• 대한임베디드공학회논문지
• /
• 제17권4호
• /
• pp.191-197
• /
• 2022

This study proposes an image-based Pose Intention Network (PIN) algorithm for rehabilitation via patients' intentions. The purpose of the PIN algorithm is for enabling an active rehabilitation exercise, which is implemented by estimating the patient's motion and classifying the intention. Existing rehabilitation involves the inconvenience of attaching a sensor directly to the patient's skin. In addition, the rehabilitation device moves the patient, which is a passive rehabilitation method. Our algorithm consists of two steps. First, we estimate the user's joint position through the OpenPose algorithm, which is efficient in estimating 2D human pose in an image. Second, an intention classifier is constructed for classifying the motions into three categories, and a sequence of images including joint information is used as input. The intention network also learns correlations between joints and changes in joints over a short period of time, which can be easily used to determine the intention of the motion. To implement the proposed algorithm and conduct real-world experiments, we collected our own dataset, which is composed of videos of three classes. The network is trained using short segment clips of the video. Experimental results demonstrate that the proposed algorithm is effective for classifying intentions based on a short video clip.

• 한국실내디자인학회논문집
• /
• 제12호
• /
• pp.91-99
• /
• 1997

Alvar Aalto has pursued National Romanticism, cultural art movement in scandinavian peninsula, organic concepts of growth and suitability, comprehensive view of nature including a possibility of coexistance of human-being and the nature well harmonized. For instance, his design expressed local features of the nature, human emotions instead of geometical arts and mathematical principles. It is noteworthy today that he built up the identity with satrical architecture vocabularies, different from modern arch-itechtural idiology. The characte-ristics of his design related to interior architecture are collectively as follows; The first, Space discontinuity of the interior and exterior, gradual process by joints which are inclined to collage with many shapes in plan and section of the space and such joints are adjusted by sensual ways and stressed with inner collectivity in his works. The second, He pursued the architectural orderfor modern irreqularity, various changes and sensual harmonies. As result, free curved line, fan shape and irregular modeling were individually expressed by technics of natural features and national characteristics of Finland. The third, Organic synthesis. A harmony through med-ums in its space, materials and space effectiveness relations are made and expressed for mixed design especially harmonized of all the materials he planned, entire harmony with total design, itemized details, materials and furnitures in entire space. The fourth, The interest of the nature based on his sense harmonized with nature made him mainly use native materials, lumbers and red bricks masonry and showed and arranged various interior sky light and grazed in to let natural light in, harmony with garden to sensually cohere to the nature and courtyard, etcetera. His major subject are to direct architectural developments through the nature and human-being in his works. At this point, it is considered that his direction of the locality and independence as a human-being made the concepts of organic space structure possible.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.209-214
• /
• 2003

We developed a new type of human-sized BWR (biped walking robot), named KUBIR1 which is driven by the closed-chain type of actuator. A new type of the closed-chain actuator for the robot is developed, which is composed of the four-bar-link mechanism driven by the ball screw which has high strength and high gear ratio. Each leg of the robot is composed of 6 D.O.F joints. For front walking, three pitch joints and one roll joint at the ankle. In addition to this, one yaw joint for direction change, and another roll joint for balancing the body are attached. Also, the robot has two D.O.F joints of each hand and three D.O.F. for eye motion. There are three actuating motors for stereo cameras for eyes. In all, a 18 degree-of-freedom robot was developed. KUBIR1 was designed to walk autonomously by adapting small 90W DC motors as the robot actuators and batteries and controllers are on-boarded. The whole weight for Kubir1 is over 90Kg, and height is 167Cm. In the paper, the performance test of KUBIR1 will be shown.

• 한국멀티미디어학회논문지
• /
• 제17권6호
• /
• pp.741-750
• /
• 2014

This paper presents a real-time motion restoration system for people who need remedial exercise of musculoskeletal based on Inverse Kinematics. A new approach is suggested to recognize a gesture based on restored human motion which is calculated the 3D positions of intermediate joints using 3D positions of body features estimated from images. For generating the 3D candidate positions of intermediate joints which cannot be extracted from images, we apply an Inverse Kinematics theory to compute the target position of intermediate joints. And we can reduce the number of candidate positions by applying the various physical constraints of body. Finally, we can generate the more accurate final position using the Kalman filter for a motion tracking and the relationship between the previous frame information and the candidate positions. The system provide motion information which are rotation angle and height in real-time, therefore the rehabilitation exercises can be performed based on the information and figured out proper exercise for individual status.

• 대한인간공학회지
• /
• 제15권2호
• /
• pp.15-24
• /
• 1996

To generate workspace analytically using the robot kinematics, data on range of human joints motion, especially range of two degrees of freedom motion, are needed. However, these data have not been investigated up to now. Therefore, in this research, we are to investigate an interaction effect of motions with two degrees of freedom occurred simultaneously at the shoulder, virtual hip(L5/S1) and hip joints, respectively, for 47 young male students. When motion with two degrees of freedom occurred at a joint such as shoulder, virtual hip and hip joints, it was found from the results of ANOVA that the action of a degree of freedom motion may either decrease or increase the effective functioning of the other degree of freedom motion. In other words, the shoulder flexion was decreased as the shoulder was adducted or abducted to $60^{\circ}C$TEX>or abducted from $60^{\circ}C$TEX>to maximum degree of abduction, while the shoulder flexion increased as the joint was abducted from $60^{\circ}C$TEX> to $60^{\circ}C$TEX> The flexion was decreased as the virtual hip was bent laterally at the virtual hip joint, and also did as the hip was adducted or abducted from the neutral position. It is expected that workspace can be generated more precisely based the data on the range of two degrees of joint motion measured in this study.

