• International Journal of Internet, Broadcasting and Communication
• /
• 제12권3호
• /
• pp.171-176
• /
• 2020

This paper presents an implementation of a gesture recognition platform that can be used in a factory workplaces. The platform consists of signages that display worker's job orders and a control center that is used to manage work orders for factory workers. Each worker does not need to bring work order documents and can browse the assigned work orders on the signage at his/her workplace. The contents of signage can be controlled by worker's hand and arm gestures. Gestures are extracted from body movement tracked by 3D depth camera and converted to the commandsthat control displayed content of the signage. Using the control center, the factory manager can assign tasks to each worker, upload work order documents to the system, and see each worker's progress. The implementation has been applied experimentally to a machining factory workplace. This flatform provides convenience for factory workers when they are working at workplaces, improves security of techincal documents, but can also be used to build smart factories.

• 한국멀티미디어학회논문지
• /
• 제10권8호
• /
• pp.981-996
• /
• 2007

본 논문에서는 연속적인 제스처 영상으로 부터 주 인자 분석을 통해 얻어진 동작 특징 정보를 이용하여 제스처를 인식하는 방법에 대해 기술한다. 제안된 방법은 먼저, 인간의 신체 영상이 포함된 연속적인 입력영상에서 2차원 실루엣 제스처 영역을 분할한 다음 전역특징정보와 지역특징정보를 추출한다. 여기서 전역특징정보는 요인 분석을 통하여 제스처를 효과적으로 표현하는 의미 있는 소수의 핵심 특징을 선택하여 이용한다. 추출 된 특징정보로 부터 제스처의 시간 변화를 나타내는 특징히스토리정보를 얻어 저 차원 제스처공간을 구성한다. 마지막으로 제스처 공간상에 투영된 모델 특징 값은 은닉마르코프 모델의 입력 기호로 이용되기 위해 군집화 알고리즘을 통해 특정한 상태 기호로 구성되며 임의의 입력 동작은 확률 값이 가장 높은 해당 제스처 모델로 인식된다. 주 인자 분석으로부터 제스처에 기여도가 높은 특징인자로 모델을 구성하기 때문에 외관기반방법에서 몸의 형상 정보만을 특징 값으로 이용하거나 직관적인 방법으로 특징을 추출하는 방법보다 복잡한 동작에서 비교적 우수한 인식률을 나타낸다.

• 제어로봇시스템학회논문지
• /
• 제13권9호
• /
• pp.832-837
• /
• 2007

Electroencephalographic(EEG) is used to record activities of human brain in the area of psychology for many years. As technology develope, neural basis of functional areas of emotion processing is revealed gradually. So we measure fundamental areas of human brain that controls emotion of human by using EEG. Hands gestures such as shaking and head gesture such as nodding are often used as human body languages for communication with each other, and their recognition is important that it is a useful communication medium between human and computers. Research methods about gesture recognition are used of computer vision. Many researchers study Emotion Recognition method which uses one of EEG signals and Gestures in the existing research. In this paper, we use together EEG signals and Gestures for Emotion Recognition of human. And we select the driver emotion as a specific target. The experimental result shows that using of both EEG signals and gestures gets high recognition rates better than using EEG signals or gestures. Both EEG signals and gestures use Interactive Feature Selection(IFS) for the feature selection whose method is based on a reinforcement learning.

• 제어로봇시스템학회논문지
• /
• 제21권12호
• /
• pp.1100-1108
• /
• 2015

A camera-based real-time hand posture and gesture recognition system is proposed for controlling various devices inside automobiles. It uses an imaging system composed of a camera with a proper filter and an infrared lighting device to acquire images of hand-motion sequences. Several steps of pre-processing algorithms are applied, followed by a background normalization process before segmenting the hand from the background. The hand posture is determined by first separating the fingers from the main body of the hand and then by finding the relative position of the fingers from the center of the hand. The beginning and ending of the hand motion from the sequence of the acquired images are detected using pre-defined motion rules to start the hand gesture recognition. A set of carefully designed features is computed and extracted from the raw sequence and is fed into a decision tree-like decision rule for determining the hand gesture. Many experiments are performed to verify the system. In this paper, we show the performance results from tests on the 550 sequences of hand motion images collected from five different individuals to cover the variations among many users of the system in a real-time environment. Among them, 539 sequences are correctly recognized, showing a recognition rate of 98%.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제5권10호
• /
• pp.503-510
• /
• 2016

