The pulse situation is a kind of biological signal that can be detected during the dynamic process in human body circulation system. In order to obtain more pulse information, the mathematical model of the space measurement principle has been established according to the characteristics of the thin film grid in the pulse image sensor, which is build on the self-developed pulse image sensor with monocular vision. The corners of pulse image in each successive frame are tracked and matched by the corner detection algorithm Harris, and the three-dimensional information of the pulse situation is reconstructed. The pulse images of the normal pulse, the slippery pulse, the slow pulse and the soft pulse were obtained and analyzed by experiment. The three-dimensional reconstruction of the pulse image is realized. It has laid a foundation to extract more features that characterize the pulse states in the space-time domain.