• Journal of Broadcast Engineering
• /
• v.21 no.5
• /
• pp.782-791
• /
• 2016

The object segmentation algorithm from the background could be used for object recognition and tracking, and many applications. To segment objects, this paper proposes a method that refer to several initial frames with real-time processing at fixed camera. First we suggest the probability model to segment object and background and we enhance the performance of algorithm analyzing the color consistency and focus characteristic of camera for several initial frames. We compensate the segmentation result by using human skeleton characteristic among extracted objects. Last the proposed method has the applicability for various mobile application as we minimize computing complexity for real-time video processing.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1416-1419
• /
• 2015

최근 건강에 대한 일반인들의 관심이 증가하면서 스마트 헬스케어 시장 규모가 기하급수적으로 커지고 있다. 특히 탈모 관련 헬스케어 시장의 경우, 국내 탈모 인구의 증가로 인해 탈모의 예방이나 관리 등 탈모 관련 어플리케이션이 빠르게 등장하고 있다. 모발 밀도는 탈모의 정도를 판단하기 위한 가장 기본적인 모발 특징 중 하나이지만, 모발의 밀도를 측정하기 위한 명확한 영상처리 기법이나 소프트웨어의 개발은 여전히 미진한 상태이다. 이에 본 논문에서는 스마트폰에 탈부착이 가능한 포터블 카메라에서 촬영된 두피 모발 현미경 영상에서 모발의 밀도를 측정하고 이를 기반으로 사용자 중심의 탈모 진단 플랫폼을 구축하고자 한다. 모발 밀도의 측정은 Contrast Stretching과 Morphology Processing을 이용한 전처리, 스켈레톤 이미지의 변환, 그리고 라인 끝점 검색 알고리즘의 적용 등 크게 세 단계로 진행된다. 제안하는 기법의 성능 평가를 위해, 50배율 포터블 카메라로 촬영한 두피 영상 30개에 대해 밀도 측정을 수행하였으며 그 결과 92.88%의 정확도를 얻었다. 결과적으로 제안하는 기법은 단순 두피 현미경 영상으로 탈모의 지표가 될 수 있는 모발 밀도를 측정하는 데 충분히 효과적임을 알 수 있다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.479-480
• /
• 2023

현대 사회는 출생아가 줄어들고 고령화 현상이 빠르게 진행 중이다. 20~30대의 사회 복지 종사자가 줄어들고 노인 인구는 늘어나는 반비례 현상이 나타나고 있다. 보호자가 없는 노인에게 낙상 사고와 같은 위급상황이 발생한다면 골든타임을 놓칠 수도 있을 것이다. 따라서, 본 논문에서는 낙상 사고 발생 시, 빠른 시간 내에 실시간 모니터링을 통해 노인 복지사가 상황을 인지할 수 있게 하는 시스템을 개발하였다. 미디어파이프 포즈 모델을 이용하여 관찰 대상의 움직임을 포착하도록 하였고 PTZ 카메라의 서보 모터 제어를 통해 포착한 관찰 대상을 추적하도록 하였다. 주요 장면은 사진으로 저장해 웹 서버로 전송하고, 심박수 측정 센서와 와이파이 통신 모듈이 장착된 아두이노 보드가 실시간으로 웹 서버로 전송하여, 전담 관리자는 사진을 통해 상황을 인식하고 심박수를 보고 얼마나 위급한지 알 수 있도록 하였다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.6
• /
• pp.89-95
• /
• 2023

In recent decades, human action recognition (HAR) has demonstrated potential applications in sports analysis, human-robot interaction, and large-scale signage content. In this paper, spatial temporal attention graph convolutional network (STAGCN)-based HAR system is proposed. Spatioal-temmporal features of skeleton sequences are assigned different weights by STAGCN, enabling the consideration of key joints and viewpoints. From simulation results, it has been shown that the performance of the proposed model can be improved in terms of classification accuracy in the NTU RGB+D dataset.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.9
• /
• pp.53-62
• /
• 2020

Product recommendation services that have been researched recently are only recommended through the customer's product purchase history. In this paper, we propose the digital signage service through customers' behavior pattern analysis that is recommending through not only purchase history, but also behavior pattern that customers take when choosing products. This service analyzes customer behavior patterns and extracts interests about products that are of practical interest. The service is learning extracted interest rate and customers' purchase history through the Wide & Deep model. Based on this learning method, the sparse vector of other products is predicted through the MF(Matrix Factorization). After derive the ranking of predicted product interest rate, this service uses the indoor signage that can interact with customers to expose the suitable advertisements. Through this proposed service, not only online, but also in an offline environment, it would be possible to grasp customers' interest information. Also, it will create a satisfactory purchasing environment by providing suitable advertisements to customers, not advertisements that advertisers randomly expose.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.6
• /
• pp.1183-1188
• /
• 2016

