The invention discloses a four-rotor aircraft adaptive neural network positioning control method based on visual feedback. The method comprises the following steps of S1, determining a kinetic model equation of a four-rotor aircraft (QAR) according to the principles of aerodynamics and rigid mechanics, S2, establishing equivalent transformation between a position error and a projection image error by adopting a spherical projection method according to the kinetic model equation, S3, determining a linear velocity error differential equation of the QAR according to the spherical projection method and the kinetic model equation, S4, constructing a backstepping virtual attitude controller according to the linear velocity error differential equation of the QAR, S5, according to the backstepping controller, determining an operation equation of the adaptive controller based on the neural network, S6, according to the operation equation of the adaptive controller, constructing an inertia matrix estimator based on the Jorleski decomposition, and S7, calculating the position of the QAR according to the operation equation of the adaptive controller and the adaptive law equation, thereby realizing QAR visual position tracking control.