• Journal of Korea Game Society
• /
• v.13 no.3
• /
• pp.77-84
• /
• 2013

We introduce a new framework for making spatial augmented reality contents fast and with low cost. The framework allows us to make projection-based augmented reality using off-the-shelf webcams and projectors. Contents producers can make a projection-based augmented reality contents easy and fast by setting a webcam and a projector and then controlling user interfaces of our framework. Since most of previous solutions are expensive and it is too difficult that the producers apply augmented reality techniques themselves, the framework helps them to concentrate contents. Once we set a webcam and a projector correctly, our framework projects a virtual object contents according to the manipulation of a trackable real object. As a result we can see realistic augmented reality contents.

• Journal of Korea Game Society
• /
• v.11 no.1
• /
• pp.147-157
• /
• 2011

Webcam doesn't perform memory-alignment in order to reduce the transmission time of image data. Memory-unaligned image data is unsuitable for the processing on GPU. Accordingly, we convert it to available color format for optimization in high speed image processing. In this paper, we propose a technique that accelerates webcam's color format conversion by using NVDIA CUDA. We propose an optimization which is about memory accesses and thread composition, also evaluate memory and computing performance for verifying a hypothesis which is the performance of the proposed architecture and optimizing degree on low-performance GPU. Following the optimization technique, we show performance improvements over maximum 68 percent.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.1
• /
• pp.66-71
• /
• 2008

Recent multimedia technology has supported various application services based on the development of effective movie compression and network techniques. On-line video conference system is a typical example that use theses two technologies effectively. On-line video conference system can be characterized into an effective conferencing method for long-distanced on-line conference members. But, unfortunately, off-line conference with face-to-face meeting is more frequent than on-line conference and their support systems have not been sufficiently considered. In this paper, we propose a recording support system for off-Line conference using face and speaker recognition. This system finds the speaker in the conference by using three microphones and three webcam cameras. And analysis is done with face region information that gathered by currently active webcam camera, and recognizes the identity of face. Finally, the system tracks speaker and records conference with extract speaker information.

• Korean Journal of Oriental Medicine
• /
• v.17 no.2
• /
• pp.115-120
• /
• 2011

Objectives : The purpose of this study is to develop an apparatus which can take a facial image by self-operated capturing technique. The user can obtain one's facial image immediately after adjusting facial tilt and focusing distance. The system has been designed for classifying Sasang typology based on facial image. Methods : The system is composed of a Webcam, one-way glass mirror and mini LCD. The Webcam takes a facial image which is displayed on the mini LCD. Then the user can see and adjust to the right position in the real time through the image mirror-reflected from the mini LCD. The optical sensor is used to estimate the proper focusing distance. To verify the performance of the system, 11 characteristic points on the facial image are used and compared with high performance DSLR camera(D700) by applying the coefficient of variance and Bland-Altman Plot. Results : The developed system and D700 show enough agreement with the small coefficient of variance to analyse constitutional types with a facial im mage. However, the result of Bland-Altman plot shows that the width parameters have distortions owing to short focusing distance. Conclusions : The system is expected to be utilized on u-healthcare services for home environment after improving the distortion in the width parameters.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.413-415
• /
• 2019

In this paper, we develop IoT-HiAS(IoT-Human Interactive Advertising Service) for sharing economy. The HiAS device shooting the front of the device via a webcam and recognizes the person in real time through the SSD model using MobileNet. If the number of persons above the set threshold is recognized by counting the recognized person, the advertisement is reproduced on the idle resource through the beam projector. At the same time as the advertisement is reproduced, the captured image of the advertisement start time in the front of the device and the number of recognized persons are sends the IoT server of an oneM2M-compliant HiAS server using the IoT client. When the advertisement is finish, the webcam is shooting the front of the device and the image is sends the IoT server. We implemented the IoT-based human interactive advertising service by transmitting the received data to the advertiser and the advertising producers through the SNS(Social Network Service) agent of the HiAS server.

