Abstract: The present provides a visual positioning method and system based on a Gaussian process and a storage medium. The method includes: collecting image of surrounding environment and moving trajectory points while traveling (S100); extracting global features and semantic features from images (S200); processing the extracted global features and semantic features and the moving trajectory points according to a preset processing rule to obtain a Gaussian process observation model (S300); and reconstructing a Bayes filtering framework according to the Gaussian process observation model, endowing a current trajectory with an initial position point, and generating a next position point of the current trajectory, the next position point being used for providing a positioning guidance for navigation (S400). An association between a current state and a historical state can be established, so that the accuracy of a predicted next position point is improved, and accurate navigation can be provided for a robot motion.