• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.244-245
• /
• 2021

Recently, A fever test is essential in a crowded places over the world because of COVID-19. A fever test is also conducted for visitors through a thermometer or a thermal imaging camera In Korea leading world with K-quarantine. However, the current body heat measurement process is divided into the steps of body heat examination and entry register. Therefore, access control person must be deployed at the entrance. In addition, since the accessor directly measures body heat and records personal information, the reliability of the information is low and the risk of personal information leakage is high. Therefore, in this paper, we consider the non-face-to-face smart authentication fever detector and propose a smart authentication process to unify the process for dualized body heat measurement and access recording.

• Korean Journal of Pharmacognosy
• /
• v.13 no.2
• /
• pp.70-78
• /
• 1982

To investigate the effect of 'Saengkankunbi-Tang' on the liver tissue recovery in about 70% cutted rat liver, the observation on the photographing by the Gamma-camera and the electromicroscopic section against the rabbit liver induced by $CCl_4$, these studies were conducted. The results were summarized as follows; Observed on the liver tissue recovery, function regeneration and body weight increase in about 70% cutted rat liver, the recovery of liver tissue and body weight were increased with the passage of the time and also they were showed to the high increase rate in proportion to administration amount. The glucose content in the serum was found in increasing tide as compared with the control group. The alkaline phosphate activity in the serum showed the significant difference in the 10th day and 13th day as compared with the control group. The ammonia content in the blood showed the significant difference only in the 10th day. Observed on the photographing by the Gamma-camera against the rabbit liver induced by $CCl_4$, sample groups were shown to be significant recovery as compared with the control group. Observed on the electromicroscopic section, sample groups showed the control action of the nuclear destruction against the rabbit liver induced by $CCl_4$ and also they showed the control action of the expansion of glycogen and granular endothelial reticulum in cytoplasm. According to the above finding, it is presume that 'Saengkankunbi-Tang' can be applicable to the extensive treatment of liver disease.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.26 no.6
• /
• pp.601-605
• /
• 2020

In large ships with complex structures, it is difficult to locate workers. In particular, it is not easy to detect when a worker falls down, making it difficult to respond quickly. Thus, research is being conducted to detect fallen workers using a camera or by attaching a device to the body. Existing image-based fall detection systems have been designed to detect a person's body parts; hence, it is difficult to detect them in various ships and postures. In this study, the entire fall area was extracted and deep learning was used to detect the fallen shipworker based on the image. The data necessary for learning were obtained by recording falling states at the shipyard. The amount of learning data was augmented by flipping, resizing, and rotating the image. Performance evaluation was conducted with precision, reproducibility, accuracy, and a low error rate. The larger the amount of data, the better the precision. In the future, reinforcing various data is expected to improve the effectiveness of camera-based fall detection models, and thus improve safety.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.2
• /
• pp.20-32
• /
• 2010

Previous hardware devices to capture human motion have many limitations; expensive equipment, complexity of manipulation or constraints of human motion. In order to overcome these problems, real-time motion capture algorithms based on computer vision have been actively proposed. This paper presents an efficient analysis method of multiple view images for real-time motion capture. First, we detect the skin color regions of human being, and then correct the image coordinates of the regions by using camera calibration and epipolar geometry. Finally, we track the human body part and capture human motion using kalman filter. Experimental results show that the proposed algorithm can estimate a precise position of the human body.

• Journal of Broadcast Engineering
• /
• v.21 no.5
• /
• pp.704-713
• /
• 2016

Recently, the value and the status of the body that are due to the mobile wearable device have attracted attention globally confusing in media convergence age. The mobile wearable device connect worldwide that are networked to overcome the limitations of space and time, also it provide a great opportunity to be able to us to open a new cultural experience and value to the populace. In this study, spatial information acquired by the virtual reality 360 degrees camera around the Gangnam station. Also, extended spatial experience performed by use of virtual reality headset, smart phone connected to the Youtube platform. Sense of body can also lose its value due to voyeurism, it is facing the transformational period in civilization. In conclusion, through deep research into the intersections of technology and a human being for the future, maintaining the proper balance is the key. Therefore, this study identified the need for interdisciplinary research.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.4
• /
• pp.65-74
• /
• 2010

