the zebra-crossing perception to a large extent. However, running all detectors jointly incurs a long latency and becomes computationally prohibitive on wearable embedded systems. In this paper, we propose a model for fast and stable segmentation of zebra-crossing from captured images. The model is improved based on a combination of SegNet and ResNet and consists of three steps. First, the input image is subsampled to extract image features and the convolutional neural network of ResNet is modified to make it the new encoder. Second, through the SegNet original up-sampling network, the abstract features are restored to the original image size. Finally, the method classifies all pixels and calculates the accuracy of each pixel. The experimental results prove the efficiency of the modified semantic segmentation algorithm with a relatively high computing speed.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.3
• /
• pp.577-582
• /
• 2021

Recently, with the development of AR, VR, and smart device technologies, the demand for services based on non-face-to-face environments is also increasing in the fitness industry. The non-face-to-face online home training service has the advantage of not being limited by time and place compared to the existing offline service. However, there are disadvantages including the absence of exercise equipment, difficulty in measuring the amount of exercise and chekcing whether the user maintains an accurate exercise posture or not. In this study, we develop a standard exercise program that can compensate for these shortcomings and propose a new non-face-to-face home training application by using a deep learning-based body posture estimation image processing algorithm. This application allows the user to directly watch and follow the trainer of the standard exercise program video, correct the user's own posture, and perform an accurate exercise. Furthermore, if the results of this study are customized according to their purpose, it will be possible to apply them to performances, films, club activities, and conferences

• Knowledge Management Research
• /
• v.22 no.4
• /
• pp.27-40
• /
• 2021

Click-Through Rate (CTR) prediction is a key function that determines the ranking of candidate items in the recommendation system and recommends high-ranking items to reduce customer information overload and achieve profit maximization through sales promotion. The fields of natural language processing and image classification are achieving remarkable growth through the use of deep neural networks. Recently, a transformer model based on an attention mechanism, differentiated from the mainstream models in the fields of natural language processing and image classification, has been proposed to achieve state-of-the-art in this field. In this study, we present a method for improving the performance of a transformer model for CTR prediction. In order to analyze the effect of discrete and categorical CTR data characteristics different from natural language and image data on performance, experiments on embedding regularization and transformer normalization are performed. According to the experimental results, it was confirmed that the prediction performance of the transformer was significantly improved when the L2 generalization was applied in the embedding process for CTR data input processing and when batch normalization was applied instead of layer normalization, which is the default regularization method, to the transformer model.

• Journal of the Institute of Convergence Signal Processing
• /
• v.22 no.4
• /
• pp.179-184
• /
• 2021

Along with the development of the fourth industry, the public sector has increasingly paid more attention to search using drones and real-time monitoring, for various goals. The drones are used and researched to complete a variety of searching and monitoring missions, including search for missing persons, security, coastal patrol and monitoring, speed enforcement, highway and urban traffic monitoring, fire and wildfire monitoring, monitoring of illegal fishing in reservoirs and protest rally monitoring. Police stations, fire departments and military authorities, however, concentrate on the hardware part, so there are little research on efficient communication systems for the real-time monitoring of data collected from high-performance resolution and infrared thermal imagining cameras, and analysis programs suitable for special missions. In order to increase the efficiency of drones with the searching mission, this paper, therefore, attempts to propose an image analysis technique to increase the precision of search by producing image data suitable for searching missions, based on images obtained from drones and provide the foundation for improving relevant policies and establishing proper platforms, based on actual field cases and experiments.

• Journal of Internet of Things and Convergence
• /
• v.10 no.2
• /
• pp.85-91
• /
• 2024

In this paper, we studied projection mapping, which is being utilized as a digital canvas beyond space and time for theme parks, mega events, and exhibition performances. Since the existing projection technology used for fixed objects has the limitation that it is difficult to map moving objects in terms of utilization, it is urgent to develop a technology that can track and map moving objects and a real-time dynamic projection mapping system based on dynamically moving objects so that it can respond to various markets such as performances, exhibitions, and theme parks. In this paper, we propose a system that can track real-time objects in real time and eliminate the delay phenomenon by developing hardware and performing high-speed image processing. Specifically, we develop a real-time object image analysis and projection focusing control unit, an integrated operating system for a real-time object tracking system, and an image processing library for projection mapping. This research is expected to have a wide range of applications in the technology-intensive industry that utilizes real-time vision machine-based detection technology, as well as in the industry where cutting-edge science and technology are converged and produced.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.28 no.4
• /
• pp.55-61
• /
• 2024

Recently, the number of aging concrete structures is steadily increasing. This is because many of these structures are reaching their expected lifespan. Such structures require accurate inspections and persistent maintenance. Otherwise, their original functions and performance may degrade, potentially leading to safety accidents. Therefore, research on objective inspection technologies using deep learning and computer vision is actively being conducted. High-resolution images can accurately observe not only micro cracks but also spalling and exposed rebar, and deep learning enables automated detection. High detection performance in deep learning is only guaranteed with diverse and numerous training datasets. However, surface damage to concrete is not commonly captured in images, resulting in a lack of training data. To overcome this limitation, this study proposed a method for generating concrete surface damage images, including cracks, spalling, and exposed rebar, using stable diffusion. This method synthesizes new damage images by paired text and image data. For this purpose, a training dataset of 678 images was secured, and fine-tuning was performed through low-rank adaptation. The quality of the generated images was compared according to three base models of stable diffusion. As a result, a method to synthesize the most diverse and high-quality concrete damage images was developed. This research is expected to address the issue of data scarcity and contribute to improving the accuracy of deep learning-based damage detection algorithms in the future.

