Extracting video structures is important for video indexing and navigation in large digital video archives. It is usually achieved by video segmentation algorithms. Little research efforts has been invested on segmentation solutions that utilize the video's emotional content. These solutions not only have the potential of providing better performances than existing segmentation methods, but are also able to provide a more natural video segmentation with which viewers can associate with. The development of an affect-based segmentation solution faces many challenges, such as the dynamic and time evolving nature of a video's emotional content. This paper introduces a novel computation method for affect-based video segmentation. It is designed based on the Pleasure-Arousal-Dominance (P-A-D) emotion model, which in principle can represent a large number of emotions. This method consists of a P-A-D estimation stage and a segmentation stage. A P-A-D estimator based on the Dynamic Bayesian Networks (DBNs) is proposed for the first stage. A clustering-based algorithm that utilizes the video's P-A-D information is proposed for the second stage. Experimental results demonstrate the feasibility of the method.