• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.04a
• /
• pp.770-772
• /
• 2015

어미로부터 생후 21일령 또는 28일령에 젖을 때는 이유자돈들만을 개별적인 돈사에서 합사하는 경우, 낯선 환경 및 새로운 동료들과의 서열 구분을 위한 공격적인 행동이 매우 빈번하게 발생한다. 이로 인한 돼지의 성장 저하는 농가의 소득 하락으로 이어져 국내 외 양돈 농가의 큰 문제로 인식되고 있다. 본 논문에서는 키넥트 카메라에서 취득할 수 있는 영상의 깊이정보를 이용하여 이유자돈들의 공격적인 행동을 조기 탐지할 수 있는 프로토타입 모니터링 시스템을 제안한다. 먼저 제안한 시스템은 키넥트의 적외선 센서에서 실시간으로 취득하는 깊이 정보로부터 움직임이 있는 객체들만을 탐지하고, 해당 객체들의 ROI를 설정한다, 둘째, ROI를 이용하여 5가지 특정 정보(객체의 평균, 최고, 최소 속도, 객체 속도의 표준편차, 두 객체 사이의 최소 거리)를 추출한다. 셋째, 취득한 특징 정보는 이진 클래스 분류 문제로 해석하여, 기계학습의 대표적인 모델인 SVM을 탐지기로 사용하였다. 실제 이유자돈사에서 취득한 키넥트 영상을 이용하여 모의 실험을 수행한 결과 안정적인 성능을 확인하였다.

• Proceedings of the Korean Society of Marine Engineers Conference
• /
• 2012.06a
• /
• pp.164-164
• /
• 2012

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.10
• /
• pp.303-310
• /
• 2016

Recently there has been growing popularity in exergame, such as Wii Sport or Xbox Fitness game, which enables users to get physical exercise while playing the games. In such experienced exercise games, the user's posture recognition is very important to find out exactly how much the users need to take their body posture as compared to the proper posture. This paper proposes a new exercise posture recognition model designed for the exercise game content for the elderly. The proposed model is based on extracting feature points of a skeleton model provided by the Kinect sensor to generate the feature vectors to recognize the user's exercise posture information. This paper describes the design and implementation of the exercise posture recognition model and demonstrates the feasibility of this proposed posture recognition model through a simple experiment. The experimental results showed 94.52% of average accordance rate for 12 exercise postures of 10 participants.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.10a
• /
• pp.185-188
• /
• 2017

Health promotion is essential for overcoming the low health longevity of senior citizens preparing for aging population. Therefore, the lower body strengthening exercise to prevent falls is crucial to prevent a fall in the number of deaths of senior citizens. In this game model, the elderly are aiming at home training contents that can be found to feel that the elderly are going out of walk and exercising in the natural environment. To achieve this, Kinect extracts a specific bone model provided by the Kinect Sensor to generate the feature vectors and recognizes the movements and motion of the user.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.109-110
• /
• 2019

본 논문에서는 Kinect sensor의 음성 인식 기능을 활용한 매장 주문 어플리케이션을 설계하고 구현한다. 노년층과 유아들은 무인주문결제시스템의 터치스크린 조작 및 사용자 인터페이스에 익숙하지 않기 때문에 매장에서 상품을 주문하고 결제하는데 불편함을 경험하고 있다. 이러한 불편함을 제거하기 위한 하나의 방법으로 키넥트 센서의 음성 인식 기능을 이용하여 음성으로 쉽게 주문을 할 수 있는 매장 주문 어플리케이션을 개발한다. Kinect에는 4개의 오디오 마이크로폰이 있어서 $-50^{\circ}{\sim}50^{\circ}$ 범위의 음성을 인식할 수 있으며 20db 이하의 주위 소음은 무시한다. 이 범위내에서 $10^{\circ}$씩 증가시키면서 음원의 위치를 추적한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.1
• /
• pp.167-174
• /
• 2016

In this paper, we propose a generation of 2D elemental images for 3D objects using Kinect in 3D depth-priority integral imaging (DPII) display. First, we analyze a principle to pickup elemental images based on ray optics. Based on our analysis, elemental images are generated with both RGB image and depth image recorded from Kinect. We reconstruct 3D images from the elemental images with the computational integral imaging reconstruction technique and then compare various perspective images. To show the usefulness of the proposed method, we carried out the preliminary experiments. The experimental results reveal that our method can provide correct 3D images with full parallax.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.510-511
• /
• 2017

In this paper, a study was conducted to prevent spinal - related diseases and to help posture correction by feeding back the wrong attitude to the users. Kinect sensor was used for this purpose. In order to measure the movement of the user, the degree of motion change was measured by indexing the skeletal data coordinate value. It is confirmed that the implemented system can observe not only posture but also distraction of user.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2012.07a
• /
• pp.315-317
• /
• 2012

본 논문에서는 인체의 골격 위치와 깊이 정보를 사용하여 주위 환경에 강건한 특성을 지니는 움직이는 사람 영역 검출 방법을 제안한다. 먼저 영상 내에서 인체의 골격 위치를 검출한 다음 인체 골격의 중심이 될 수 있는 지점에 대해 인체의 평균적 깊이 범위 내에서 깊이 세분화를 수행한다. 그리고 깊이 세분화를 통하여 검출된 사람 영역의 후보군에 대해 윤곽선 기반의 움직임 검출기법을 사용하여 후보군 내에서 움직이는 사람에 해당하는 특징점을 검출한다. 마지막으로 잡음 제거 및 움직이는 사람에 해당하는 영역 검출을 위하여 개선된 깊이 세분화 과정을 수행한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.12
• /
• pp.2297-2304
• /
• 2016

In this study, we designed and developed the virtual reality Exergame using the smart mat and the camera sensor for exercises in indoor environments. For detecting the gestures of a upper body of users, the KINECT camera based the gesture recognition algorithm used angles between user's joint information system was adopted, and the smart mat system including a LED equipment and Bluetooth communication module was developed for user's stepping data during the exercises that requires the gestures and stepping of users. Finally, the integrated virtual reality Exergame system was implement along with the Unity 3D engine and different kinds of user' virtual avatar characters with entertainment game contents such as displaying gesture guideline and a scoring function. Therefore, the designed system will useful for elders who need to improve cognitive ability and sense of balance or general users want to improve exercise ability and the indoor circumstances such home or wellness centers.

• The Journal of the Korea Contents Association
• /
• v.22 no.3
• /
• pp.593-605
• /
• 2022

The purpose of this study is to investigate the personalized treacmill exercise analysis using a smart mirror based on Kinect sensor. To evaluate the performance of the development system, 10 health males were used to measure the range of the hip joint, knee joint, and ankle joint using a smart mirror when walking on a treadmill. For the validity and reliability of the development system, the validity and reliability were analyzed by comparing the human movement data measured by the Kinect sensor with the human movement data measured by the infrared motion capture device. As a result of validity verification, the correlation coefficient r=0.871~0.919 showed a high positive correlation, and through linear regression analysis, the validity of the smart mirror system was 88%. Reliability verification was conducted by ICC analysis. As a result of reliability verification, the correlation coefficient r=0.743~0.916 showed high correlation between subjects, and the consistency for repeated measurement was also very high at ICC=0.937. In conclusion, despite the disadvantage that Kinect sensor is less accurate than the motion capture system, Kinect is it has the advantage of low price and real-time information feedback. This means that the Kinect sensor is likely to be used as a tool for evaluating exercise prescription through human motion measurement and analysis.