Urban open space outdoor human body thermal comfort prediction method based on thermal image analysis

The invention relates to an urban open space outdoor human body thermal comfort prediction method based on thermal image analysis. The invention relates to the urban design and building environment technical field. The method comprises the following steps: carrying out gridding processing on an urban open space to obtain a plurality of regions; collecting subjective human body thermal sensation evaluation data; based on the collected thermal image of the urban open space, extracting the surface temperature of the urban open space in the thermal image; and establishing a mapping relation between the urban open space thermal image and the human body thermal comfort by adopting a convolutional neural network, and predicting the human body thermal comfort. According to the method, the problem of human resource and economic resource consumption caused by arrangement of a plurality of stations in a traditional outdoor space thermal comfort prediction method is solved, and the urban open space surface temperature is