• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.483-486
• /
• 1999

In this paper, we present a real-time hand gesture recognition system that controls motion of a human avatar based on the pre-defined dynamic hand gesture commands in a virtual environment. Each motion of a human avatar consists of some elementary motions which are produced by solving inverse kinematics to target posture and interpolating joint angles for human-like motions. To overcome processing time of the recognition system for teaming, we use a Fuzzy Min-Max Neural Network (FMMNN) for classification of hand postures

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.566-569
• /
• 2022

In this paper, the algorithm was developed to recognize hand golve gesture and implemented a system to remotely control the robot. The system consists of a camera and a controller that controls robot motion by hand position gesture. The camera recognizes the specific color of the glove and outputs the recognized range and position by including the color area of the glove. We recognize the velocity vector of robot motion and control the robot by the output data of the position and the detected rectangle. Through the several experiments, it was confirmed that the robot motion control was successfully performed.

• Journal of IKEEE
• /
• v.16 no.4
• /
• pp.369-374
• /
• 2012

This paper handles the UX implementation for system control using the visual input information of hand motion. Kinect sensor from Microsoft is used to acquire the user's skeleton image from the 3-D depth map at a rate of 30 frames per sec. and eventually knows the x-y coordinates of hand joints. The x-y coordinate value changes of hands between the present frame and next frame shows the direction of changes and rotation of changes and the various hand motion is used as a UX input command for remote image control on smart TV, etc. Through the experiments, we showed the implementation of the proposed idea.

• Smart Media Journal
• /
• v.9 no.4
• /
• pp.102-108
• /
• 2020

In this paper, we propose a real-time method of detecting hand motions and extracting the signal frame induced by EF(Electric Field) sensors. The signal induced by hand motion includes not only noises caused by various environmental sources as well as sensor's physical placement, but also different initial off-set conditions. Thus, it has been considered as a challenging problem to detect the motion signal and extract the motion frame automatically in real-time. In this study, we remove the PLN(Power Line Noise) using LPF with 10Hz cut-off and successively apply MA(Moving Average) filter to obtain clean and smooth input motion signals. To sense a hand motion, we use two thresholds(positive and negative thresholds) with offset value to detect a starting as well as an ending moment of the motion. Using this approach, we can achieve the correct motion detection rate over 98%. Once the final motion frame is determined, the motion signals are normalized to be used in next process of classification or recognition stage such as LSTN deep neural networks. Our experiment and analysis show that our proposed methods produce better than 98% performance in correct motion detection rate as well as in frame-matching rate.

• The Journal of Korea Robotics Society
• /
• v.10 no.3
• /
• pp.162-170
• /
• 2015

This paper describes the development of a hand module of NREX (National Rehabilitation Center Robotic Exoskeleton) designed to assist individuals with sustained neurological impairments such as stroke and spinal cord injuries. To construct a simple and lightweight hand module, the robotic hand adopts a mechanism driven by a motor and moved by two four-bar linkages. The motor facilitates the flexion-extension movements of the thumb and the other four fingers simultaneously. Thus, an individual using the robotic hand module can effectively grip and release objects related to daily life activities. The robotic hand module has been designed to cover the range of motion with respect to its link distance. This hand module can be used in therapeutic rehabilitation as well as for daily life assistance. In addition, this hand module can either be mounted on an NREX or used as a standalone module.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.231-232
• /
• 2014

We develop a remote control system of a walking robot using a Leap motion sensor. Hand gestures and the position of fingers are provided from the Leap motion sensor. We use Processing and the LeapMotionP5 library for the development software.

• Journal of the Korean Society of Industry Convergence
• /
• v.17 no.1
• /
• pp.21-26
• /
• 2014

The focus of this paper is the designing a flexible three fingered hand system with 16 D.O.F for dynamic manipulation with an intelligent controller, and to build a useful database for dynamic manipulation based on the experimental results. The weight of the hand module is only 0.7 kg, but flexible motion and powerful grasping are possible. To achieve such a dynamic motion in a robotic hand, we have developed a flexible fingered hand with a control system incorporating image recognition system in which we deal with the problems of not only accuracy and range of motion but also the flexibility of hand. The fingers are arranged so as to grasp both circular and prismatic objects. In order to achieve the light mechanism, we reduced the number of joints and fingers as much as possible. We used three fingers, which is the minimum number to achieve a stable grasp.

• Journal of the Korean Society of Industry Convergence
• /
• v.21 no.4
• /
• pp.183-189
• /
• 2018

The focus of this paper is to design and control a three fingered hand system with eight axes for smart factory with an flexible controller, and to keep a useful big database for dynamic manipulation based on the experimental results. The weight of the hand module is only 1.2 kg, but flexible motion and powerful grasping are possible. To achieve such a flexible motion control of a robotic hand, we have developed a robust and precise fingered hand with a control system incorporating image recognition system in which we deal with the problems of not only accuracy and range of motion but also the flexibility of hand. The fingers are arranged so as to grasp both circular and prismatic objects. In order to achieve the light mechanism, we reduced the number of joints and fingers as much as possible. In this study, it was used three fingers with eight axes which is the optimal number to achieve a robust grasping diverse shape parts for smart factory.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.17 no.6
• /
• pp.71-76
• /
• 2008

The focus of this paper is the designing a flexible three fingered hand system with 16 D.O.F for dynamic manipulation with an intelligent controller, and to build a useful database for dynamic manipulation based on the experimental results. The weight of the hand module is only 0.7 kg, but flexible motion and powerful grasping are possible. To achieve such a dynamic motion in a robotic hand, we have developed a flexible fingered hand with a control system incorporating image recognition system in which we deal with the problems of not only accuracy and range of motion but also the flexibility of hand. The fingers are arranged so as to grasp both circular and prismatic objects. In order to achieve the light mechanism, we reduced the number of joints and fingers as much as possible. We used three fingers, which is the minimum number to achieve a stable grasp.

• Korean Journal of Applied Biomechanics
• /
• v.12 no.1
• /
• pp.173-191
• /
• 2002

The purpose of this study was defined efficient throw motion pattern to obtain the quantitative data and to achieve successful bowling through kinetic - kinematic variables on the throw motion. Subject of group composed of three groups : Higher bowlers who are two representative bowlers with 200 average points and one pro-bowler. Middle bowlers who are three common persons with 170 average points. Lower bowler who are three common persons with 150 average points. Motion analysis on throw motion in three groups respectively has been made through three-dimension cinematography using DLT method. Two high-speed video camera at operating 180 frame per secondary. One-way ANOVA has been used to define variable relations. Analyzed result and conclusion are the following : The displacement of back of the hand must have wider difference of each right-left displacement to increase the spin of the ball. In high bowlers group, difference between the front-rear position of back of the hand in case of success and that in case of failure in follow throw is 0.17m. That is to say, momentum in case of success come to increase greatly, compared with that in case of failure. To increase the spin of the ball, the potential difference should be narrower in follow through. In case of the high bowlers, the velocity of the front-rear direction of the back of the hand has been the fastest both in release and follow through, compared with those in other groups, which has contributed to increasing the spin force of the ball. The orders in the resultant velocity of the back of the hand has shown the this : the finger tip$\rightarrow$the back of the hand$\rightarrow$wrist.These orders made the proximal segment support the distal segment. The distal segment has provided the condition to accelerate the velocity. In case of failure, the suddenly increased velocity has caused the failure in the follow through. Acutely flexing the angle of the back of the hand has contributed to lifting to increase the spin of the ball.