최근 제안된 FsGr 모델은 가속도 센서 기반의 제스처 인식을 위한 방법으로 DTW 알고리즘을 두 단계로 적용하여 인식률을 개선하였다. FsGr 모델에서는 유사제스처 집합 개념을 정의하는데 훈련과정에서 유사제스처 집합들을 생성한다. 제스처 인식의 1차 인식 시도에서 유사제스처 집합이 정의된 제스처로 판정되면, 이 유사제스처 집합의 제스처들에 대해 특징이 강조된 부분들을 추출해 DTW를 통한 2차 인식을 시도한다. 그러나 동일 제스처도 사용자의 신체 크기, 나이, 성별, 등의 신체적인 특징에 따라 매우 다른 특성을 보이고 있어 FsGr 모델을 다중 사용자 환경에 적용하기에는 한계가 있다. 본 논문에서는 이를 다중 사용자 환경으로 확장한 FsGrM 모델을 제안하고 이를 사용한 스마트TV의 채널 및 볼륨 제어 프로그램을 보인다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제7권4호
• /
• pp.256-261
• /
• 2007

Electroencephalographic(EEG) is used to record activities of human brain in the area of psychology for many years. As technology developed, neural basis of functional areas of emotion processing is revealed gradually. So we measure fundamental areas of human brain that controls emotion of human by using EEG. Hands gestures such as shaking and head gesture such as nodding are often used as human body languages for communication with each other, and their recognition is important that it is a useful communication medium between human and computers. Research methods about gesture recognition are used of computer vision. Many researchers study Emotion Recognition method which uses one of EEG signals and Gestures in the existing research. In this paper, we use together EEG signals and Gestures for Emotion Recognition of human. And we select the driver emotion as a specific target. The experimental result shows that using of both EEG signals and gestures gets high recognition rates better than using EEG signals or gestures. Both EEG signals and gestures use Interactive Feature Selection(IFS) for the feature selection whose method is based on the reinforcement learning.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.2283-2286
• /
• 2003

This paper has expressed human's motion data into orthogonal parameters in low dimension, and created new motion data through this. We have reconstructed a new model consisting of orthogonal parameters from dividing human body data into three parts - hand, leg, and body to make new motions. Mixing these parts of body from different motions has leaded to new good motion data. It will be possible to use this motion editing not only for Animation Technology, but also for a three dimensional gesture recognition skill.

• 디지털콘텐츠학회 논문지
• /
• 제13권1호
• /
• pp.91-99
• /
• 2012

우리는 본 논문에서 아날로그 영역의 퀴즈 게임을 디지털화시키는 작업을 소개한다. 우리는 퀴즈 진행, 퀴즈 참가자 파악, 문제 제시, 먼저 손든 참가자 인식, 정오답 판단, 점수 합산, 승리팀 판단 등 기존의 퀴즈 게임이 아날로그 방식으로 수행해온 작업을 디지털화시키는 작업을 수행하였다. 이를 자동화하기 위해 최근 주목받기 시작한 키넥트 카메라를 이용하여 깊이 영상을 입력받아, 사용자들의 위치를 파악하고 사용자 위주로 정의된 제스처를 인식하는 알고리즘을 고안하였다. 영상의 깊이 값의 분포를 분석하여 퀴즈 참가자들의 상체를 검출하고 사용자들의 분할하였고 손 영역을 검출하였다. 또한 손바닥, 주먹, 기타 손 모양을 인식하기 위한 특징 추출 및 판단 함수를 고안하여 사용자가 퀴즈 보기를 선택할 수 있게 하였다. 구현된 퀴즈 응용 프로그램은 실시간 테스트에서 매우 만족스러운 제스처 인식 결과를 보였으며 원활한 게임 진행이 가능하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.334-336
• /
• 2007

This paper presents a beat gesture recognition method to synchronize the tempo of a robot playing a piano with the desired tempo of the user. To detect an unstructured beat gesture expressed by any part of a body, we apply an optical flow method, and obtain the trajectories of the center of gravity and normalized central moments of moving objects in images. The period of a beat gesture is estimated from the results of the fast Fourier transform. In addition, we also apply a motion control method by which robotic fingers are trained to follow a set of trajectories, Since the ability to track the trajectories influences the sound a piano generates, we adopt an iterative learning control method to reduce the tracking error.

• 제어로봇시스템학회논문지
• /
• 제14권2호
• /
• pp.178-183
• /
• 2008

Human motion analysis is researched as a new method for human-robot interaction (HRI) because it concerns with the key techniques of HRI such as motion tracking and pose recognition. To analysis human motion, extracting features of human body from sequential images plays an important role. After finding the silhouette of human body from the sequential images obtained by CCD color camera, the skeleton model is frequently used in order to represent the human motion. In this paper, using the silhouette of human body, we propose the feature extraction method based on hybrid skeleton for detecting human motion. Finally, we show the effectiveness and feasibility of the proposed method through some experiments.