Abstract. A stereoscopic visual fatigue measurement model based on Bayesian networks (BNs) is presented. Our approach focuses on the interdependencies between factors, such as contextual and environmental, and the phenomena of visual fatigue in stereoscopy. Specifically, the implementation of BN with the use of multiple features provides a systematic way to project and evaluate visual fatigue. Compared with another measurement model, our present BN-based scheme is more comprehensive. The test validation also indicates that our proposed model can be used as a reliable method for the visual fatigue inferring in stereoscopy.