• Journal of International Academy of Physical Therapy Research
• /
• v.12 no.1
• /
• pp.2261-2266
• /
• 2021

Background: Deep learning related research works on website medical images have been actively conducted in the field of health care, however, articles related to the musculoskeletal system have been introduced insufficiently, deep learning-based studies on classifying orthopedic manual therapy images would also just be entered. Objectives: To create a deep learning model that categorizes cervical mobilization images and establish a web application to find out its clinical utility. Design: Research and development. Methods: Three types of cervical mobilization images (central posteroanterior (CPA) mobilization, unilateral posteroanterior (UPA) mobilization, and anteroposterior (AP) mobilization) were obtained using functions of 'Download All Images' and a web crawler. Unnecessary images were filtered from 'Auslogics Duplicate File Finder' to obtain the final 144 data (CPA=62, UPA=46, AP=36). Training classified into 3 classes was conducted in Teachable Machine. The next procedures, the trained model source was uploaded to the web application cloud integrated development environment (https://ide.goorm.io/) and the frame was built. The trained model was tested in three environments: Teachable Machine File Upload (TMFU), Teachable Machine Webcam (TMW), and Web Service webcam (WSW). Results: In three environments (TMFU, TMW, WSW), the accuracy of CPA mobilization images was 81-96%. The accuracy of the UPA mobilization image was 43~94%, and the accuracy deviation was greater than that of CPA. The accuracy of the AP mobilization image was 65-75%, and the deviation was not large compared to the other groups. In the three environments, the average accuracy of CPA was 92%, and the accuracy of UPA and AP was similar up to 70%. Conclusion: This study suggests that training of images of orthopedic manual therapy using machine learning open software is possible, and that web applications made using this training model can be used clinically.

• Proceedings of The KACE
• /
• 2017.08a
• /
• pp.121-124
• /
• 2017

초등 교육과정에 소프트웨어 교육 내용이 포함되는 2015 개정 교육과정의 시행을 앞두고, 학교 현장의 교사들은 이에 대한 지도 준비 수준이 낮으며 소프트웨어 교육 관련 교수 학습 자료도 부족하다고 느끼고 있었다. 이에 본 논문에서는 체험을 주 내용으로 하는 초등학교 프로그래밍 영역에 활용이 가능한 웹캠 기반 스크래치 프로그래밍 교육 콘텐츠를 개발하였다. 이 때 프로그래밍 흥미를 높일 수 있는 방법으로 웹캠을 사용하여 사용자의 움직임과 상호작용이 가능한 콘텐츠를 제작하였으며 총 10차시로 구성하였다. 추후 본 논문에서 제안한 교육 콘텐츠를 초등학생들에게 적용하여 교육적 효과를 검토할 것이다.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.3 no.3
• /
• pp.151-157
• /
• 2008

In this paper, we propose a three dimensional distance measurement method for a stereo system by using web cams. Using a parallel stereo system, a robot gets two images from each webcam and equalize brightness of both images. And we suggest an image processing method such as labeling, isolating an object from background and finding center of an object. We also propose a method of calculating the focal distance by using least square algorithm based on triangulation and we can reduce calculation error by this method. From experimental results, we show that the proposed method can be effective for 3D distance measurement.

• Proceedings of the KIEE Conference
• /
• 2015.07a
• /
• pp.1419-1420
• /
• 2015

본 연구는 무구속 신장측정 기초연구로 웹캠을 기반으로 한 무구속 신장측정 시스템을 모델링하고 실험을 통해 가능성을 평가한다. 시스템 모델링은 웹캠의 수직화각, 피사체까지의 거리, 웹캠의 높이, 웹캠 해상도 등을 고려하여 수행되었다. 개발된 모델의 정확도는 실제높이를 마커로 표시하고, 획득된 영상에서 마커를 추출한 뒤 실제높이를 추정하는 방법으로 평가 되었다. 실험에서 마커는 150 cm부터 200 cm까지 5 cm 간격으로 위치하였다. 결과적으로 영상기반으로 추정된 높이는 실제 높이를 과추정(over-estimated)하며, 높이에 따라 -4.5% ~ -1.6%의 오차율을 가지는 것으로 나타났다. 하지만, 오차율이 높이와 일관된 비례양상을 보여 보상 파라미터를 통해 정확도를 향상시킬 수 있는 가능성을 보였다.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2009.10a
• /
• pp.1228-1231
• /
• 2009

This paper presented an automatic system for display quality measurement by image processing. The goal is to replace human eyes for display quality evaluation by computer vision and get the objective quality review for consumer to make purchase of monitor or TV. Color, contrast, brightness, sharpness and motion blur are the main five factors to affect display quality that could be measured by supplying patterns and analyzing the corresponding images captured from webcam. The scores are calculated by image processing techniques. Linear regression model is then adopted to find the relation between human score and the measured display performance.