Kinect sensor version 2 is a kind of camera released by Microsoft as a computer vision and a natural user interface for game consoles like Xbox one. It allows acquiring color images, depth images, audio input and skeletal data with a high frame rate. In this paper, using depth image, we present a surveillance system of a certain area within Kinect's field of view. With computer vision library(Emgu CV), if an object is detected in the target area, it is tracked and kinect camera takes RGB image to send it in database server. Therefore, a mobile application on android platform was developed in order to notify the user that Kinect has sensed strange motion in the target region and display the RGB image of the scene. User gets the notification in real-time to react in the best way in the case of valuable things in monitored area or other cases related to a reserved zone.

• The Journal of the Korea Contents Association
• /
• v.5 no.3
• /
• pp.133-140
• /
• 2005

It is important matter to develop game that language should consider improving game development environment. It is hardly any language that is designed to develop a game. Most developer used general purpose programming language in these situations, and directly modeling with engine. For this reasons, developers cannot easily develop games and must programming on engine level. It is hard to develop a game in this environment that was not able to understand an engine well. Moreover, developer and planner want to use an abstracted high-level language on planner phase and are going to easily develop a game. It was not have communication tool between developer and planner. Therefore, we defined a script language for modeling based on abstract engine level. In addition, we did build IDE to develop game using abstracted high-level language. It was able to develop a game on high-speed development environment. Therefore, developer does not must develop with engine phase but can develop a game with planners. In addition, game planner and developer can use a communication tool because it is able to develop skeleton game.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.19 no.4
• /
• pp.35-42
• /
• 2015

This study analytically reviewed the behavior of Steel Plate Concrete(SC) walls subjected to cyclic loads to investigate the effects of shape and arrangement spacing of studs on the behavior of SC walls. To perform it, 9 cases of finite element analyses considering the different shape and spacing of studs in SC wall were carried out. As the results, the skeleton curves were obtained from the load-displacement history curves and the ultimate and yielding forces were increased as the spacing of studs decrease. In addition, the strength of inclined studs are shown to be bigger compared to that of general studs. The damping ratios are increased as the decrease of strength ratio. Finally, as the decrease of stud spacings, the cumulative dissipated energy was increased and the seismic performance was improved.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.5
• /
• pp.53-60
• /
• 2013

This paper proposed visualization tool for motion of snowboarding using Skeleton data obtained by the Microsoft's Kinect sensor. The BBP(Balanced Body Position) posture is a most basic motion in the Snowboarding. This posture is the primary technology for stable turns. The implementation of visualization tool to analyse the BBP posture of snowboard. comparative analysis with standard postures to the ankles, knees, hips and spine angle of joints and body tracking using coordinate information obtained by the Kinect Sensor. Analysis of the final results of the screen through the OpenGL library. This research result could be used to analysis for turn postures of snowboarding.

• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.35 no.7
• /
• pp.45-52
• /
• 2019

In recent years, there has been a demand for a residential supply model that can actively and flexibly cope with various housing demands in the changing paradigm of public rental housing. This study focuses on the two-step supply system that has been studied in Japan. It was used to examine and analyze cases to recommend a supply plan that can be used for domestic public rental housing. In more detail, the literature review of the two-step supply system discloses that four types by supply methods (A-1, A-2, B-2, and C-2) and four types of relationship (construction and management combine entities type, management entity type, construction entity type, a separated entity type) can be categorized. In addition, from the actual case study, it revealed that the way of linking and supplying activities among the entity can have a great influence on "ease of supply (supply)", "diversity of housing demand (diversity)," and "quality of construction (construction)". "Ease of supply (supply)" refers to whether the construction entity is separated, and the owner is a manager. "Diversity" refers to whether the management subject is separated, and if the owner is also the constructor or the manager. "Construction" is whether the management entity is connected and managed by the management entity and can be evaluated in "Good", "Middle", and "Bad" level. As a summary, even if the existing public rental housing in Korea can be separated into a skeleton and infill system, the result suggested that it has a limitation on response to residential demand. In addition, the paper was able to propose an improved plan to make the infill as a secondary operator.