• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.43 no.2 s.308
• /
• pp.11-19
• /
• 2006

In this paper, we propose a method to estimate camera extrinsic parameter based on projective and permutation invariance point features. Because feature informations in previous research is variant to c.:men viewpoint, extraction of correspondent point is difficult. Therefore, in this paper, we propose the extracting method of invariant point features, and new matching method using similarity evaluation function and Graham search method for reducing time complexity and finding correspondent points accurately. In the calculation of camera extrinsic parameter stage, we also propose two-stage motion parameter estimation method for enhancing convergent degree of LM algorithm. In the experiment, we compare and analyse the proposed method with existing method by using various indoor images to demonstrate the superiority of the proposed algorithms.

• The Academic Congress of Korean Shoulder and Elbow Society
• /
• 2008.03a
• /
• pp.165-165
• /
• 2008

A 27-year-old, right-hand-dominant woman with a posttraumatic anterior shoulder dislocation 3 months earlier after traYc accident presented because of pain and limited range of motion in the right shoulder. On physical examination, the patient had negative instability tests and a sulcus sign. On arthroscopic examination, a bifurcate long biceps tendon with two limbs was observed about 1 cm distal to the origin in the supraglenoid tubercle. We found no evidence of a tear in the long biceps tendon on probing, and the margin of each limb was smooth and round. Although this anatomic variant may be benign, its presence might be associated with other shoulder pathology. It is interesting to speculate whether the aberrant biceps anatomy in our patient contributed to transfer of injury at dislocation to the rotator cuff rather than to the classic anterior-inferior capsulolabral complex. In addition, recognition of the described anatomic variant on arthroscopy can aid the shoulder surgeon in focusing treatment on the actual pathology.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.1
• /
• pp.117-122
• /
• 2005

This paper proposes an algorithm for Facial Characteristic Point(FCP) extraction. The FCP plays an important role in expression representation for face animation, avatar mimic or facial expression recognition. Conventional algorithms extract the FCP with an expensive motion capture device or by using markers, which give an inconvenience or a psychological load to experimental person. However, the proposed algorithm solves the problems by using only image processing. For the efficient FCP extraction, we analyze and improve the conventional algorithms detecting facial components, which are basis of the FCP extraction.

• Journal of Korea Multimedia Society
• /
• v.17 no.2
• /
• pp.248-256
• /
• 2014

This paper designs a serious game for rehabilitation of patients with body pains because they sit down for a long time in the same position, or less physical movement. Activity-based game induces to player improvements in physical exercise with fun elements of the game through entertainment to help the body function and substantially increases the player's commitment during challenging goal. This research is a game design that combines the treatment of color and movement of body to the rhythm of the music. We constructed with XNA Game Studio and KINECT interface with gesture recognition technology. We need to research of evaluation system and test for the actual effect of the treatment and advanced functions of game playes like adding various musics and variety of motion.

• Journal of the Korean Society of Safety
• /
• v.35 no.2
• /
• pp.94-99
• /
• 2020

Bikers can be subjected to injuries from unexpected accidents even if they wear basic helmets. A properly designed airbag can efficiently protect the critical areas of the human body. This study introduces a wearable smart airbag system using machine learning techniques to protect human neck and shoulders. When a bicycle accident happens, a microprocessor analyzes the biker's motion data to recognize if it is a critical accident by comparing with accident classification models. These models are trained by a variety of possible accidents through machine learning techniques, like k-means and SVM methods. When the microprocessor decides it is a critical accident, it issues an actuation signal for the gas inflater to inflate the airbag. A protype of the wearable smart airbag with the machine learning techniques is developed and its performance is tested using a human dummy mounted on a moving cart.

• The Journal of Korea Robotics Society
• /
• v.15 no.1
• /
• pp.55-61
• /
• 2020

Getting on and off an elevator is one of the most important parts for multi-floor navigation of a mobile robot. In this study, we proposed the method for the pose recognition of elevator doors, safe path planning, and motion estimation of a robot using RGB-D sensors in order to safely get on and off the elevator. The accurate pose of the elevator doors is recognized using a particle filter algorithm. After the elevator door is open, the robot builds an occupancy grid map including the internal environments of the elevator to generate a safe path. The safe path prevents collision with obstacles in the elevator. While the robot gets on and off the elevator, the robot uses the optical flow algorithm of the floor image to detect the state that the robot cannot move due to an elevator door sill. The experimental results in various experiments show that the proposed method enables the robot to get on and off the elevator safely.

• Journal of Korea Multimedia Society
• /
• v.19 no.1
• /
• pp.60-67
• /
• 2016

PC users have long been controlling their computers using input devices such as mouse and keyboard. To improve inconveniences of these devices, the method of screen-touching has widely been used these days, and devices recognizing human gestures are being developed one after another. Fox example, Kinect, developed and distributed by Microsoft, is a non-contact input device that recognizes human gestures through motion-recognizing sensors, thus replacing the mouse as an input device. However, when controlling the mouse on a large screen, it suffers from the problem of requiring large motions in order to move the mouse pointer to the edges of the screen. In this paper, we propose a joystick-driven mouse-controlling method which enables the user to move the mouse pointer to the corners of the screen with small motions. The experimental results show that movements of the user's palm within the range of 30 cm ensure movements of the mouse pointer to the edges of the screen.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.91-92
• /
• 2018

As we begin to develop into an aging society, a lot of safety issues are emerging recently. Also, laws and products related to the safety and welfare of the elderly are being released. Therefore, this paper investigated the safety of the elderly. In this paper, we propose a system that can detect motion such as falling or slipping of elderly people by using gyro sensor and accelerometer to solve these factors.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.700-702
• /
• 2018

In this abstract, introduces a system that enables communication by tracking the pupils of Lou Gehrig's disease patients who are unable to move their bodies. Face and eye pupil tracking perform using OpenCV, and eye movement recognition and character selection by eye movement is obtained using Python. In this paper, you will use the webcams, track your eyes, determine eye movements based on the coordinates of your pupils, and print characters that meet your preferences. It can easily output text messages using Bluetooth.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.6
• /
• pp.237-242
• /
• 2013

There are some limitations to use the fitness center frequently by various reasons, excessive business workload, geographic location and time limit. This research specially focuses on the developement of health care application tool for aerobic/anaerobic exercise in a house accompanied by training coach, simply for the purpose of preventing from a boredom moment by exercing alone. This study newly proposes the realization of program tool by using Microsoft Kinect hardware tool which can be seen easily in the internet stores and can recognize the user. In addition, this program are designed to take care of movement control, weight and calory by maping the perceived user implementing modeling of 3D model.