• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.219-221
• /
• 2007

Recent changes to ubiquitous computing requires more natural human-computer(HCI) interfaces that provide high information accessibility. Hand-gesture, i.e., gestures performed by one 'or two hands, is emerging as a viable technology to complement or replace conventional HCI technology. This paper deals with hand-posture recognition. Hand-posture database construction is important in hand-posture recognition. Human hand is composed of 27 bones and the movement of each joint is modeled by 23 degrees of freedom. Even for the same hand-posture,. grabbed images may differ depending on user's characteristic and relative position between the hand and cameras. To solve the difficulty in defining hand-postures and construct database effective in size, we present a method using a 3D hand model. Hand joint angles for each hand-posture and corresponding silhouette images from many viewpoints by projecting the model into image planes are used to construct the ?database. The proposed method does not require additional equations to define movement constraints of each joint. Also using the method, it is easy to get images of one hand-posture from many vi.ewpoints and distances. Hence it is possible to construct database more precisely and concretely. The validity of the method is evaluated by applying it to the hand-posture recognition system.

• IEIE Transactions on Smart Processing and Computing
• /
• 제5권4호
• /
• pp.267-273
• /
• 2016

Hand posture recognition is an important technique to enable a natural and familiar interface in the human-computer interaction (HCI) field. This paper introduces a hand posture recognition method using a depth camera. Moreover, the hand posture recognition method is incorporated with the Moving Picture Experts Group Rich Media User Interface (MPEG-U) Advanced User Interaction (AUI) Interface (MPEG-U part 2), which can provide a natural interface on a variety of devices. The proposed method initially detects positions and lengths of all fingers opened, and then recognizes the hand posture from the pose of one or two hands, as well as the number of fingers folded when a user presents a gesture representing a pattern in the AUI data format specified in MPEG-U part 2. The AUI interface represents a user's hand posture in the compliant MPEG-U schema structure. Experimental results demonstrate the performance of the hand posture recognition system and verified that the AUI interface is compatible with the MPEG-U standard.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권2호
• /
• pp.763-774
• /
• 2015

Hand posture recognition has been a wide region of applications in Human Computer Interaction and Computer Vision for many years. The problem arises mainly due to the high dexterity of hand and self-occlusions created in the limited view of the camera or illumination variations. To remedy these problems, a hand posture recognition method using 3-D point cloud is proposed to explicitly utilize 3-D information from depth maps in this paper. Firstly, hand region is segmented by a set of depth threshold. Next, hand image normalization will be performed to ensure that the extracted feature descriptors are scale and rotation invariant. By robustly coding and pooling 3-D facets, the proposed descriptor can effectively represent the various hand postures. After that, SVM with Gaussian kernel function is used to address the issue of posture recognition. Experimental results based on posture dataset captured by Kinect sensor (from 1 to 10) demonstrate the effectiveness of the proposed approach and the average recognition rate of our method is over 96%.

• PNF and Movement
• /
• 제10권1호
• /
• pp.9-17
• /
• 2012

Purpose : This study's purpose is consideration about change of the hand grip strength according to different posture and shoulder flexion angle. The shoulder joint permits the greatest mobility and carries out the important function of stabilization for hand use. Hand grip activity is important to evaluate while assessing loads of shoulder in hand mobilities. Methods : Thirty(15 male, 15 female) college students with unknown shoulder dysfunction participated subject in five different positions of elbow extension with sitting and standing posture, different positions is followed : (1) shoulder $0^{\circ}$ flexion (2) shoulder $45^{\circ}$ flexion (3) shoulder $90^{\circ}$ flexion (4) shoulder $135^{\circ}$ flexion (5) shoulder $180^{\circ}$ flexion. Results : On the average, in the hand grip strength, the standing posture is higher than sitting posture. Sitting posture showed a most high level at the man's $0^{\circ}$ and woman's $135^{\circ}$. And standing posture showed a most high level at the man's $135^{\circ}$ and woman's $90^{\circ}$. Conclusion : The paired t-test was used to determine the different in grip strength between sitting and standing posture by shoulder angle change. There was no significant difference between the five position by sitting and standing posture. In man, correlation analysis revealed significant connection for all five position by sitting and standing posture. And in woman, correlation analysis revealed connection for all five position by sitting and standing posture.

• 한국지능시스템학회논문지
• /
• 제16권3호
• /
• pp.271-274
• /
• 2006

본 논문에서는 비전 기술에 기반을 둔 손 모양 인식 시스템의 성능 향상을 위해 학습을 통해 손 모양과 손 구조 간 유사도를 결정하는 방법을 제안한다. 비전 센서에 기반을 둔 손 모양 인식은 손의 높은 자유도로 인한 자체 가림 현상과 관찰 방향 변화에 따른 입력 영상의 다양함으로 인해 인식에 어려움이 따른다. 따라서 비전 기반 손 모양 인식의 경우, 카메라와 손 간의 상대적인 각도에 제한을 두거나 여러 대의 카메라를 배치하는 것이 일반적이다. 그러나 카메라와 손 간의 상대적 각도에 제한을 두는 경우에는 사용자의 움직임에 제약이 따르게 되며, 여러 대의 카메라를 사용할 경우에는 각 입력된 영상에 대한 인식 결과를 최종 인식 결과에 반영하는 방식에 대해서 추가적으로 고려해야 한다. 본 논문에서는 비전 기반 손 모양 인식의 이러한 문제점을 개선하기 위하여 인식의 과정에서 사용되는 손 모양 특징을 손 구조적인 각도 정보와 손 영상 특징으로 나누고, 학습을 통해 각 특징 간 연관성을 정의한다.

