• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.7
• /
• pp.1348-1353
• /
• 2007

We developed an augmented new reality tool for vision-based hand gesture recognition in a camera-projector system. Our recognition method uses modified Fourier descriptors for the classification of static hand gestures. Hand segmentation is based on a background subtraction method, which is improved to handle background changes. Most of the recognition methods are trained and tested by the same service-person, and training phase occurs only preceding the interaction. However, there are numerous situations when several untrained users would like to use gestures for the interaction. In our new practical approach the correction of faulty detected gestures is done during the recognition itself. Our main result is the quick on-line adaptation to the gestures of a new user to achieve user-independent gesture recognition.

• Smart Media Journal
• /
• v.11 no.9
• /
• pp.81-93
• /
• 2022

In an era where non-face-to-face meetings become common, eXtended Reality(XR) is rapidly developing and filling areas that are not satisfied in online meetings based on existing photos/video method. In particular, general users are also able to easily access and use HMD-type mixed reality devices. However, the basic operations applied in HMD-type in Mixed Reality(MR) with hands as the main input tool do not have a standardized system, and each manufacturer operates in a separate response to each other's hand movements. Therefore, this study considered that a systematic hand motion matching system considering the usability and efficiency of operations performed in mixed reality was necessary, and conducted a study to clarify this. First, the basic operation performed in the MR environment and its attributes were investigated, and at the same time, the structure of the hand and the attributes of the possible hand movements were identified. Based on the identified properties, it is intended to present a system that can intuitively and efficiently match basic operation properties in the MR environment with subtle operation properties according to the structure/context of the hand.

• Journal of the Institute of Convergence Signal Processing
• /
• v.15 no.2
• /
• pp.42-47
• /
• 2014

A finger-gesture game controller using the single camera is implemented in this paper, which is based on the recognition of the number of fingers and the index finger moving direction. Proposed method uses the CAMShift algorithm to trace the end-point of index finger effectively. The number of finger is recognized by using a double circle tracing method. Then, HSI color mode transformation is performed for the CAMShift algorithm, and YCbCr color model is used in the double circle tracing method. Also, all processing tasks are implemented by using the Intel OpenCV library and C++ language. In order to evaluate the performance of the proposed method, we developed a shooting game simulator and validated the proposed method. The proposed method showed the average recognition ratio of more than 90% for each of the game command-mode.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.04a
• /
• pp.1022-1024
• /
• 2015

휴먼-컴퓨터 인터렉션과 같은 응용분야에서 손동작 인식을 위한 많은 연구가 이루어지고 있다. 손동작 인식을 이용한 인터렉션의 성능 향상을 위해서는 정확한 손 영역 검출이 필요하다. 본 논문에서는 색상 정보를 이용하여 Cascade 방식에 기반한 손 영역 검출 방법을 제안한다. Cascade 방식으로 손 영역을 검출할 경우보다 강인한 인식률을 얻기 위해서 색상정보를 이용하였으며, Haar-like 특징점으로 학습된 분류기를 통해 손 영역 검출 방법을 제안한다.

• Journal of Korea Game Society
• /
• v.6 no.2
• /
• pp.3-12
• /
• 2006

Recently, Many 3D augmented reality games that provide strengthened immersive have appeared in the 3D game environment. In this article, we describe a barehanded interaction method based on human hand gestures for augmented reality games. First, feature points are extracted from input video streams. Point features are tracked and motion of moving objects are computed. The shape of the motion trajectories are used to determine whether the motion is intended gestures. A long smooth trajectory toward one of virtual objects or menus is classified as an intended gesture and the corresponding action is invoked. To prove the validity of the proposed method, we implemented two simple augmented reality applications: a gesture-based music player and a virtual basketball game. In the music player, several menu icons are displayed on the top of the screen and an user can activate a menu by hand gestures. In the virtual basketball game, a virtual ball is bouncing in a virtual cube space and the real video stream is shown in the background. An user can hit the virtual ball with his hand gestures. From the experiments for three untrained users, it is shown that the accuracy of menu activation according to the intended gestures is 94% for normal speed gestures and 84% for fast and abrupt gestures.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.11a
• /
• pp.146-147
• /
• 2016

