Temperature segregation of asphalt mixture is one of the major reasons for pavement damage. The premise of ensuring desired properties of the asphalt mixture is to propose a reliable measuring method to monitor temperature variations before paving. Few existing studies focus on this issue due to the absence of suitable and efficient measuring instruments. This study proposes an innovative method to evaluate the temperature variation of asphalt mixture throughout the transportation process by combining the infrared camera and machine learning algorithms. Static and dynamic field tests are performed to measure the contact and non-contact temperatures of the asphalt mixture. A set of temperature measuring probes is specially designed. Influences of the measuring depth, measuring location, and environmental conditions are considered. Correlations between the infrared temperature and the contact temperature are identified using regression model, Support Vector Regression (SVR), and Extreme Gradient Boosting (XGBoost). The accuracy of the proposed model is verified against the experimental result.