• Journal of Korea Multimedia Society
• /
• v.22 no.2
• /
• pp.167-177
• /
• 2019

Even though so much progresses have been achieved in Multiple Object Tracking (MOT), most of reported MOT methods are not still satisfactory for commercial embedded products like Pan-Tilt-Zoom (PTZ) camera. In this paper, we propose a real-time multiple pedestrians tracking method for embedded environments. First, we design a new light weight convolutional neural network(CNN)-based pedestrian detector, which is constructed to detect even small size pedestrians, as well. For further saving of processing time, the designed detector is applied for every other frame, and Kalman filter is employed to predict pedestrians' positions in frames where the designed CNN-based detector is not applied. The pose orientation information is incorporated to enhance object association for tracking pedestrians without further computational cost. Through experiments on Nvidia's embedded computing board, Jetson TX2, it is verified that the designed pedestrian detector detects even small size pedestrians fast and well, compared to many state-of-the-art detectors, and that the proposed tracking method can track pedestrians in real-time and show accuracy performance comparably to performances of many state-of-the-art tracking methods, which do not target for operation in embedded systems.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.205-207
• /
• 2014

This paper uses $Color-x^2$ histogram that is composed of merits of color histogram and ones of histogram, in order to efficiently extract violent scenes in elevator. Also, we use a threshold so as to find out key frame, by use of existing $Color-x^2$ histogram. To increase the probability that discerns whether a real violent scene or not, we take advantage of statistical judgments with 20 sample visual images.

• Journal of the Architectural Institute of Korea Structure & Construction
• /
• v.35 no.10
• /
• pp.143-153
• /
• 2019

In this study, a full scale 3-axes shake table test for M-bar and T-bar type ceilings commonly used in the country was conducted. Through damage inspection during the test, seismic performance of ceilings according to variables, such as clearance between wall mold and ceiling as well as existence of facilities, was evaluated. A test frame consisted of square hollow section members was used for the shake table test. The experimental method was performed as a fragility test using required response spectrum described in ICC-ES AC156. In the case of architectural nonstructural component that contain ceilings, it mainly is evaluated the performance by post-test visual inspection. For the evaluation of seismic performance of ceilings, this study classified and defined damaged items for targeted ceiling system referring to illustrative damage according to nonstructural performance levels accordance with ASCE 41 and previous studies. And proposed illustrative damage items classification was utilized to compare the degree of the damage according to experimental variables. The experiment results confirmed that differences in boundary conditions due to the clearance at wall mold and the installation of facilities had a significant effect on the seismic performance of the ceiling.

• Applied Microscopy
• /
• v.50
• /
• pp.23.1-23.9
• /
• 2020

We propose an effective deep learning model to denoise scanning transmission electron microscopy (STEM) image series, named Noise2Atom, to map images from a source domain 𝓢 to a target domain 𝓒, where 𝓢 is for our noisy experimental dataset, and 𝓒 is for the desired clear atomic images. Noise2Atom uses two external networks to apply additional constraints from the domain knowledge. This model requires no signal prior, no noise model estimation, and no paired training images. The only assumption is that the inputs are acquired with identical experimental configurations. To evaluate the restoration performance of our model, as it is impossible to obtain ground truth for our experimental dataset, we propose consecutive structural similarity (CSS) for image quality assessment, based on the fact that the structures remain much the same as the previous frame(s) within small scan intervals. We demonstrate the superiority of our model by providing evaluation in terms of CSS and visual quality on different experimental datasets.

• International Journal of High-Rise Buildings
• /
• v.11 no.2
• /
• pp.115-124
• /
• 2022

Welding is a significant part of the construction industry. Since most high-rise building construction structures rely on a robust metal frame welded together, welding defect can damage welded structures and is critical to safety and quality. Despite its importance and heavy usage in construction, the labor shortage of welders has been a continuous challenge to the construction industry. To deal with the labor shortage, the ultimate goal of this study is to design and develop an automated robotic welding system composed of a welding machine, unmanned ground vehicle (UGV), robotic arm, and visual sensors. This paper proposes and focuses on automated weaving using the robotic arm. For automated welding operation, a microcontroller is used to control the switch and is added to a welding torch by physically modifying the hardware. Varying weave patterns are mathematically programmed. The automated weaving is tested using a brush pen and a ballpoint pen to clearly see the patterns and detect any changes in vertical forces by the arm during weaving. The results show that the weave patterns have sufficiently high consistency and precision to be used in the actual welding. Lastly, actual welding was performed, and the results are presented.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.25 no.1
• /
• pp.65-81
• /
• 2023

The purpose of this study is to interpret the semantic actions of body image symbolized in body expression images shown by micro-influencers body profiles to understand the body profile phenomenon of the MZ generation. As a result of collecting body profile data from micro-influencers, the body profile image types of female influencers on SNS were classified into four types, Athletic, Slim body, Natural, and, Glamorous. Images representing each type were analyzed using the Roland Barthes' Myth model analysis frame. As a result of the semantic analysis, influencers were found to be very active and bold, emphasizing certain body parts according to the type of body image they pursue. Fashion is strategically used to emphasize these aspects. It was found that the ideology of a 'subjective modern woman' was commonly expressed through emphasis on visual signs. This study is meaningful in that it can indirectly lead to the understanding the fashion culture expressed by the MZ generation and provide consumer information and essential data that can be used for communication strategies in the fashion market.

