• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.41-42
• /
• 2020

전 세계적으로 코로나 바이러스가 확산되면서 언택트 시대가 되었다. 언택트 시대에서는 대부분의 대면활동이 비대면으로 전환되고 있다. 전 세계적으로 열광중인 케이팝 댄스의 대중화를 위해 우리는 비대면으로 댄스 학습이 가능한 DETR 기반 객체탐지를 사용한 댄스 자세교정 연구를 제안한다. 본 논문에서 제안한 댄스 자세교정은 객체탐지에 DETR을 적용한 방식이다. DETR은 기존 객체탐지 모델에서 앵커박스, 바운딩박스 중복처리를 제거하는 NMS같은 휴리스틱한 방법을 사용하지 않고 트랜스포머를 통해 자동으로 학습하도록 만든 모델이다. DETR로 객체탐지를 한 후 강사와 사용자의 동작유사성을 샴 뉴럴 네트워크를 통해 계산한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.87-88
• /
• 2023

본 논문에서는 COVID-19 팬데믹으로 인해 사회적 거리두기 및 규제조치가 시행되면서 다양한 분야에서 큰 영향을 가져왔다. 변화된 홈트레이닝 분야는 운동기구를 구비하여 개인운동을 통해 건강을 유지하고 있으나 전문적인 교육을 받지 않은 홈트레닝으로 부상 위험에 노출 되고 있다. 요가는 호흡운동과 명상을 지향하는 운동으로 요가의 효과를 얻기 위해 올바른 움직임과 자세가 중요 하다. 본 논문에서는 실시간으로 입력된 영상 프레임을 OpenCV와 MediaPipe를 통해 추출된 주요좌표 값을 벡터 내적공식을 대입, 코사인2법칙을 통해 요가의 올바른 자세를 분석하여 종합적인 정보를 제공하는 요가교정 모델이다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.2
• /
• pp.304-310
• /
• 2010

Chronic pain and herniated disk is a common disease that 80% of adults are experienced. There diseases rates of caused by the physical shock, such as the traffic accident, and the accidental fall is about 10%. And the most of these diseases is caused by having habitual incorrect position. People know that incorrect position would cause to accumulate continuous stress, but it is not easy to correct position. Because it does not recognize incorrect position repeated habitual consequently. This system collects data of user position after sensors that could measure position attach on use and presumes correct position used by position presumption algorithms. Its system purpose is continuing incorrect position could be aware to user and lead to change to correct position to prevent habituation of incorrect position. If habitual of correct position continues through accurate measurement and repeating cognitive learning, it would help for children and chronic patience.

• Journal of Digital Contents Society
• /
• v.19 no.2
• /
• pp.245-250
• /
• 2018

Ab Image Processing can be applied to the various fields nowadays. The healthcare, which people may have interest, is one of those fields. The healthcare program which fitness equipments are used requires the correct posture of body. However, people usually does exercise by oneself with various reasons such as cost to hiring personal trainer. In this case, the effectiveness of training should not be guaranteed. Moreover, reverse effect may be produced. This paper is an implementing a correcting posture program by using image processing techniques, which people can use exercise training by oneself. It is expected that people can have a personal trainer who coaches the correct postur through this program.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2016.07a
• /
• pp.217-218
• /
• 2016

본 논문에서는 매년 증가하고 있는 청소년 허리질환의 문제를 해결하고자 가성비가 높은 스마트 방석을 개발하였다. 스마트 방석은 일반 방석에 압력센서 4개를 장착하고 앉은 사람의 자세를 모니터링하여 스마트폰과 PC를 통해 실시간 또는 통계적으로 분석해 준다. 이는 사용자로 하여금 경각심을 갖도록 유도하며 좌, 우측별 불균형한 자세를 교정하도록 하는 효과를 얻을 수 있다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.489-490
• /
• 2023

본 논문에서는 신체 영상 인식 기술을 이용한 운동 자세 교정 시스템을 제안하고 개발하였다. 구글에서 제공하는 미디어파이프 포즈(MediaPipe Pose) 오픈소스를 사용하여 웹캠으로 사용자의 운동 동작을 실시간으로 인식하여, 인식된 신체 구조의 33개의 관절 위치로 Pose Landmark를 사용하여 사용자의 운동 자세에 대한 횟수 카운트, 운동 동작의 정확도 측정을 할 수 있게 하여 혼자 운동하거나 처음 운동하는 사람들에게 운동의 접근성을 높이고, 올바른 자세로 운동을 하도록 유도할 수 있다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.3
• /
• pp.115-122
• /
• 2022

