Tyre crane control method and system based on vision

The invention provides a tire crane control method and a tire crane control system based on vision, which are used for controlling a plurality of tire cranes and comprise the following steps of: determining the current state of an executing mechanism of each tire crane in the plurality of tire cranes, the state comprising running or stopping; the method comprises the following steps: acquiring video data in front of all door legs of a tire crane which is currently in a running state; performing inference analysis on the video data by using a pre-trained deep learning model, and determining whether an obstacle or area intrusion exists in front of a door leg of the corresponding tire crane; if yes, an emergency stop instruction is sent to a controller used for controlling a corresponding tire crane executing mechanism; and scheduling the tire crane videos to be displayed on the plurality of display screens according to the number of the tire cranes currently in the running state and the number of the tire crane