• Journal of Dental Anesthesia and Pain Medicine
• /
• v.24 no.1
• /
• pp.1-17
• /
• 2024

The video laryngoscope is a novel instrument for intubation that enables indirect visualization of the upper airway. It is recognized for its ability to enhance Cormack-Lehane grades in the management of difficult airways. Notably, video laryngoscopy is associated with equal or higher rates of intubation success within a shorter time frame than direct laryngoscopy. Video laryngoscopy facilitates faster and easier visualization of the glottis and reduces the need for Magill forceps, thereby shortening the intubation time. Despite the advanced glottic visualization afforded by video laryngoscopy, nasotracheal tube insertion and advancement occasionally fail. This is particularly evident during nasotracheal intubation, where oropharyngeal blood or secretions may obstruct the visual field on the monitor, thereby complicating video laryngoscopy. Moreover, the use of Magill forceps is markedly challenging or nearly unfeasible in this context, especially in pediatric cases. Furthermore, the substantial blade size of video laryngoscopes may restrict their applicability in individuals with limited oral apertures. This study aimed to review the literature on video laryngoscopy, discuss its clinical role in nasotracheal intubation, and address the challenges that anesthesiologists may encounter during the intubation process.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.44 no.5
• /
• pp.12-25
• /
• 2016

In this study, in order to facilitate analysis in a continuous sequence, including the concept of the landscape experience time, countless frames of a continuous landscape were extracted. The amount of visual elements in each frame was data-converted numerically to take advantage of the quantitative data necessary for landscape planning and design was calculated in the rhythm of the sequence. In Order to shoot video with the flow of the line of sight of experience in landscape districts and landscape control points along the landscape corridor which is a continuous path, each of the corresponding computer motion techniques. This study developed a CRVP Koo computer program to effectively calculate the continuous visual number of specific landscape components by extracting uncounted frames at regular intervals, and after verifying, attempting to apply this to the target site. Through the applied result, it was possible to extract the digitized quantitative rhythm for each component of each landscape, the margin of error is very small when compared with the results of manual in photoshop, it was able to overcome the drawbacks of the manual. Using the rhythm of the derived sequence, and those close to the experience of the landscape, it was possible to achieve quantitative analysis derived from a variety of perspectives as well as was possible to be used as quantitative basis data and analysis technique for landscape planning and design.

• Journal of Korean Ophthalmic Optics Society
• /
• v.14 no.1
• /
• pp.9-15
• /
• 2009

Purpose: The aim of this study is to examine various national standards and to suggest problems and improvements on KS (Korean Industrial Standards) in spectacle frames. Methods: We surveyed the latest published KS, ISO (International Organization for Standardization), JIS (Japanese Industrial Standards), DIN (Deutsches Institut fur Normung) and ANSI (American National Standards Institute) standards with relating spectacle frames. The titles that were considered in comparative study were terms and vocabulary, measuring system and terminology, marking, requirements and test methods, formers, screw threads, and others. Results: There were 9 different languages such as English (USA and UK), French, Russian, Japanese, Chinese, German, Italian and Spanish for the lists of equivalent terms and vocabulary in all standards except KS and ANSI, but gave an explanation for terms and vocabulary in only KS. Complementary terms and definitions were not existed in annex of KS and ANSI for measuring system and terminology, but they were included in annex of standards of the others. KS and ANSI standard for requirements and test methods differed from the ISO revision. Except JIS and ANSI, standards of formers were almost identical. KS standard of screw threads were similar to JIS. Standards of welded joints and nickel release did not exist in KS. Conclusions: All standards except ANSI tend to follow ISO, especially DIN is almost entirely identical to ISO. But KS is behind the times because it has been amended lately or established in accordance with older editions of ISO. Therefore, in order to assist quality control and safety for spectacle frames, KS standards shall be superseded by the specifications which is identical to ISO within a reasonable time.

• Journal of Digital Convergence
• /
• v.17 no.6
• /
• pp.373-380
• /
• 2019

In this study, I examined the visual elements for narrative structure and the symbols, scene components and visual styles in the images through analyze the flat staging in Tomm Moore's animated feature film, . As a research method, I figure out the general theories about staging and analyze extracted scenes which revealed flat staging in the , then summarize and clarify the flat staging production elements and features of Tomm Moore. As a result, in , the composition of the screen using the basic shapes, the screen composition containing the spiral which is symbol of the Celtic traditional pattern, the stable and flat frame expression through the balanced screen composition, expression of spatial sensation using perspective, appearance of the period by using the inverted perspective, and composition that can emphasize the flat formability are appeared as a characteristic. Through this, the two-dimensional planarity was maximized to convey the feeling of appreciating the illustrations of fairy tales. Tomm Moore, who produced animation based on folk tales in order to inherit the traditional culture of Ireland, has been attracting worldwide attention because of its flat staging to help narrative, enhancing the original expression and performance of animation. I hope that this study will be used as basic data for industry workers and researchers who make unique and excellent animated feature film.