• Journal of the Korea Academia-Industrial cooperation Society
• /
• 제11권11호
• /
• pp.4087-4094
• /
• 2010

The sensor data which is measured by Quadruped robot is utilized to recognize the physical environment or other information and to control the posture and walking of robot system. In order to control the robot precisely, high accuracy of sensor data is required, most of these sensors however, belongs to expensive and low-durable products. Moreover, these are exposed excessive load operation in a field condition if it is applied to field robot system. This issue becomes more serious one when the robot system is manufactured as a mass product. As in this context, this study suggests a virtual sensor technology to alternate or assist the main sensor system. This scheme is realized by using back-propagation algorithm of neural network theory, and the quality of estimated sensor data could be improved through the algorithmic and hardware based treatments. This study performs the various trial to identify the effective parameters which effect to the quality and reliability of estimated sensor data and tries to show the possibility of proposed methodology.

• Journal of Korea Society of Industrial Information Systems
• /
• 제23권6호
• /
• pp.29-38
• /
• 2018

In this paper, we developed a virtual cloth try-on (VTON) technology that segement the cloth image worn on the mannequin and applies it to the user 's photograph. The two-dimensional image-based virtual wear study which does not require three-dimensional information of cloth and model is of practical value, but the research result shows that there are limitations of of the current technology for the problem of occlusion or distortion. In this study, we proposed an algorithm to apply the results obtained from the DNN- based segmentation and posture estimation to the user 's photograph, assuming that the mannequin cloth reduces the difficulties in this part. In order to improve the performance compared with the existing one, we used the validity check of the pre-attitude information, the improvement of the deformation using the outline, and the improvement of the divided area. As a result, a significantly improved result image of more than 50% was obtained.

• Journal of IKEEE
• /
• 제26권2호
• /
• pp.249-256
• /
• 2022

The prosthetic leg is a device that performs walking instead of a amputated lower limb, and require a change in locomotion mode by providing the user's intention to respond to a discontinuous locomotion environment. Research has been conducted to detect the users' intentions through biomechanical features inside the socket that directly contacts the cut site in demand for natural locomotion mode changes without external control equipment. However, there is still a need for a sensor system that is suitable for the internal environment of the main body and socket of the cut site. Accordingly, this paper proposed a film-type sensor system that is suitable for the main body characteristics of the cut site, is not affected by the temperature and humidity conditions inside the socket, and is easy to manufacture in various sizes. The proposed sensor is manufactured base on Velostat film and takes into account the pressure measurement characteristics that vary with size. Through the experiment, the change in the internal pressure of the socket due to the intentional posture performance of the wearer was measured, and the possibility of detecting the intention to change the locomotion mode was confirmed.

• Journal of Broadcast Engineering
• /
• 제25권5호
• /
• pp.750-757
• /
• 2020

One of the basic tasks for robots to interact with humans is to quickly and accurately grasp human behavior. Therefore, it is necessary to increase the accuracy of human pose recognition when the robot is estimating the human pose and to recognize it as quickly as possible. However, when the human pose is estimated using deep learning, which is a representative method of artificial intelligence technology, recognition accuracy and speed are not satisfied at the same time. Therefore, it is common to select one of a top-down method that has high inference accuracy or a bottom-up method that has high processing speed. In this paper, we propose two methods that complement the disadvantages while including both the advantages of the two methods mentioned above. The first is to perform parallel inference on the server using multi GPU, and the second is to mix bottom-up and One-class Classification. As a result of the experiment, both of the methods presented in this paper showed improvement in speed. If these two methods are applied to the entertainment robot, it is expected that a highly reliable interaction with the audience can be performed.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• 제17권2호
• /
• pp.299-306
• /
• 2016

In this paper, a method of shape prediction of an endoscope handling robot that can imitate a surgeon's behavior using a sensor network is suggested. Unit sensors, which are composed of a 3-axis magnetometer and 3-axis accelerometer pair comprise the network through CAN bus communication. Each unit of the sensor is used to detect the angle of the points in the longitudinal direction of the robot, which is made from a flexible tube. The signals received from the sensor network were filtered using a low pass Butterworth filter. Here, a Butterworth filter was designed for noise removal. Finally, the Euler angles were extracted from the signals, in which the noise was filtered by the low path Butterworth filter. Using this Euler angle, the position of each sensor on the sensor network is estimated. The robot body was assumed to consist of links and joints. The position of each sensor can be assumed to be attached to the center of each link. The position of each link was determined using the Euler angle and kinematics equation. The interpolation was carried out between the positions of the sensors to be able to connect each point smoothly and obtain the final posture of the endoscope in operation. The experimental results showed that the shape of the colonoscope can be visualized using the Euler angles evaluated from the sensor network suggested and the shape of serial link estimated from the kinematics chain model.