With the outbreak of COVID-19 a few years ago, video conferencing and electronic document work have increased, and for this reason, the proportion of computer work among modern people's daily routines is increasing. However, as more and more people work on computers in the wrong posture for a long time, the number of patients with poor eyesight and text neck is increasing. Until recently, many studies have been published to correct posture, but most of them have limitations that users may experience discomfort because they have to correct posture by wearing equipment. A posture correction sensor algorithm is proposed to prevent access to the minimum distance between a computer monitor and a person using an ultrasonic sensor device. At this time, an algorithm for minimizing false alarms among warning alarms that sound at the minimum distance is also proposed. Because the ultrasonic sensor device is used, posture correction can be performed without attaching a device to the body, and the user can relieve discomfort. In addition, experimental results showed that accuracy can be improved by reducing false alarms by removing more than half of the noise generated during distance measurement.

• Journal of the Institute of Convergence Signal Processing
• /
• v.20 no.2
• /
• pp.99-104
• /
• 2019

Recently, modern people are increasing the incidence of various musculoskeletal diseases due to wrong posture. Prevention is possible through proper posture habit, but it is not easy to recognize posture by oneself. Various studies have been conducted to monitor persistent posture in daily life, but most studies using constrained measurement methods and high-cost measurement equipment are not suitable for daily life. In this paper, we implemented a posture discrimination system using a FSR sensor array that can induce posture correction spontaneously through sitting posture monitoring in daily life. The implemented system is designed as a cushion type so it is easy to apply to existing chair. In addition, it can identify five most common postures in everyday life, and can monitor real-time through Android-based smart-phone monitoring application. For the performance evaluation of the implemented system, each posture was measured 50 times repeatedly. As a result, 97.6% accuracy was confirmed.

• Progress in Medical Physics
• /
• v.24 no.2
• /
• pp.85-91
• /
• 2013

At present, megavoltage computed tomography (MVCT) is the only method used to correct the position of tomotherapy patients. MVCT produces extra radiation, in addition to the radiation used for treatment, and repositioning also takes up much of the total treatment time. To address these issues, we suggest the use of a video image-guided setup (VIGS) system for correcting the position of tomotherapy patients. We developed an in-house program to correct the exact position of patients using two orthogonal images obtained from two video cameras installed at $90^{\circ}$ and fastened inside the tomotherapy gantry. The system is programmed to make automatic registration possible with the use of edge detection of the user-defined region of interest (ROI). A head-and-neck patient is then simulated using a humanoid phantom. After taking the computed tomography (CT) image, tomotherapy planning is performed. To mimic a clinical treatment course, we used an immobilization device to position the phantom on the tomotherapy couch and, using MVCT, corrected its position to match the one captured when the treatment was planned. Video images of the corrected position were used as reference images for the VIGS system. First, the position was repeatedly corrected 10 times using MVCT, and based on the saved reference video image, the patient position was then corrected 10 times using the VIGS method. Thereafter, the results of the two correction methods were compared. The results demonstrated that patient positioning using a video-imaging method ($41.7{\pm}11.2$ seconds) significantly reduces the overall time of the MVCT method ($420{\pm}6$ seconds) (p<0.05). However, there was no meaningful difference in accuracy between the two methods (x=0.11 mm, y=0.27 mm, z=0.58 mm, p>0.05). Because VIGS provides a more accurate result and reduces the required time, compared with the MVCT method, it is expected to manage the overall tomotherapy treatment process more efficiently.

• Journal of the Institute of Convergence Signal Processing
• /
• v.22 no.3
• /
• pp.128-133
• /
• 2021

Recently Recently, the incidence of spinal diseases due to poor posture among students and office workers is increasing, and various studies have been conducted to help maintain correct posture. In previous studies, a membrane sensor or a pressure sensor was placed on the seat cushion to see the weight bias, or a sensor that restrained the user was attached to measure the position change. In our previous study, we developed a sensor device which can be easily attached to the body with an adhesive gel sheet and that measures and outputs the user's posture and body position in real time, but it has a limitation in the accuracy of the sensor value. In this study, a study was conducted to improve the performance of the position conversion sensor device and quantitatively evaluate the accuracy of the angle conversion measurement value, and a high accuracy with 2.53% of error rate was confirmed. In future research, it is considered that additional research targeting actual users is needed by diversifying posture correction training contents with multimedia elements added.