Infrared Target Simulation Method Based on Generative Adversarial Neural Networks

A model applied to the simulation of infrared targets is proposed. By the trained conditional deep convolutional generative adversarial networks, only the random noise and category label arc necessary for the automatic generation of the simulation images of infrared targets belonging to the expected category. The parameters arc trained on the handwritten digital dataset ( MNIST) and the infrared dataset, respectively, and subsequently the automatic generation experiment is carried out, which can produce the high trueness sample images. The features extracted by the discrimination network arc used in the classification experiments, and the images synthesized by the proposed method arc used for data augmentation to improve the classifier performance. The research results show that the proposed method can effectively imitate the infrared radiation characteristics.