본 연구에서는 노인의 건강 증진 및 건강 유지를 위해 노인 맞춤형 운동 애플리케이션 개발을 목표로, 스마트폰을 활용한 실시간 동작 추적 기술과 영상과 사진을 바탕으로 한 AI 학습을 통 해 단계별 동작 인식과 판단이 가능한 운동 동작 모델을 구현하였다. 노인 맞춤형 운동 애플리 케이션은 실시간 피드백을 지원하고, 노인의 운동 능력과 신체 가동 범위에 적합하게 단계적 운동이 가능하도록 구현되어야 할 것이다. 이를 위해 본 논문에서는 골포스트 스퀴즈(Goal Post Squeeze) 운동 동작을 대상으로 하여 이를 일련의 단위 동작으로 설계하고, MoveNet 포 즈 추정 기법을 기반으로 동작 인식 모델을 개발하였다. 구현한 운동 동작 모델에 대한 작동 실험 결과 단계별 데이터 인식과 판단, 정동작과 오동작 판단, 수평유지를 판단하고 이를 바탕 으로 사용자에게 실시간 피드백을 제공할 수 있음을 확인하였다.

More than 6,000 power tiller accidents occurred in 2015, accounting for 50% of all agricultural machinery accidents. Despite this, educational institutions for farmers are only conducting theoretical education due to lack of training systems with guaranteed safety. This study developed an object motion tracking algorithm enabling trainees to control a power tiller driving simulator while wearing a HMD(head mounted display) in order to provide safe hands-on training equipment. A power tiller driving simulator was built using encoders, proximity sensors and displacement sensors to detect the locations of various operating devices such as steering clutch, and a computer model for this simulator was designed. Center coordinate synchronization of the driving simulator and the computer model was achieved with a tracker, and the motion of the power tiller driving simulator was tracked by computing position coordinates and rotation angles of the simulator. The maximum distance error was 23mm, and there was no difficulty maneuvering the driving simulator while wearing an HMD, even at maximum distance error. This motion tracking algorithm is expected to be applicable to the development of mixed reality based power tiller driving simulators for training, contributing to the reduction of power tiller accidents.

Recently, robot-assisted joint replacement surgeries are on the rise. Robot-assisted surgery can make more accurate outcome, and thus it will be more popular. For the accurate result, secure fixation of bone is necessary, but there are numerous difficulties for the secure fixation. Detecting bone motion is necessary to prevent some errors. Currently, optical sensor and location sensor are in use; however, these sensors can cause interventional problem for the friction between mechanical devices. This study shows how to compose the bone motion detecting device using electromagnetic sensor, how to commercialize the bone motion detecting device.

This study introduces an efficient image-based three-dimension motion tracking system for civil structures. The proposed system consists of hardware (four camcorders, a commercial PC and frame grabber) and software. The effective software and measurement scheme are developed to obtain the dynamic motion with six degrees of freedom. Several laboratory tests were conducted to verify the effectiveness of the proposed system with the maximum error of less than 3%.

This paper presents a method, Exposure Controlled Temporal Filtering (ECF), applied to visual motion tracking, that can cancel the temporal aliasing of periodic vibrations of cameras and fluctuations in illumination through the control of exposure time. We first present a theoretical analysis of the exposure induced image time integration process and how it samples sensor impingent light that is periodically fluctuating. Based on this analysis we develop a simple method to cancel high frequency vibrations that are temporally aliased onto sampled image sequences and thus to subsequent motion tracking measurements. Simulations and experiments using the ‘Center of Gravity’ and Normalized Cross-Correlation motion tracking methods were performed on a microscopic motion tracking system to validate the analytical predictions