360-degree real-time video streaming and environmental analysis system and method

A 360-degree real-time video streaming and environmental analysis method, which is performed through a system including a 360-degree streaming device having a 360-degree camera, an environmental sensor module, an embedded module, and a data analysis unit having an AI computation module, and a network connected to the 360-degree streaming device, the method comprising:

• step a) of obtaining, by the 360-degree camera, a 360-degree video of a work site;
• step b) of measuring, by the environmental sensor module, environmental data including at least one of gas concentration, temperature, humidity, and pressure data of a work environment in real time;
• step c) of processing, by the embedded module, the 360-degree video of the work site that is obtained by the 360-degree camera;
• step d) of analyzing, by the data analysis unit, the 360-degree video processed by the embedded module and the environmental data;
• and
• step e) of providing the data analyzed by the data analysis unit in real time to a site worker or remote manager and supporting the site worker or remote manager to perform safety management and response
• wherein, in step (d), the AI computation module tracks the worker in the 360-degree video processed by the embedded module and performs real-time AI analysis for worker data including at least one of face detection, person tracking, respiration and pulse analysis, and area invasion detection,
• analyzes minute color changes occurring in the worker's face in the video processed by the embedded module to detect a change in blood volume pulse (BVP) and to estimate the worker's pulse state, temporally analyzes expansion and contraction patterns of the worker's facial skin to inter a respiration rate, and thereby generates biometric information of the worker, and
• calculates a stress value by using, as respective parameters, ability of the pulse state and a degree of mismatch between the pulse state and the respiration rate while assigning predetermined weights thereto, and generates a warning notification signal when the stress value exceeds a set value.