Cooperative automated driving system is nowadays considered as one of the main solutions to solve traffic congestion without high vehicle cost. Due to the complexity of these systems, simulation is a high cost-efficient way to optimize their performance and the cooperation strategy of different components in them. However, sensor models with high validity and fidelity are required for an effective test in simulation. Camera model, as one of the sensor modelled used in cooperative automated driving system simulation, should be proven valid enough for neural network-oriented recognition algorithms in cooperative automated driving systems. The conventional image quality evaluation methods can only assess image quality statistically and therefore are not suitable to be used for this kind of evaluation. This paper introduces a general method for neural network algorithm faced image quality evaluation for sensor models. Evaluation results of a sensor model are exemplarily presented.