Abstract: In order to carry out the monitoring experiment of Geo-synchronous orbit (GEO) targets, Shanghai Astronomical Observatory developed an equipment with 100-square-degree field of view, called "optical prototype of Geo-synchronous orbit dynamic monitoring system". There are a large number of targets in the field of view, how to recognize the GEO targets effectively from the complex observation images is the focus of this paper. GEO targets appear motionless, at a fixed position in the sky, to ground observers. Due to the earth rotation, stars move at a speed of 15"/s relative to the ground observers. We propose the combination of frame difference method and track correlation method. Frame difference method is used to remove a large number of stars from the images, and track correlation method is used to confirm the GEO targets and connect them from different images. The feasibility and accuracy of the method are verified by the analyses of the observation data. The method can recognize more than 50 GEO targets in the field of view at the same time, and the recognition accuracy exceeds 95%.