인문학
사회과학
자연과학
공학
의약학
농수해양학
예술체육학
복합학
DBpia AI
AI 에이전트
AI 아이디어
AI 리더
AI 뷰어
Citeasy
크롬 서지관리 다운로드
지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
피인용 0
초록·키워드
Objective: The aim of this study is to develop recommendations for optimal analysis methods in non-contact work posture evaluation using a depth camera.
Background: The assessment of occupational loads, aimed at preventing musculoskeletal disorders, has primarily relied on manual methods such as photo and video recording. These methods, which depend on visual observation, have inherent limitations in accuracy and reliability. Therefore, recommendations on a non-contact evaluation system utilizing depth cameras are needed to enhance accuracy, reliability, and applicability in industrial settings while reducing costs.
Method: Five common working postures frequently observed in industrial sites were identified and defined. Two separate experiments were conducted. The first experiment used a depth camera, with independent variables set as working postures (5) and camera angles (5). The second experiment used manual evaluation, with the independent variable set as working postures (5). The OWAS (Ovako Working Posture Analysis System) action level result was used as the common dependent variable in both experiments. In the depth camera experiment, OWAS results were generated in real time using JACK human simulation software.
Results: In the depth camera experiment, accurate skeletal information was collected only at 0° and 45° angles. Other angles made measurements difficult, highlighting the challenge of accurate data collection when the subject's body is not fully within the camera's view. The posture involving a 180° body rotation was particularly challenging to measure and was excluded from manual assessments. However, OWAS evaluations were consistent between depth camera and manual assessments.
Conclusion: When assessing workload using depth cameras, evaluations can be easily conducted at any time through human simulation software, saving time and costs and providing real-time verification of results. It is essential to adjust the camera angle to ensure that equipment or objects do not obscure the worker's body. If obstacles are present, capture the worker's posture at angles between 0° (frontal) and 45°. For movements involving a 180° torso rotation, segment the task actions and reposition the depth camera before conducting the evaluation.
Application: These findings can serve as foundational data for evaluating work posture using depth cameras.
Background: The assessment of occupational loads, aimed at preventing musculoskeletal disorders, has primarily relied on manual methods such as photo and video recording. These methods, which depend on visual observation, have inherent limitations in accuracy and reliability. Therefore, recommendations on a non-contact evaluation system utilizing depth cameras are needed to enhance accuracy, reliability, and applicability in industrial settings while reducing costs.
Method: Five common working postures frequently observed in industrial sites were identified and defined. Two separate experiments were conducted. The first experiment used a depth camera, with independent variables set as working postures (5) and camera angles (5). The second experiment used manual evaluation, with the independent variable set as working postures (5). The OWAS (Ovako Working Posture Analysis System) action level result was used as the common dependent variable in both experiments. In the depth camera experiment, OWAS results were generated in real time using JACK human simulation software.
Results: In the depth camera experiment, accurate skeletal information was collected only at 0° and 45° angles. Other angles made measurements difficult, highlighting the challenge of accurate data collection when the subject's body is not fully within the camera's view. The posture involving a 180° body rotation was particularly challenging to measure and was excluded from manual assessments. However, OWAS evaluations were consistent between depth camera and manual assessments.
Conclusion: When assessing workload using depth cameras, evaluations can be easily conducted at any time through human simulation software, saving time and costs and providing real-time verification of results. It is essential to adjust the camera angle to ensure that equipment or objects do not obscure the worker's body. If obstacles are present, capture the worker's posture at angles between 0° (frontal) and 45°. For movements involving a 180° torso rotation, segment the task actions and reposition the depth camera before conducting the evaluation.
Application: These findings can serve as foundational data for evaluating work posture using depth cameras.
본문·목차
인공지능 문자 인식 모델을 통해 추출된 텍스트로, 일부 오타나 오류가 포함될 수 있으나 지속적으로 개선 중입니다.
오류를 발견하셨다면 해당 부분을 드래그한 후 ' 를 통해 신고해주세요.
오류를 발견하셨다면 해당 부분을 드래그한 후 ' 를 통해 신고해주세요.
최근 본 자료 전체보기
UCI(KEPA) : I410-151-25-02-092111208
