Unlike static objects,dynamic objects have the characteristic of real-time changes,which increases the difficulty of target recognition.To accurately recognize dynamic objects in monocular AR environment,this paper pro-posed an algorithm for dynamic object recognition.Firstly,we collected a series of dynamic object images in monocular AR environment through a camera.Then,we used the MMTD and soft threshold filtering method to filter the target images.Next,we introduced the Hough transform method to obtain the straight-line information of the dy-namic target,thus obtaining the position and orientation of the dynamic object through pattern recognition.According to this information,we achieved dynamic object recognition.The experimental results show that the proposed algorithm can accurately recognize dynamic targets in a short time with low target recognition error.Therefore,this method has certain reference value for dynamic image recognition.