선박은 크고, 복잡한 구조로 되어 있기 때문에 다른 작업자의 위치를 알아내기 어려우며, 특히 작업자가 쓰러진 경우에는 발견하기가 쉽지 않아 신속한 대처가 어렵다. 그리하여, 신체에 디바이스를 부착하는 방법이나 카메라를 이용하여 쓰러짐을 검출하기 위한 연구가 진행되고 있다. 기존의 영상기반 쓰러짐 검출은 사람의 신체부위를 검출하여 쓰러짐을 판단하였으나, 조선소에서는 다양한 복장과 자세로 작업으로 인해 검출하기가 어렵다. 본 논문에서는 쓰러짐 영역 전체를 추출하여 딥러닝 학습으로 선박 작업자의 쓰러짐을 이미지 기반으로 검출하였다. 학습에 필요한 데이터는 조선소의 건조중인 선박에서 쓰러진 모습을 연출하여 획득하였으며, 이미지를 좌우대칭, 크기조절, 회전하여 학습 데이터의 수를 증가하였다. 성능평가는 정밀도, 재현율, 정확도 그리고 오차율로 평가하였으며, 데이터의 수가 많을수록 정밀도가 향상되었다. 다양한 데이터를 보강하면 카메라를 이용한 쓰러짐 검출 모델의 실효성이 향상됨으 로서 안전 분야에 기여할 수 있을 것으로 사료된다.

The purpose of this study was to examine associations between subjective symptoms of musculoskeletal diseases and the degree of job stress among shipyard workers. The study population was 7,078 employees of the D shipbuilding company. Survey data was obtained from 1,727 employees using a proportional sample according to age and a self-administered questionnaire. The associations were examined with and logistic regression. The main results were as follows: First, the prevalence of musculoskeletal disease in any one part is 59.5% by NIOSH standard. Second, subjects who had worked in the shipyard for over five years had a prevalence of musculoskeletal disease 1.8 times higher than subjects who had worked in the shipyard for less than five years (p<.01). Finally, those who had less support from co-worker's had a prevalence of musculoskeletal disease 1.3 times higher than subjects who had more support from co-worker's (p<.05). Throughout the results, shipyard workers had higher occurrences of musculoskeletal diseases than other manufacturing workers and the risk of musculoskeletal disorder tended to increase with higher job stress. In this research, the plan to reduce musculoskeletal diseases involved making a program and policy which would be able to lower job stress socio-psychologically. This research will prove useful by using basic preventive materials to improve the musculoskeletal health of labores who work in shipyards and similar places.