To realize the adaptive nonuniformity correction of infrared focal plane arrays (IRFPA) is very important for an advanced infrared detection system. With the increase of the complexity and scale, the correction system algorithms are more difficult to be designed. A system-level modeling method based on OO-TDPN is used to model an IRFPA nonuniformity correction system based on the BP neural network from top to bottom hierarchically. In the modeling method, the abstracted system object class is specified; then, a hierarchical model based on polymerization of object class is established for the system; finally, the Verilog language is used to specify the model and simulation is carried out in the simulation environment. The simulation result shows that the model is correct and the method is feasible.