• 대한인간공학회지
• /
• 제26권1호
• /
• pp.29-37
• /
• 2007

This study was performed to evaluate the characteristics of transmitted vibration to hand-arm system under different work posture while operating a light-weighted powered hand grinder. For the experiment, 8 different types of wrist posture (natural, unlar-flexion, radual-flexion, flexion, extension, complex posture, and etc.) and 3 types of feed force (20[N], 50[N], 70[N]) were considered. 10 male subjects were employed to polish metal plate with a hand grinder. All of them were normal and healthy with no history and symptom of the work related musculoskeletal disorders in the dominant hand. Vibration acceleration data were recorded with sampling rate, 2048[Hz]. In addition, unweighted overall R.M.S. acceleration at the tool and wrist, and transmissibility between them were used to evaluate factors from the recorded tri-axial vibration acceleration. The results indicate that transmissibility of natural wrist posture was significantly higher than others. In addition, as the feed force becomes larger, the vibration was transmitted in large quantities to hand-arm system through radius.

• 방송공학회논문지
• /
• 제19권1호
• /
• pp.83-95
• /
• 2014

최근 손과 손가락을 인식하는 기술은 HCI(human computer interaction)에서 자연스럽고 친숙한 환경을 제공하기 위한 기술로 주목 받고 있다. 본 논문에서는 깊이 카메라를 이용하여 손과 손가락의 모양을 검출 및 인식하는 방법을 제안하고, 그 인식 결과를 활용하여 다양한 기기와 상호연동 할 수 있는 MPEG-U 기반 향상된 사용자 상호작용 인터페이스 시스템을 제안한다. 제안하는 시스템은 깊이 카메라를 이용하여 손을 검출한 후, 손목의 위치를 찾아 최소 손 영역을 검출한다. 이어서 검출된 최소 손 영역으로부터 손가락 끝점을 검출 한 후, 최소 손 영역의 중심점과 손가락 끝점간의 뼈대를 만든다. 이렇게 만든 뼈대의 길이와 인접 뼈대간의 각도차를 분석하여 손가락을 판별한다. 또한, 제안하는 시스템은 사용자가 MPEG-U에서 정의하는 다양한 심벌들을 손 자세로 취하였을 때 제안 방법을 이용하여 손 자세를 인식하고, 인식 결과를 상호연동 가능한 MPEG-U 스키마 구조로 표현한다. 실험에서는 다양한 환경에서 제안하는 손 자세 인식 방법의 성능을 보인다. 또한, 제안 시스템의 상호연동성을 보이기 위해 인식 결과를 MPEG-U part2 표준에 맞는 XML 문서로 표현하고, MPEG-U 참조 소프트웨어를 이용하여 그 표현 결과에 대한 표준 부합성을 검증한다.

• 전자공학회논문지CI
• /
• 제43권3호
• /
• pp.39-49
• /
• 2006

본 논문에서는 비전 기술에 기반을 둔 손 모양 인식 시스템의 성능 향상을 위하여 강화학습에 의한 손 모양 인식 방법을 제안한다. 비전 센서에 기반을 둔 손 모양 인식은 손의 높은 자유도로 인한 자체 겹침 (self-occlusion) 현상과 관찰 방향 변화에 따른 입력 영상의 다양함으로 인식에 어려움이 따른다. 따라서 비전 기반 손 모양 인식의 경우, 카메라와 손 간의 상대적인 각도에 제한을 두거나 여러 대의 카메라를 배치하는 것이 일반적이다. 그러나 카메라와 손 간의 상대적 각도에 제한을 두는 경우에는 사용자의 움직임에 제약이 따르게 되며, 여러 대의 카메라를 사용할 경우에도 각 입력된 영상에 대한 인식 결과를 최종 인식 결과에 반영하는 방식에 대하여 추가적인 고려를 해야 한다. 본 논문에서는 비전 기반 손 모양 인식의 이러한 문제점을 개선하기 위하여 인식 과정에서 사용되는 특징을 손 구조적인 각도 정보와 손 윤곽선 정보로 나누고 강화학습을 통하여 각 특징간의 연관성을 정의하는 방식을 제안한다. 또한 제안된 방법을 세 대의 카메라를 이용한 손 모양 인식 시스템에 적용하여 유용성을 검증한다.

• 대한인간공학회지
• /
• 제29권5호
• /
• pp.727-734
• /
• 2010

The objective of this study was to evaluate the resting postures of the fingers and wrist based on the biomechanical model in term of hand posture (neutral, pronation, and supination) and gender (male and female). The finger and wrist joint angles were measured with VICON motion system. The EMG system was used to examine the muscle activity in the resting condition. The participants consisted of twenty male and twenty female students. The angles of the fingers and wrist were analyzed by means of the coordinate system associated with the International Society of Biomechanics. Hand posture was significant for all the joints. The finger and wrist joint flexed in supination more than in neutral and pronation. The hand posture and gender were not significant for the results of muscle activity, but it had larger muscle activities in supination more than in neutral and pronation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권7호
• /
• pp.2585-2598
• /
• 2015

Hand posture recognition has played a very important role in Human Computer Interaction (HCI) and Computer Vision (CV) for many years. The challenge arises mainly due to self-occlusions caused by the limited view of the camera. In this paper, a robust hand posture recognition approach based on 3D point cloud from two RGB-D sensors (Kinect) is proposed to make maximum use of 3D information from depth map. Through noise reduction and registering two point sets obtained satisfactory from two views as we designed, a multi-viewed hand posture point cloud with most 3D information can be acquired. Moreover, we utilize the accurate reconstruction and classify each point cloud by directly matching the normalized point set with the templates of different classes from dataset, which can reduce the training time and calculation. Experimental results based on posture dataset captured by Kinect sensors (from digit 1 to 10) demonstrate the effectiveness of the proposed method.