• Journal of Korea Multimedia Society
• /
• v.14 no.4
• /
• pp.481-493
• /
• 2011

As the development of mobile devices, mobile phones are equipped with many features. Video-call feature is one of them. In this paper, we present distance measurement between speaker and smart-phone using multiple color spaces and multiple thresholds. first, detect face based on skin color information. and second, measure distance between speaker and smart-phone using the detected face region. Especially, the first considering point in the development of face area detection is real-time processing and the second point is robustness to solve the problems of face detection errors due to rapid change of object movement, lighting and background between adjacent frames.

• Journal of Korea Multimedia Society
• /
• v.24 no.3
• /
• pp.396-405
• /
• 2021

In surgery to remove pancreatic cancer, it is important to figure out the shape of a patient's pancreas. However, previous studies have a limit to detect a pancreas automatically in abdominal CT images, because the pancreas varies in shape, size and location by patient. Therefore, in this paper, we propose a method of learning various shapes of pancreas according to the patients and adjacent slices using Faster R-CNN based on Inception V2, and automatically detecting the pancreas from abdominal CT images. Model training and testing were performed using the NIH Pancreas-CT Dataset, and intensity normalization was applied to all data to improve pancreatic detection accuracy. Additionally, according to the shape of the pancreas, the test dataset was classified into top, middle, and bottom slices to evaluate the model's performance on each data. The results show that the top data's mAP@.50IoU achieved 91.7% and the bottom data's mAP@.50IoU achieved 95.4%, and the highest performance was the middle data's mAP@.50IoU, 98.5%. Thus, we have confirmed that the model can accurately detect the pancreas in CT images.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.44 no.6
• /
• pp.19-29
• /
• 2007

This paper introduces a robot knowledge framework which is represented with multiple classes, levels and layers to implement robot intelligence at real environment for mobile robot. Our root knowledge framework consists of four classes of knowledge (KClass), axioms, rules, a hierarchy of three knowledge levels (KLevel) and three ontology layers (OLayer). Four KClasses including perception, model, activity and context class. One type of rules are used in a way of unidirectional reasoning. And, the other types of rules are used in a way of bi-directional reasoning. The robot knowledge framework enable a robot to integrate robot knowledge from levels of its own sensor data and primitive behaviors to levels of symbolic data and contextual information regardless of class of knowledge. With the integrated knowledge, a robot can have any queries not only through unidirectional reasoning between two adjacent layers but also through bidirectional reasoning among several layers even with uncertain and partial information. To verify our robot knowledge framework, several experiments are successfully performed for object recognition and navigation.

• Journal of KIISE:Computer Systems and Theory
• /
• v.36 no.6
• /
• pp.476-487
• /
• 2009

The virtual memory system in 4.4 BSD operating systems exploits a clustering scheme to reduce disk I/Os in paging out (or flushing) modified pages that are intended to be replaced in order to make free rooms in memory. Upon the page out of a victim page, the scheme stores a cluster (or group) of modified pages contiguous with the victim in the virtual address space to swap disk at a single disk write. However, it fails to find large clusters of contiguous pages if applications change pages not adjacent with each other in the virtual address space. To address the problem, we propose a new clustering scheme called Multiple-Object Clustering (MOC), which together stores multiple clusters in the virtual address space at a single disk write instead of paging out the clusters to swap space at separate disk I/Os. This multiple-cluster transfer allows the virtual memory system to significantly decrease disk writes, thus improving the page-out performance. Our experiments in the FreeBSD 6.2 show that MOC improves the execution times of realistic benchmarks such as NS2, Scimark2 SOR, and nbench LU over the traditional clustering scheme ranging from 9 to 45%.

• Smart Media Journal
• /
• v.1 no.3
• /
• pp.36-42
• /
• 2012

Recently, the smart applications, such as smart phone and smart TV, become a hot issue in IT consumer markets. In particular, the smart TV provides 3D video services, hence efficient coding methods for 3D video data are required. Three-dimensional (3D) video involves stereoscopic or multi-view images to provide depth experience through 3D display systems. Binocular cues are perceived by rendering proper viewpoint images obtained at slightly different view angles. Since the number of viewpoints of the multi-view video is limited, 3D display devices should generate arbitrary viewpoint images using available adjacent view images. In this paper, after we explain a view synthesis method briefly, we propose a new algorithm to compensate view synthesis errors around object boundaries. We describe a 3D warping technique exploiting the depth map for viewpoint shifting and a hole filling method using multi-view images. Then, we propose an algorithm to remove boundary noises that are generated due to mismatches of object edges in the color and depth images. The proposed method reduces annoying boundary noises near object edges by replacing erroneous textures with alternative textures from the other reference image. Using the proposed method, we can generate perceptually inproved images for 3D video systems.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.44 no.1
• /
• pp.107-118
• /
• 2016

