• Journal of the Korea Computer Graphics Society
• /
• v.13 no.4
• /
• pp.29-36
• /
• 2007

The objective of this paper is to develop the motion recognition method for the rehabilitation program of the people with physical disabilities. Using the infrared ray LED, this method gets the information of the user's motion and tells the difference between the information we get and the pre-defined information. In order to get the fast recognition and comparison, this method positions the specific coordinates of infrared ray LED in the pre-classified sector which keeps certain distance and angle from the point of origin. The result in our experiment shows the speed over 20 frames per second in every motion, and we are satisfied the rate for the recognition of the motions which is near 98%.

• Journal of the Korea Society of Computer and Information
• /
• v.9 no.4 s.32
• /
• pp.109-116
• /
• 2004

This paper describes a cloth simulation system for dressing 3D virtual human model with different pieces of clothing. The garments are constructed of cutting patterns seamed together. The system reads a body file and a cutting pattern file and produces a new model dressed with the specified garment by using a physical simulation based on a mass-spring model. For the realistic cloth simulation, it performs collision detection and response between triangles of the 3D human model and the garment. Because the number of triangles of a human model is very large. the collision detection and response requires a lot of time. To overcome this problem, we propose a pruning method which decreases the number of collision detection and response by a space-subdivision method. Experimental results show that the system produces realistic images and makes it possible to sew a garment around a virtual human body in several seconds.

• Journal of the Korea Computer Graphics Society
• /
• v.24 no.1
• /
• pp.19-26
• /
• 2018

In this paper, we propose a gaze depth estimation method based on a binocular eye tracker for virtual reality and augmented reality applications. The proposed gaze depth estimation method collects a wide range information of each eye from the eye tracker such as the pupil center, gaze direction, inter pupil distance. It then builds gaze estimation models using Multilayer perceptron which infers gaze depth with respect to the eye tracking information. Finally, we evaluated the gaze depth estimation method with 13 participants in two ways: the performance based on their individual models and the performance based on the generalized model. Through the evaluation, we found that the proposed estimation method recognized gaze depth with 90.1% accuracy for 13 individual participants and with 89.7% accuracy for including all participants.

• The Journal of the Korea Contents Association
• /
• v.11 no.8
• /
• pp.14-22
• /
• 2011

It is important for the strategy of service to provide the health information in the environment that the healthcare has been changed focusing on the preventive medicine. Recently, the various applications of u-healthcare have been presented by researchers. In this paper, we proposed the health information monitoring system using the context sensors based band. By wearing the proposed hand, the health status is gathered and vital signals are transmitted to the connected UMPC. It can be easily monitored according to the user locations in real time. To provide the health index according to the temperature, the air conditioning, the illumination, the humidity, and the ultraviolet rays, we use the various XML links extracted from RSS of the Korea Meteorological Administration. The health information is analyzed in terms of factors, such as, the asthma index, the stroke index, the skin disease index, the pulmonary disease index, the pollen concentration index, and the city high temperature index. Ultimately, this paper suggests empirical application to verify the adequacy and the validity with the proposed system. Accordingly, the satisfaction and the quality of services will be improved the healthcare.

• The Journal of the Korea Contents Association
• /
• v.5 no.5
• /
• pp.287-295
• /
• 2005

This paper describes user context awareness system, which is one of the most essential technologies in various application services of ubiquitous computing. The proposed system used two-akial accelerometer, embedded in SenseWear(R)PRO2 Armband (BodyMedia). When it was worn on the right upper arm of the experiment subjects, MAD (mean of absolute difference) value of the sensor data was calculated to quantify the amount of the wear's activity. Using this data, PC-based fuzzy inference system was realized to distinguish human motion states, such as, lying, sitting, walking and running and to recognize the restricted emergency situations. In laboratory experiment, the amount of activities for tying, sitting, walking and running were 0.204 g/s, 0.373 g/s, 2.808 g/s and 16.243 g/s respectively. The recognition rates of human motion states were 96.7 %, 93.0 %, 95.2 % and 98.4 % respectively for lying, sitting, walking and running. The recognition rate of restricted emergency situation was 100%.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.2
• /
• pp.136-140
• /
• 2014