At the aim of solving the problems appearing in traditional optical motion capturing systems such as the interference among multiple patches and the complexity of sensor and patch allocations, this paper proposes a new motion capturing system which is composed of a single camera and multiple motion sensors. A motion sensor is consisted of an acceleration sensor and a gyro sensor to detect the motion of a patched body and the orientation (roll, pitch, and yaw) of the motion, respectively. Although Image information provides the positions of the patches in 2D, the orientation information of the patch motions acquired by the motion sensors can generate 3D pose of the patches using simple equations. Since the proposed system uses the minimum number of sensors to detect the relative pose of a patch, it is easy to install on a moving body and can be economically used for various applications. The performance and the advantages of the proposed system have been proved by the experiments.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.6
• /
• pp.44-56
• /
• 2008

Previous hardware devices to capture human motion have many limitations; expensive equipment, complexity of manipulation or constraints of human motion. In order to overcome these problems, real-time motion capture algorithms based on computer vision have been actively proposed. This paper presents an efficient analysis method of multiple view images for real-time motion capture. First, we detect the skin color regions of human being, and then correct the image coordinates of the regions by using camera calibration and epipolar geometry. Finally, we track the human body part and capture human motion using kalman filter. Experimental results show that the proposed algorithm can estimate a precise position of the human body.

• Korean Journal of Applied Biomechanics
• /
• v.13 no.2
• /
• pp.101-114
• /
• 2003

The purpose of this study was to examine the major kinematicak variance to Increase the club head velocity during the driver swing two PGA prp-golfers utilizing 3-dimensional Image analyzing linear velocity of the club-head during the impact quantiatively. To achive these purpose, two high speed camera in 120 field/s and one high-speed camera in 500 field/s were used in this study. The program made by Younghoo Kwon(1944) was used to analysis the digitalization of reference point, digitalization of joint venter, synchronization, calculation of 3-Dimensional coordinate by DLT method, and smoothing. Through this study, the conclusions are as follow. 1. During the drivel swing, in the percentile of the total time, two pro-golfer showed 0.925, 0.929 second from adress to top-swing, 0.236, 0.929 second from top-swing to impact. 2. During the driver swing, in the displacement of the center of the body, two pro-golfer showed 45.3, 45.23% from adress, 44.3, 44.24% front impact. 3. In the velocity variance, The maximum club-head velocity two pro-golfer showed 43.36, 43.24m/s respectively the down swing. The ball velocity showed 63.12, 63.06m/s. 4. In the rotational angle of the shoulder joint. two pro-golfer showed $-13.5,-13.53^{\circ}$, during the back swing respectively. Two subject adressed opening status og upper body. 5. In the rotational angle of the right knee angle showed $156.3,154.7^{\circ}$ from the adress.

• Journal of Electrical Engineering and Technology
• /
• v.11 no.6
• /
• pp.1857-1862
• /
• 2016

Human activity recognition using depth information is an emerging and challenging technology in computer vision due to its considerable attention by many practical applications such as smart home/office system, personal health care and 3D video games. This paper presents a novel framework of 3D human body detection, tracking and recognition from depth video sequences using spatiotemporal features and modified HMM. To detect human silhouette, raw depth data is examined to extract human silhouette by considering spatial continuity and constraints of human motion information. While, frame differentiation is used to track human movements. Features extraction mechanism consists of spatial depth shape features and temporal joints features are used to improve classification performance. Both of these features are fused together to recognize different activities using the modified hidden Markov model (M-HMM). The proposed approach is evaluated on two challenging depth video datasets. Moreover, our system has significant abilities to handle subject's body parts rotation and body parts missing which provide major contributions in human activity recognition.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.6
• /
• pp.1179-1186
• /
• 2012

In this paper, we propose an algorithm that recognizes human activity patterns using the human body's joints and the information of the joints. The proposed method extracts the object from inputted video, automatically extracts joints using the ratio of the human body, applies block-matching algorithm for each joint and gets the motion information of joints. The proposed method uses the joints to move, the directional vector of motions of joints, and the sign to represent the increase or decrease of x and y coordinates of joints as basic parameters for human recognition of activity. The proposed method was tested for 8 human activities of inputted video from a web camera and had the good result for the ration of recognition of the human activities.