손동작 인식은 대부분 스킨 컬러 검출을 이용하였다. 하지만 이와 같은 방법으로는 빛이나 주변 사물에 의해 영향을 많이 받기 때문에 정확한 값을 일정하게 도출 해낼 수 없었다. 이에 본 논문은 운동축적 기법을 이용하여 움직임을 파악한 후 손의 움직임을 트랙킹하여 운동 방향을 구한다. 제안된 시스템은 C/C++을 기반으로 구현하여, 실험에서 제안 방법이 안정적이고 우수한 성능을 보여줌을 증명하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1679-1680
• /
• 2015

본 논문에서는 Depth 카메라를 이용하여 검지 끝을 인식하고 공간 터치 손 제스처를 인식하는 방법에 대해 제안한다. 제안된 방법은 손의 형태학적으로 엄지 끝을 추정하고 보정하는 방법을 제안하고, 추정된 검지와 엄지 끝의 위치를 이용해 마우스 이동, 클릭을 구현하여 문자 입력 시스템에 적용하였다. 제안된 방법을 실험하기 위하여 실제 디스플레이와 Depth 카메라를 하드웨어적으로 구성하고 마우스 기반 콘텐츠를 제작하여 이용하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.415-417
• /
• 2020

무형문화유산의 전수 방식은 장인과 이수자의 직접적인 교육으로만 이루어져 왔으며 또한 전수는 긴 시간 동안 이루어지고 전수 방식을 따로 기록하는 경우가 드물며 동작이나 구전으로만 전해지기 때문에 표준화된 전수는 이루어질 수 없었다. 현재 국제 유네스코와 국내문화재청에서는 유무형문화재에 대한 전수와 기록의 중요성을 알고 다양한 디지털 기록을 진행하고 있다. 하지만 4차 산업혁명 시대에 무형유산 기록화 기술은 보유자의 기 예능 장인 공법을 기록하는 부분으로 영상기록 및 사진기록 도서 음원 등 아직까지 기존 아날로그 기술 방법으로 기록이 이루어지고 있으며 최근 5G 상용화와 함께 디지털 4차 산업 혁명시대와 발맞춰 무형유산 정보관리 기관에서도 무형유산 ICT 기반 기술 지원을 활성화되고 있는 시점에서 본 연구는 오랜 시간 동안 숙련도 높은 기술공법으로 한국 전통문화의 맥을 이어가고 있는 무형문화재 장인들의 기술 중에서 손을 사용하는 바느질 중심으로 자이로센서 기반으로 정확한 손동작 정보를 획득하고 기록할 수 있는 시스템 설계 및 연구개발을 통하여 ICT 기반 장인 공법 4D 기록화 기술을 제시하고자 한다. 이와 같은 기술로 무형문화유산의 새로운 4D 기록 방법으로 정확하게 기록하고 보존하여 무형문화유산 전승과 교육을 할 수 있고 문화유산의 유형에 맞는 교육·산업·홍보 등 다양한 사용 목적에 맞는 형태로 폭넓게 사용될 수 있다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.22 no.3
• /
• pp.1-11
• /
• 2017

There is a Growing Interest in Motion Recognition for Recognizing Human Motion in Camera Images. As a Result, Researches are Being Actively Conducted to Control Digital Devices with Gestures at a Long Distance. The Interface Using Gesture can be Effectively Used in the Digital Signage Industry Where the Advertisement Effect is Expected to be Exposed to the Public in Various Places. Since the Digital Signage Contents can be Easily Controlled through the Non-contact Hand Operation, it is Possible to Provide the Advertisement Information of Interest to a Large Number of People, Thereby Providing an Opportunity to Lead to Sales. Therefore, we Propose a Digital Signage Content Control System Based on Hand Movement at a Certain Distance, which can be Effectively Used for the Development of Interactive Advertizing Media.

• Smart Media Journal
• /
• v.6 no.2
• /
• pp.26-32
• /
• 2017

In this paper, we implement a signal-detecting electric circuit based LED lighting control system which is essential in NUI technology using EPIC converting surrounding earth electric field disturbance signals to electric potential signals. We used signal-detecting electric circuits which was developed to extract individual signal for each EPIC sensor while conventional EPIC-based development equipments provide limited forms of signals. The signals extracted from our developed circuit contributed to better performance as well as flexiblity in processes of feature extracting stage and pattern recognition stage. We designed a system which can control the brightness and on/off of LED lights with four hand gestures in order to justify its applicability to real application systems. We obtained faster pattern classification speed not only by developing an instruction system, but also by using interface control signals.