• The KIPS Transactions:PartB
• /
• v.14B no.4
• /
• pp.311-320
• /
• 2007

This paper presents vision-based 3D facial expression animation technique and system which provide the robust 3D head pose estimation and real-time facial expression control. Many researches of 3D face animation have been done for the facial expression control itself rather than focusing on 3D head motion tracking. However, the head motion tracking is one of critical issues to be solved for developing realistic facial animation. In this research, we developed an integrated animation system that includes 3D head motion tracking and facial expression control at the same time. The proposed system consists of three major phases: face detection, 3D head motion tracking, and facial expression control. For face detection, with the non-parametric HT skin color model and template matching, we can detect the facial region efficiently from video frame. For 3D head motion tracking, we exploit the cylindrical head model that is projected to the initial head motion template. Given an initial reference template of the face image and the corresponding head motion, the cylindrical head model is created and the foil head motion is traced based on the optical flow method. For the facial expression cloning we utilize the feature-based method, The major facial feature points are detected by the geometry of information of the face with template matching and traced by optical flow. Since the locations of varying feature points are composed of head motion and facial expression information, the animation parameters which describe the variation of the facial features are acquired from geometrically transformed frontal head pose image. Finally, the facial expression cloning is done by two fitting process. The control points of the 3D model are varied applying the animation parameters to the face model, and the non-feature points around the control points are changed by use of Radial Basis Function(RBF). From the experiment, we can prove that the developed vision-based animation system can create realistic facial animation with robust head pose estimation and facial variation from input video image.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.49 no.4
• /
• pp.64-73
• /
• 2021

The purpose of this study is to present a method to assess the landscape aesthetic value of Bukhansan National Park using geotagged images that have been shared on social media sites. The method presented in this study consisted mainly of collecting geotagged image data, identifying landscape images, and analyzing the cumulative visibility by applying a target probability index. Ramblr is an application that supports outdoor activities with many users in Korea, from which a total of 110,954 geotagged images for Bukhansan National Park were collected and used to assess the landscape aesthetics. The collected geotagged images were interpreted using the Google Vision API, and were subsequently were divided into 11 landscape image types and 9 non-landscape image types through cluster analysis. As a result of analyzing the landscape types of Bukhansan National Park based on the extracted landscape images, landscape types related to topographical characteristics, such as peaks and mountain ranges, accounted for the largest portion, and forest landscapes, foliage landscapes, and waterscapes were also commonly found as major landscape types. In the derived landscape aesthetic value map, the higher the elevation and slope, the higher the overall landscape aesthetic value, according to the proportion and characteristics of these major landscape types. However, high landscape aesthetic values were also confirmed in some areas of lowlands with gentle slopes. In addition, the Bukhansan area was evaluated to have higher landscape aesthetics than the Dobongsan area. Despite the high elevation and slope, the Dobongsan area had a relatively low landscape aesthetic value. This shows that the aesthetic value of the landscape is strongly related not only to the physical environment but also to the recreational activities of visitors who are viewing the scenery. In this way, the landscape aesthetics assessment using the cumulative visibility of geotagged images is expected to be useful for planning and managing the landscape of Bukhansan National Park in the future, through allowing the geographical understanding of the landscape values based on people's perceptions and the identification of the regional deviations.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.6
• /
• pp.18-26
• /
• 2011

Debates concerning the competitive edge of leading 3DTV technology of the shutter glasses (SG) 3D and the film-type patterned retarder (FPR) are flaring up. Although SG technology enables Full-HD 3D vision, it requires complex systems including the sync transmitter (emitter), the sync processor chip, and the LCD lens in the active shutter glasses. In addition, the transferred sync-signal is easily affected by the external noise and a 3DTV viewer may feel flicker-effect caused by cross-talk of the left and right image. The operating current of the sync processor in the 3DTV active shutter glasses is gradually increasing to compensate the sync reconstruction error. The proposed chip is a low-power hardware sync processor based discrete-event SoC(system on a chip) designed specifically for the 3DTV active shutter glasses. This processor implements the newly designed power-saving techniques targeted for low-power operation in a noisy environment between 3DTV and the active shutter glasses. This design includes a hardware pre-processor based on a universal edge tracer and provides a perfect sync reconstruction based on a floating-point timer to advance the prior commercial 3DTV shutter glasses in terms of their power consumption. These two techniques enable an accurate sync reconstruction in the slow clock frequency of the synchronization timer and reduce the power consumption to less than about a maximum of 20% compared with other major commercial processors. This article describes the system's architecture and the details of the proposed techniques, also identifying the key concepts and functions.