• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.5
• /
• pp.863-870
• /
• 2015

A Compensation Algorithm for The Position of the User Hands based on the Moving Mean-Shift ($CAPUH_{MMS}$) in Human Robot Interface (HRI) System running the Kinect sensor is proposed in order to improve the performance of the gesture recognition is proposed in this paper. The average error improvement ratio of the trajectories ($AEIR_{TJ}$) in left-right movements of hands for the $CAPUH_{MMS}$ is compared with other compensation algorithms such as the Compensation Algorithm based on the Compensation Algorithm based on the Kalman Filter ($CA_{KF}$) and the Compensation Algorithm based on Least-Squares Method ($CA_{LSM}$) by the developed realtime performance simulator. As a result, the $AEIR_{TJ}$ in up-down movements of hands of the $CAPUH_{MMS}$ is measured as 19.35%, it is higher value compared with that of the $CA_{KF}$ and the $CA_{LSM}$ as 13.88% and 16.68%, respectively.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2008.04a
• /
• pp.400-402
• /
• 2008

The human-computer interaction technology (HCI) that has played an important role in the exchange of information between human being and computer belongs to a key field for information technology. Recently, control studies through which robots and control devices are controlled by using the movements of a person's body or hands without using conventional input devices such as keyboard and mouse, have been going only in diverse aspects, and their importance has been steadily increasing. This study is proposing a recognition method of user's gestures by applying measurements from an acceleration sensor to the PCA algorithm.

• Journal of Sensor Science and Technology
• /
• v.21 no.1
• /
• pp.28-33
• /
• 2012

The visual sensing of human hands plays an important part in many man-machine interaction/interface systems. Most existing visionbased hand detection techniques depend on the color cues of human skin. The RGB color image from a vision sensor is often transformed to another color space as a preprocessing of hand detection because the color space transformation is assumed to increase the detection accuracy. However, the actual effect of color space transformation has not been well investigated in literature. This paper discusses a comparative evaluation of the pixel classification performance of hand skin detection in four widely used color spaces; RGB, YIQ, HSV, and normalized rgb. The experimental results indicate that using the normalized red-green color values is the most reliable under different backgrounds, lighting conditions, individuals, and hand postures. The nonlinear classification of pixel colors by the use of a multilayer neural network is also proposed to improve the detection accuracy.

• Journal of Engineering Education Research
• /
• v.8 no.1
• /
• pp.5-19
• /
• 2005

This paper describes the design and fabrication of magnetic levitation kits for use in the hands on experiments of automatic control, digital control and microprocessor applications in the division of mechatronics in Samcheok university. The kits are developed inspired by MIT's design, but it is designed on the digital basis, whereas MIT's is designed on the analog basis. As a result, the kits can be monitored and controlled on the analog and digital control techniques. Furthermore, the cost of kit components is comparable or lower to that of MIT design. And the kits can be controlled with magnetic hall sensors and/or infrared sensors, which provides more versatile experience on the use of sensors and signal filtering to the students. The design is fabricated and tested by authors and will be provided to the students as lab projects. The kits will be intentionally presented with a device that is poorly instrumented and poorly compensated. And the students are expected to analyze sensor signal and controller performance, and then, perform compensator design and signal filtering.

• Smart Media Journal
• /
• v.2 no.1
• /
• pp.27-30
• /
• 2013

In this paper, we research the hand tracking and calibration algorithm using the EPIC sensor. We analyze the characteristics of EPIC sensor to be more sensitive in the around E-filed, and then we implement the 2-dimensional axis-transformation using the difference of detected amplitude between EPIC sensors. In addition, we implement the calibration algorithm considering the characteristics of EPIC sensor, and then we apply the Kalman filter to efficiently track a target. Thus, we implement the environment of window applications for verification and analysis the implemented algorithm. In turn, we use the DAQ API to extract the analog data. The DAQ hardware has the function of measuring and generating an electrical signal. Moreover, we confirm the movement of mouse cursor by detecting the potential difference depending on the movement of the user's hands.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.1 no.1
• /
• pp.1-6
• /
• 2007

