The study examined the relationship between workers’safety awareness, safety performance and the components of the intelligent image analysis system in accordance with preventing the workers from safety hazard in dangerous working area. Based on the safety performance model, we include safety knowledge, safety motivation, safety compliance and safety participation, and we also define three additional factors of the intelligent image analysis system such as functional feature, penalty and incentive by using factor analysis. SEM(Structural Equation Modeling) analyses on the data from the total of 73 workers showed that functional feature of intelligent analysis system and incentive were positively related to safety knowledge and safety motivation. And mediation effects of the relationship were verified to safety compliance and safety participation through safety knowledge as well.

To prevent safety hazards in dangerous working area, we have proposed an intelligent image analysis system. Six common patterns of safety violations of workers’ are defined and its motion detection algorithms are developed for alarm to CCTV　monitoring system. Developed algorithms are implemented at 195 dangerous areas such as chemical and gas treated room. The results of violated motion detection ratio by developed system shows 94.95% of true positive cases, and 0.21% of false positive cases from all 587,645 event cases in one month implementation period. In the period, it is observed that the number of safety rule violations and the following accidents are decreased.

해양경찰 경비함정에서 근무하는 경찰관, 전경 등 승조원이 바다로 추락하는 사고가 발생할 경우 CCTV 영상을 실시간으로 분석하여 경보를 발령하고 즉시 구조할 수 있는「함정 승조원 추락 경보 시스템」을 개발하였다. 길게는 7박 8일의 출동 임무를 수행하는 함정요원들은 수시로 급변하는 해상기상의 영향을 많이 받는 함상생활 중 불의의 추락사고를 당할 위험에 노출 돼 있는 것이 사실이다.