This paper introduces a multi-touch recognition and tracking method for self capacitive TSP(Touch Screen Pannel). Self capacitive TSP recognizes finger touches by sensing capacitive change of ITO transparent conducting film arranged by rows and columns on the TSP pannel. They have some advantages such as high SNR, fast sensing, and simple touch processing, but have very difficulties for multi-touch processing. This disadvantage makes that the mutual capacitive TSPs, which have no such disadvantage, have been more widely used especially for multi-touch applications. However, since the other applications for remote control pad or recently developed wearable devises have only restrictive requirements for multi-touch, the disadvantage of self capacitive TSP is not a critical problem. In this paper, we first describe multi-touch recognition problems in self capacitive TSP and then propose how to overcome those problems and a tracking method of two touches when they are moving. Experimental results of our method showed that our algorithm works well in two touches.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.7
• /
• pp.1383-1390
• /
• 2012

In this paper, we propose a robust pupil detection method using rank order filter and pixel value difference in facial image. We have detected the potential pupil candidates using rank order filter. Many false pupil candidates found at eyebrow are removed using the fact that the pixel difference is much at the boundary between pupil and sclera. The rest pupil candidates are grouped into pairs. Each pair is verified according to geometric constraints such as the angle and the distance between two candidates. A fitness function is obtained for each pair using the pixel values of two pupil regions, we select a pair with the smallest fitness value as a final pupil. The experiments have been performed for 400 images of the BioID face database. The results show that it achieves more than 90% accuracy, and especially the proposed method improves the detection rate and high accuracy for face with spectacle.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.4
• /
• pp.781-788
• /
• 2013

In this paper, we introduce a quadruped robot-based alarm system for monitoring the emergency situation due to falling in the elderly. Quadruped robot includes the FPGA Board(Field Programmable Gate Array) applying a red-color tracking algorithm. To detect a falling of the elderly, a sensor node is worn on chest and accelerations and angular velocities measured by the sensor node are transferred to quadruped robot, and then the emergency signal is transmitted to manager if a fall is detected. Manager controls the robot and then he judges the situation by monitoring the real-time images transmitted from the robot. If emergency situation is decided by the manager, he calls 119. When the fall detection system using only sensor nodes is used, sensitivity of 100% and specificity of 98.98% were measured. Using the combination of the fall detection system and portable camera (robot), the emergency situation was detected to 100 %.

• Smart Media Journal
• /
• v.9 no.3
• /
• pp.25-30
• /
• 2020

The purpose of this paper is to implement a deep learning-based real-time video analysis algorithm that monitors safety of workers in industrial facilities. The worker's clothes were divided into six classes according to whether workers are wearing a helmet, safety vest, and safety belt, and a total of 5,307 images were used as learning data. The experiment was performed by comparing the mAP when weight was applied according to the number of learning iterations for 645 images, using YOLO v4. It was confirmed that the mAP was the highest with 60.13% when the number of learning iterations was 6,000, and the AP with the most test sets was the highest. In the future, we plan to improve accuracy and speed by optimizing datasets and object detection model.

• Science of Emotion and Sensibility
• /
• v.6 no.1
• /
• pp.17-26
• /
• 2003

With rapid expansion in e-retailing of apparel business, the virtual fitting model is used for comparing fit of the selected garments. The researchers experimented women's perceived body size for developing virtual fitting model. 50 women who were 20's in age were participated in the experiment They were graduate students with clothing & textile major. The results of this study showed that the subjects perceived themselves with fuller figure at waist or hips and with shorter figure at waist height than their actual body site. Many subjects believed that their body sizes were close to the average site. Especially, subjects whose abdomen girth of hip girth was much larger than average thought that they have relatively flat abdomen. It was concluded that not only the user's body measurements but also user's perception on their figure type are needed to be considered in the process of developing virtual fitting model for e-retailing of apparel. It was expected that the virtual fitting model of extraordinary size body would not be accepted by the female consumers even though they are extra large or small size person in reality.