• Journal of the Korean Institute of Intelligent Systems
• /
• 제14권4호
• /
• pp.438-444
• /
• 2004

The intelligent robots that will be needed in the near future are human-friendly robots that are able to coexist with humans and support humans effectively. To realize this, robots need to recognize their position and posture in known environment as well as unknown environment. Moreover, it is necessary for their localization to occur naturally. It is desirable for a robot to estimate of his position by solving uncertainty for mobile robot navigation, as one of the best important problems. In this paper, we describe a method for the localization of a mobile robot using image information of a moving object. This method combines the observed position from dead-reckoning sensors and the estimated position from the images captured by a fixed camera to localize a mobile robot. Using the a priori known path of a moving object in the world coordinates and a perspective camera model, we derive the geometric constraint equations which represent the relation between image frame coordinates for a moving object and the estimated robot's position. Since the equations are based or the estimated position, the measurement error may exist all the time. The proposed method utilizes the error between the observed and estimated image coordinates to localize the mobile robot. The Kalman filter scheme is applied for this method. its performance is verified by the computer simulation and the experiment.

• Journal of the Institute of Electronics and Information Engineers
• /
• 제51권7호
• /
• pp.239-247
• /
• 2014

The CTSIB (Clinical Test of Sensory Integration on Balance) using high sensitive pressure sensors is normally used to assess the sense of balance in hospital. It takes an objective measurement of the amount of sway that occurs in the body trunk by observing the change in the center of pressure (CoP) on the foot at the upright posture. In this paper, we would like to propose method to easily measure trunk sway in home. Although the Wii balance board(WBB) is used for games, it can measures the center of pressure, which is highly correlated. The Wii remote controller(WRC) is inexpensive compared to the WBB, but it has problems with estimation of trunk sway because it can't measure pressure directly like WBB. We collected data from 10 normal subjects (5 males, 5 females) from two devices in order to compare the CoP from WBB and the center of mass (CoM) from WRC. The results of WRC and WBB was similar when the data were analyzed by the convex hull and ellipse area.

• Journal of the Korea Convergence Society
• /
• 제8권9호
• /
• pp.365-372
• /
• 2017

Squat exercise is one of the important free weight exercises that can safely and effectively expect the athletic performance by establishing the rationale. Therefore, it is necessary to study the side effects caused by incorrect exercise, scientific countermeasures and to develop a exercise estimation model. It is effective and accurate to use a variety of assistive devices to calibrate athletic posture. The issues of the structural analysis for designing a foot plate for squat exercise is to model the behavior by the dynamic behavior. It should be consider that the center of gravity of each segmented body is different when the maximum load is applied. It is applied to complete system design through simulation method with kinematic dynamic, ground reaction force and load analysis for the free weight exercise equipment, VR device, and safety foot plate. In this paper, the authors propose the design method for the vertical load distribution applied in the design of the foot plate used for the squat exercise mechanism, and based on these results, design make the more safe and reliable free weight exercise equipment system.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• 제22권2호
• /
• pp.127-133
• /
• 2021

A recent study of people physically falling focused on analyzing the motions of the falls using a recurrent neural network (RNN) and a deep learning approach to get good results from detecting 2D human poses from a single color image. In this paper, we investigate a detection method for estimating the position of the head and shoulder keypoints and the acceleration of positional change using the skeletal keypoints information extracted using PoseNet from an image obtained with a low-cost 2D RGB camera, increasing the accuracy of judgments about the falls. In particular, we propose a fall detection method based on the characteristics of post-fall posture in the fall motion-analysis method. A public data set was used to extract human skeletal features, and as a result of an experiment to find a feature extraction method that can achieve high classification accuracy, the proposed method showed a 99.8% success rate in detecting falls more effectively than a conventional, primitive skeletal data-use method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.165-167
• /
• 2022

The proportion of cat cats among companion animals has been increasing at an average annual rate of 25.4% since 2012. Cats have strong wildness compared to dogs, so they have a characteristic of hiding diseases well. Therefore, when the guardian finds out that the cat has a disease, the disease may have already worsened. Symptoms such as anorexia (eating avoidance), vomiting, diarrhea, polydipsia, and polyuria in cats are some of the symptoms that appear in cat diseases such as diabetes, hyperthyroidism, renal failure, and panleukopenia. It will be of great help in treating the cat's disease if the owner can recognize the cat's polydipsia (drinking a lot of water), polyuria (a large amount of urine), and frequent urination (urinating frequently) more quickly. In this paper, 1) Efficient version of DeepLabCut for posture prediction running on an artificial intelligence server, 2) yolov4 for object detection, and 3) LSTM are used for behavior prediction. Using artificial intelligence technology, it predicts the cat's next, polyuria and frequency of urination through the analysis of the cat's behavior pattern from the home CCTV video and the weight sensor of the water bowl. And, through analysis of cat behavior patterns, we propose an application that reports disease prediction and abnormal behavior to the guardian and delivers it to the guardian's mobile and the main server system.