Method and system for calculating occupant activity using occupant pose classification based on deep learning

摘要

The present invention relates to a method and system for calculating the occupant activity amount using deep learning-based occupant pose classification, and the method for calculating the occupant activity amount using the deep learning-based occupant pose classification detects the occupant from the indoor image collected by the camera sensor Step of calculating the joint coordinate value of the occupant by learning the characteristics of the occupant image: classifying the indoor activity pose of the occupant through the deep learning by inputting the acquired positional coordinates of the human joint and classifying the amount of activity (MET) Obtaining; And calculating the activity amount of the occupant required for controlling the indoor thermal environment using the indoor activity poses of the occupant classified by a predetermined time unit and the acquired activity amount. According to the present invention, as a model for measuring the MET of the occupants required when introducing the PMV control method for indoor comfort control, the occupant activity amount calculation model can be used to control the indoors along with other environmental variables and improve satisfaction in comfort range. have. Since only the camera sensor is used and the image of the occupant is analyzed to measure the pose and the amount of activity, the occupant does not need to operate or attach the device directly, so it is applicable. In addition, it is possible to reduce errors by determining the actual action being taken, rather than indirectly measuring the incidental information of the occupant's activities.