• The KIPS Transactions:PartB
• /
• v.16B no.5
• /
• pp.347-358
• /
• 2009

In this thesis, we develop a vision based hand motion recognition system using a camera with two rotational motors. Existing systems were implemented using a range camera or multiple cameras and have a limited working area. In contrast, we use an uncalibrated camera and get more wide working area by pan-tilt motion. Given an image sequence provided by the pan-tilt camera, color and pattern information are integrated into a tracking system in order to find the 2D position and direction of the hand. With these pose information, we estimate 3D motion plane on which the gesture motion trajectory from approximately forms. The 3D trajectory of the moving finger tip is projected into the motion plane, so that the resolving power of the linear gesture patterns is enhanced. We have tested the proposed approach in terms of the accuracy of trace angle and the dimension of the working volume.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.4
• /
• pp.529-535
• /
• 2020

It is important to secure the driver's external field view in armored vehicles surrounded by iron armor for preparation for the enemy's firepower. For this purpose, a 360 degree rotatable surveillance camera is mounted on the vehicle. In this case, the key idea is to recognize the head of the driver wearing a helmet so that the external camera rotated in exactly the same direction. In this paper, we introduce a method that uses a MEMS-based AHRS sensor and a illuminance sensor to compensate for the disadvantages of the existing optical method and implements it with low cost. The key idea is to set the direction of the camera by using the difference between the Euler angles detected by two sensors mounted on the camera and the helmet, and to adjust the direction with illuminance sensor from time to time to remove the drift error of sensors. The implemented prototype will show the camera's direction matches exactly in driver's one.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.4
• /
• pp.83-92
• /
• 2020

A recent study to determine the fall is focused on analyzing fall motions using a recurrent neural network (RNN), and uses a deep learning approach to get good results for detecting human poses in 2D from a mono color image. In this paper, we investigated the improved detection method to estimate the position of the head and shoulder key points and the acceleration of position change using the skeletal key points information extracted using PoseNet from the image obtained from the 2D RGB low-cost camera, and to increase the accuracy of the fall judgment. In particular, we propose a fall detection method based on the characteristics of post-fall posture in the fall motion analysis method and on the velocity of human body skeleton key points change as well as the ratio change of body bounding box's width and height. The public data set was used to extract human skeletal features and to train deep learning, GRU, 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 the conventional primitive skeletal data use method.

• The Journal of Korea Robotics Society
• /
• v.7 no.2
• /
• pp.120-128
• /
• 2012

The loop closure problem is one of the most challenging issues in the vision-based simultaneous localization and mapping community. It requires the robot to recognize a previously visited place from current camera measurements. While the loop closure often relies on visual bag-of-words based on point features in the previous works, however, in this paper we propose a line-based method to solve the loop closure in the corridor environments. We used both the floor line and the anchored vanishing point as the loop closing feature, and a two-step loop closure algorithm was devised to detect a known place and perform the global pose correction. We propose an anchored vanishing point as a novel loop closure feature, as it includes position information and represents the vanishing points in bi-direction. In our system, the accumulated heading error is reduced using an observation of a previously registered anchored vanishing points firstly, and the observation of known floor lines allows for further pose correction. Experimental results show that our method is very efficient in a structured indoor environment as a suitable loop closure solution.

• Journal of the Korean Society of Costume
• /
• v.23
• /
• pp.53-65
• /
• 1994

The images signifying flight in modern costumes are not made of one characteristic but the combination of complex meanings. Among the distinctive features some of them are as follows. First, the flying styles found in the costumes showed the birds as agents which sent human spirit to the celestial body. By simplifying the images of the wings connecting the present age with the heavenly body, the transforming emotions towards rhythm, direction, and organic curves transcending the real objectively constitutes a new space for expression. Second, colors appeal directly to man's emotions and incites emotional responses. The flying was shown in lines and colors. By using horizontal , vertical, oblique, and spiral lines and contrasted and paralleled colors, man's desire to fly dwells in newly colored space by reflecting speculative emotion through uniting surface. Third, the flying except for the costumes can be found in the advertisement through model's pose and camera technique, the flying itself is described through model's pose, the materials of the costumes, details, and sustaining stuffs. This symbolizes man's wish towards the unknown world vividly and dynamically. As discussed above the spirit of flying was, when expressed distinctively , in accordance with the varying cultural traits and transitions. The shape made by the vitality of symbolizing flying birds and animals along with the flying in the natural aspects such as wind and cloud were reappeared, simplified and symbolized , in modern costumes as consituting a new modeling space.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.479-480
• /
• 2023