Applying the gyroscopic technology, HeadZmouse has been developed to simulate left and right mouse click, double click, drag and drop, and even a wheel function for navigating web. This device was designed to work on both PC and Macintosh environments using a USB cable. The first time you use this device, you'll find out how much freedom it offers to someone who can't use his or her hands freely. Rather than being tied to your computer, simple manipulation such as blowing an air (breathing) into a sonic sensor can simulate all the functions which standard mouse has, even including a wheel function. Also, a macro-interface device has been developed. By storing repetitive tasks into a memory, you can carry out repetitive tasks just by clicking a button once.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.19-23
• /
• 2024

Patients with amputations of both hands need prosthetic hands that serve both cosmetic and functional purposes, and research on prosthetic hands using electromyography of remaining muscles is active, but there is still the problem of high cost. In this study, an artificial prosthetic hand was manufactured and its performance was evaluated using low-cost parts and software such as a surface electromyography sensor, machine learning software Edge Impulse, Arduino Nano 33 BLE, and 3D printing. Using signals acquired with surface electromyography sensors and subjected to digital signal processing through Edge Impulse, the flexing movement signals of each finger were transmitted to the fingers of the prosthetic hand model through training to determine the type of finger movement using machine learning. When the digital signal processing conditions were set to a notch filter of 60 Hz, a bandpass filter of 10-300 Hz, and a sampling frequency of 1,000 Hz, the accuracy of machine learning was the highest at 82.1%. The possibility of being confused between each finger flexion movement was highest for the ring finger, with a 44.7% chance of being confused with the movement of the index finger. More research is needed to successfully develop a low-cost prosthetic hand.

• Smart Media Journal
• /
• v.9 no.4
• /
• pp.97-101
• /
• 2020

Using passive electric field sensor which operates in non-contact mode, we can measure the electric potential induced from the change of electric charges on a sensor caused by the movement of human body or hands. In this study, we propose a new method, which utilizes PLN induced to the sensor around the moving object, to detect one's hand movement and extract gesture frames from the detected signals. Signals from the EPS sensors include a large amount of power line noise usually existing in the places such as rooms or buildings. Using the fact that the PLN is shielded in part by human access to the sensor, signals caused by motion or hand movement are detected. PLN consists mainly of signals with frequency of 60 Hz and its harmonics. In our proposed method, signals only 120 Hz component in frequency domain are chosen selectively and exclusively utilized for detection of hand movement. We use FFT to measure a spectral-separated frequency signal. The signals obtained from sensors in this way are continued to be compared with the threshold preset in advance. Once motion signals are detected passing throng the threshold, we determine the motion frame based on period between the first threshold passing time and the last one. The motion detection rate of our proposed method was about 90% while the correct frame extraction rate was about 85%. The method like our method, which use PLN signal in order to extract useful data about motion movement from non-contact mode EPS sensors, has been rarely reported or published in recent. This research results can be expected to be useful especially in circumstance of having surrounding PLN.

• Journal of the Korean Society for Precision Engineering
• /
• v.30 no.5
• /
• pp.529-536
• /
• 2013

Most serious stroke patients have the paralysis on their wrists, and can't use their hands freely. But their wrists can be recovered by rehabilitation exercises. Recently, professional rehabilitation therapeutists help stroke patients exercise their wrists in hospital. But it is difficult for them to rehabilitate their wrists, because the therapeutists are much less than stroke patients in number. Therefore, the wrist twist-exercise rehabilitation robot that can measure the twist force of the patients' wrists is needed and developed. In this paper, the six-axis force/moment sensor was designed appropriately for the robot. As a test result, the interference error of the six-axis force/moment sensor was less than 0.85%. It is thought that the sensor can be used to measure the wrist twist force of the patient.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.12
• /
• pp.158-164
• /
• 2015

Lane detection is one of the key parts among autonomous vehicle technologies because lane keeping and path planning are based on lane detection. Camera is used for lane detection but there are severe limitations such as narrow field of view and effect of illumination. On the other hands, Lidar sensor has the merits of having large field of view and being little influenced by illumination because it uses intensity information. Existing researches that use methods such as Hough transform, histogram hardly handle multiple lanes in the co-occuring situation of lanes and road marking. In this paper, we propose a method based on RANSAC and regularization which provides a stable and precise detection result in the co-occuring situation of lanes and road marking in highway scenarios. This is performed by precise lane point extraction using circular model RANSAC and regularization aided least square fitting. Through quantitative evaluation, we verify that the proposed algorithm is capable of multi lane detection with high accuracy in real-time on our own acquired road data.