• 대한정형도수물리치료학회지
• /
• 제24권1호
• /
• pp.39-46
• /
• 2018

Background: In most human lives, 80 percent have problems with the ankle and can be solved with a treatment that is objective in proper assessment. Discrepacts in the ankle are also associated with walking patterns and affect hip and knee joints. An evaluation of hip flexion and extensor muscles was performed to check the strength of hip joints after ankle sprain patients application of arthesis. Methods: In the hospital in Bucheon, 20 outpatients who visited the hospital for treatment with ankle sprain were tested with 10 male and 10 female patients. The criteria for selection of the study subjects were randomly divided into those with joint movement techniques applied to the ankle joints and those with conservative physical therapy. Results: In applying arthrography and preservation physical therapy to patients with ankle sprain, a difference in muscle strength between hip flexion and extensor was noted in post-evaluation comparisons. There were significant differences in the assessment of walking speed and walking time between the two counties in the gait analysis assessment (p<.05). Conclusion: Studies have shown that applying arthrography to people with ankle sprain has a greater therapeutic effect than using conservative physical therapy.

• 한국해양공학회지
• /
• 제26권6호
• /
• pp.59-65
• /
• 2012

In this research, a novel mater arm was studied as a teaching device for an underwater revolute robot arm used as a slave arm. The master arm was designed to be a seven-degree-of-freedom (DOF) structure, with a structure similar to that of the slave arm, and to be desktop size to allow it to be worn on a human arm. The master arm with encoders on the joints was used as an input device for teaching a slave robot arm. In addition, small electric magnets were installed at the joints of the master arm to generate the haptic force. A control system was designed to sense excessive force and torque in the joints of the master arm and protect it by controlling the position and velocity of the slave arm through the encoder signal of the master arm.

• Advances in robotics research
• /
• 제2권2호
• /
• pp.129-140
• /
• 2018

With the increasing demand for the development of human pose estimation, such as human-computer interaction and human activity recognition, there have been numerous approaches to detect the 2D poses of people in images more efficiently. Despite many years of human pose estimation research, the estimation of human poses with images remains difficult to produce satisfactory results. In this study, we propose a robust 2D human body pose estimation method using an RGB camera sensor. Our pose estimation method is efficient and cost-effective since the use of RGB camera sensor is economically beneficial compared to more commonly used high-priced sensors. For the estimation of upper-body joint positions, semantic segmentation with a fully convolutional network was exploited. From acquired RGB images, joint heatmaps accurately estimate the coordinates of the location of each joint. The network architecture was designed to learn and detect the locations of joints via the sequential prediction processing method. Our proposed method was tested and validated for efficient estimation of the human upper-body pose. The obtained results reveal the potential of a simple RGB camera sensor for human pose estimation applications.

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 1995년도 춘계공동학술대회논문집; 전남대학교; 28-29 Apr. 1995
• /
• pp.787-796
• /
• 1995

A man model is a useful design tool for the evaluation of man machine systems and products. An arm reach trajectory prediction for such a model will be specifically useful to present human activities and, consequently, could increase the accuracy and reality of the evaluation. In this study, a three-dimensional reach trajectory prediction model was developed using an inverse kinematics technique. The upper body was modeled as a four link open kinematic chain with seven degrees of freedom. The Resolved Motion Method used for the robot kinematics problem was used to predict the joint movements. The cost function of the perceived discomfort developed using the central composite design was also used as a performance function. This model predicts the posture by moving the joints to minimize the discomfort on the constraint of the end effector velocity directed to a target point. The results of the pairwise t-test showed that all the joint coordinates except the shoulder joint's showed statistically no differences at .alpha. = 0.01. The reach trajectory prediction model developed in this study was found to accurately simulate human arm reach trajectory and the model will help understand the human arm reach movement.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권2호
• /
• pp.1118-1133
• /
• 2017

Computer vision-based human activity recognition (HAR) has become very famous these days due to its applications in various fields such as smart home healthcare for elderly people. A video-based activity recognition system basically has many goals such as to react based on people's behavior that allows the systems to proactively assist them with their tasks. A novel approach is proposed in this work for depth video based human activity recognition using joint-based motion features of depth body shapes and Deep Belief Network (DBN). From depth video, different body parts of human activities are segmented first by means of a trained random forest. The motion features representing the magnitude and direction of each joint in next frame are extracted. Finally, the features are applied for training a DBN to be used for recognition later. The proposed HAR approach showed superior performance over conventional approaches on private and public datasets, indicating a prominent approach for practical applications in smartly controlled environments.