현대 사회는 출생아가 줄어들고 고령화 현상이 빠르게 진행 중이다. 20~30대의 사회 복지 종사자가 줄어들고 노인 인구는 늘어나는 반비례 현상이 나타나고 있다. 보호자가 없는 노인에게 낙상 사고와 같은 위급상황이 발생한다면 골든타임을 놓칠 수도 있을 것이다. 따라서, 본 논문에서는 낙상 사고 발생 시, 빠른 시간 내에 실시간 모니터링을 통해 노인 복지사가 상황을 인지할 수 있게 하는 시스템을 개발하였다. 미디어파이프 포즈 모델을 이용하여 관찰 대상의 움직임을 포착하도록 하였고 PTZ 카메라의 서보 모터 제어를 통해 포착한 관찰 대상을 추적하도록 하였다. 주요 장면은 사진으로 저장해 웹 서버로 전송하고, 심박수 측정 센서와 와이파이 통신 모듈이 장착된 아두이노 보드가 실시간으로 웹 서버로 전송하여, 전담 관리자는 사진을 통해 상황을 인식하고 심박수를 보고 얼마나 위급한지 알 수 있도록 하였다.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.46 no.6
• /
• pp.479-486
• /
• 2018

In order to ensure reliable navigation performance of a lunar exploration rover, navigation algorithms using additional sensors such as inertial measurement units and cameras are essential on lunar surface in the absence of a global navigation satellite system. Unprecedentedly, Visual Odometry (VO) using a stereo camera has been successfully implemented at the US Mars rovers. In this paper, we estimate the 6-DOF pose of the lunar exploration rover from gray images of a lunar-like terrains. The proposed algorithm estimates relative pose of consecutive images by sparse image alignment based semi-direct VO. In order to overcome vulnerability to non-linearity of direct VO, we add adaptive motion prior weights calculated from a linear function of the previous pose to the optimization cost function. The proposed algorithm is verified in lunar-like terrain dataset recorded by Toronto University reflecting the characteristics of the actual lunar environment.

• The Journal of the Korea Contents Association
• /
• v.10 no.9
• /
• pp.1-8
• /
• 2010

In this paper, we propose a large scale entertainment system based on gesture recognition for learning Chinese character contents. The system is consisted of parts that forecast user's posture in two infrared images and part that recognize gestures from continuous poses. And we can divide and acquire in front side pose and side pose about one pose in each IR camera. This entertainment system is immersive in nature and convenient for its gestures based controlling system. Also, it can maximize information transmission because induce immersion and interest using two large size displays and various multimedia elements. The learning Chinese character contents can master Chinese character naturally because give interest to user and supply game and education at the same time. Therefore, it can expect synergy effect that can learn playing to user combining with large entertainment system based on gesture recognition.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.5
• /
• pp.13-24
• /
• 2011

This paper deals with a 3D-pose (orientation and position) estimation problem of a circular object in 3D-space. Circular features can be found with many objects in real world, and provide crucial cues in vision-based object recognition and location. In general, as a circular feature in 3D space is perspectively projected when imaged by a camera, it is difficult to recover fully three-dimensional orientation and position parameters from the projected curve information. This paper therefore proposes a 3D pose estimation method of a circular feature using a coplanar point. We first interpret a circular feature with a coplanar point in both the projective space and 3D space. A procedure for estimating 3D orientation/position parameters is then described. The proposed method is verified by a numerical example, and evaluated by a series of experiments for analyzing accuracy and sensitivity.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.12
• /
• pp.1574-1580
• /
• 2020

Traditional pose estimation methods include using special devices or images through image processing. The disadvantage of using a device is that the environment in which the device can be used is limited and costly. The use of cameras and image processing has the advantage of reducing environmental constraints and costs, but the performance is lower. CNN(Convolutional Neural Networks) were studied for pose estimation just using only camera without these disadvantage. Various techniques were proposed to increase cognitive performance. In this paper, the effect of the skip connection on the network was experimented by using various skip connections on the joint recognition of the hand. Experiments have confirmed that the presence of additional skip connections other than the basic skip connections has a better effect on performance, but the network with downward skip connections is the best performance.