Objectives: The proposed Occupant Count Measurement (OCM) model aims to enhance sustainability, energy efficiency, comfort, and safety in smart buildings by accurately determining occupant count using thermal camera images and body temperature data. Methods: The model leverages real-time thermal camera images without the need for a pre-existing dataset. Key parameters include temperature threshold, occupant motion, size, and shape to ensure accurate occupancy estimation. The K-means algorithm identifies and clusters regions of interest (ROI) in thermal images corresponding to human body temperatures. The model also employs sensors like PIR, RGB cameras, and thermal image sensors. Manual counting serves as a benchmark for comparison. Findings: The K-means algorithm extracts regions with elevated temperatures related to human bodies from thermal images, partitioning them into K-clusters based on temperature ranges and assigning each pixel to one of the clusters. A temperature threshold differentiates human clusters in the thermal image, while connected component labeling refines human object segmentation by identifying blobs, which are then used for occupant counting. The model's precision is assessed using diverse image sensors and compared to the actual number of occupants. The proposed OCM model achieves an accuracy of about 90.2% compared to traditional methods. Novelty: This study introduces an OCM model that uses thermal images to estimate the number of occupants in a room based on their body temperature. The method focuses on detecting and counting occupants by their overall thermal body signature, providing a novel approach to occupant measurement in smart buildings. Keywords: Thermal Images, Segmentation, Occupant Estimation, Occupant Comfort, Smart Building