The effect of motor imagery applied to dysphagia patients with Wallenberg syndrome has not yet been reported. This trial aimed to investigate the effect and mechanism of motor imagery based on action observation treatment in the rehabilitation of patients with dysphagia in Wallenberg syndrome. A randomized controlled trial. The setting was in-patient. Thirty patients with dysphagia of Wallenberg syndrome. The patients were divided into the experimental group and the control group. Both groups received conventional dysphagia treatment, and the experimental group underwent the addition of motor imagery based on action observation treatment to the control group once a day for 14 days. Overall swallowing function was assessed with specific scales before and after intervention. Meanwhile, the functional near infrared spectroscopy was used to detect changes in cerebral hemodynamics during the execution of volitional swallowing task and swallowing motor imagery. The standardized swallowing assessment score (P=0.030), Murray secretion scale score (P=0.044) and swallowing quality of life score (P=0.011) of the experimental group improved better than those of the control group. In addition, multiple brain regions of the cortical presented extensive activation (P<0.05) during the execution of swallowing motor imagery. Moreover, there were significant differences (P<0.05) in brain regions pre-motor and supplementary motor cortex, right primary motor cortex, and right primary somatosensory cortex of the experimental group before and after treatment. The present study indicated that motor imagery based on action observation treatment could improve swallowing function for patients with dysphagia of Wallenberg syndrome as an add-on training. As a top-down rehabilitation training, the mechanism of this therapy may be related to the selective activation of mirror neuron system. Motor imagery based on action observation treatment can be implemented as part of the therapeutic for dysphagia of Wallenberg syndrome.