The Seoul metropolitan government announced an open design competition for reconfiguring the annex building of the National Tax Service Building site on Sejong-daero as a space for citizens to commemorate the 70th anniversary of Korea's liberation. The site, built during the Japanese colonial period, has been in use ever since. This study, as one of the entries for the competition, described the strategy and design contents by drawing the concept and main points of the design through an analysis of the historical context of the site. As the guidelines instructed to consider the value of the Sejong-daero area and the cultural heritage through a comprehensive analysis, this study specified the site as a place connecting the past, present and future. Since the foundation of the Joseon dynasty, the Korean Empire and the Japanese colonial period, Sejong-daero has been a main site for important events and activities along with the change of the city structure. Jungdong, to the rear of the site, was a place for adopting new culture during the beginnings of modern Korea, while adjacent places like Duksugung, the Anglican church, and the Seoul City Council building have also been historic urban landscapes of the historical layers of time as the city has changed. When Gojong announced the Korean Empire, the city structure was remodeled with this site as the center along with Sogong-ro, Wongudan and so forth. In this study, public interest stated in the guidelines was focused and the relevance of the road and the plaza was considered from the view of an historic urban landscape by a comprehensive analysis with Sejong-daero as the center. The restoration of public interest was to be drawn as the concept of the object site by considering the current status and the change around the site and Jungdong at the rear. Returning the site to the public is ambiguous with the relevance of the restoration of public interest and as the symbol of the idea of the Korean Empire by Gojong's announcement. The object site, having the characteristic of being returned to the public, must ensure public interest and therefore the design strategy has been established with the keywords of openness, connection and void. As a result of a review of the alternatives, a plan for a square has an 8% slope, just as the original site does, and provides ramps for convenient access for all, including the disabled and the elderly, and is connected to the grounds adjacent. No construction is allowed at the terrace square of the Anglican church level and the main square connected to the pedestrian street, so a variety of modern city utilization can be done. The value of the site at which this design is aimed shall be given back to the public with the concepts of modern democracy, independence, and the vision of Gojong by reinterpreting the space from a modern viewpoint. This study focused on the processes of establishing a main concept and strategy rather than the content of the design details, and the suggestion is meaningful in that the design for the object site with historic backgrounds and the layers of time can continue to be grown.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.30 no.6
• /
• pp.531-539
• /
• 2017

This paper deals with the development of bonded joints for fibre reinforced plastic (FRP) hull structures using moulding-in concept. Focus is placed on bonded in-plane connections between two adjacent panels that could form the boundaries of hull structural module. Traditional construction in FRP hull structures requires the construction of a mould, usually from steel or aluminium. In this construction the FRP materials are laid in the mould, and resin is saturated, and then the structural member is cured. This is expensive since it involves the fabrication of metal hull mould for every different hull type, which is sacrificed after the production of the FRP ship. One way of encouraging greater use of FRP in ship construction is to investigate the possible construction of FRP hull structures in a similar manner to metallic ships, that is in terms of blocks or modules. Such a manner of construction would eliminate the need for expensive hull moulds permitting greater flexibility in the construction of FRP ships. The main issue then would be the design and construction of adequate bonded connections between adjacent panels. To fulfill this object, the simplified and automated way of manufacturing joint edge shapes for bonded joints is developed, and their structural assessment is performed in both experimentally and numerically.

• Korean Journal of Remote Sensing
• /
• v.33 no.6_2
• /
• pp.1151-1157
• /
• 2017

Street Trees is an important object for urban environment improvement. Especially the height of the trees needs to be precisely measured as a factor that greatly influences the removal of air pollutants in the Urban Street Canyons. In this study, we extracted the height of the tree based on the stereo image using the precisely adjusted UAV Images of the target area. The adjustment of UAV image was applied photogrammetric SfM (Structure from motion) based on the collinear condition. We measured the height of the trees on the Street Canyon using stereoscopic vision on stereo plotting system. We also acquired the height of the building adjacent to the street trees and the average height of the road surface was calculated for accurate measurement of the height of each object. Through the visual analysis with the plotting operation system, it was possible to measure height of the tree and to calculate the relative height difference value with building quickly. This means that the height of buildings and trees can be calculated without making a 3D point cloud of UAV and it has the advantage of being able to utilize non-experts. In the future, further studies for semiautomatic/automation of this technique should be performed. The development and research of these technologies is expected to help to understand the current status of environmental policies and roadside trees in urban areas.

• Science of Emotion and Sensibility
• /
• v.18 no.3
• /
• pp.35-48
• /
• 2015

It is frequently found in daily life that people who experience good luck as lottery winners try to improve their background (e.g., home, car) but it has not been empirically validated why they do that. Present research attempts to explore the prediction that people who experience good luck expand the scope of attention to background and those who undergo bad luck shrink the scope of attention to adjacent objects. Findings from Experiment 1a indicate that participants who experienced good luck (won the rock-paper-scissors game) paid more attention to background and performed worse in the "find the hidden picture" (below FHP) task while those who underwent bad luck (lost the rock-paper-scissors game) paid more attention to objects, leading to better performance in the FHP task. It is also found in Experiment 1a that, if people washed their hands after experiencing good or bad luck, the opposite result occurred. Experiment 1b confirmed that the rock-paper-scissor game manipulated good and bad luck successfully and did not influence self-control. Experiment 2 shows that people who strongly believe in good luck performed poorly in FHP task while those who do not believe in good luck performed well in FHP task. Overall, three experiments support the proposed research hypotheses. Implications of the study findings for cognitive psychology and related fields including consumer and sports psychology are discussed.

• Journal of KIISE:Computer Systems and Theory
• /
• v.30 no.12
• /
• pp.756-771
• /
• 2003

Digital Video Library System which manages a large amount of multimedia information requires efficient and effective retrieval methods. In this paper, we propose and implement a new video search and retrieval algorithm that compares the query video shot with the video shots in the archives in terms of foreground object, background image, audio, and its context. The foreground object is the region of the video image that has been changed in the successive frames of the shot, the background image is the remaining region of the video image, and the context is the relationship between the low-level features of the adjacent shots. Comparing these features is a result of reflecting the process of filming a moving picture, and it helps the user to submit a query focused on the desired features of the target video clips easily by adjusting their weights in the comparing process. Although the proposed search and retrieval algorithm could not totally reflect the high level semantics of the submitted query video, it tries to reflect the users' requirements as much as possible by considering the context of video clips and by adjusting its weight in the comparing process.