Thermographic cameras integrated with artificial intelligence (AI) models have recently become widespread to assess thermal comfort via extracted facial skin temperature. The study aimed to examine the potential use of camera-extracted facial skin temperature to predict thermal sensation for a group of people. To deal with the limitations of previous works, this study extended the camera-subject distance, enabling the detection of multiple faces facing different orientations. Thermal sensation and thermographic data were collected from 32 subjects under transient conditions, where the air temperature gradually changed between 21 °C and 29 °C. The relationship between their subjective votes and extracted skin temperatures across five facial regions and the whole face was analyzed. Using analysis of variance, results showed that the facial skin temperatures at each sensation scale were significant differences and provided a good prediction for the 3-point thermal sensation scale. The right cheek temperature was the most potential predictor of human thermal sensation, while the forehead temperature was less accurate due to noise interference. The proposed method is cost-effective and acceptably assesses thermal comfort for multi-occupant spaces.