Infrared Target Recognition Technology Based on Few Shot Learning

Aiming at the problems of sparse sample data and high difficulty of embedded implementation under the constraint of limited resources in the military application of infrared target recognition, this paper proposes a lightweight target recognition technology based on few shot learning. This technology improves the structure of generator and discriminator network by designing the Cycle Generative Adversarial Network model, and realizes the migration from visible image to infrared image, so as to achieve the purpose of expanding the training data; Through the improvement of YOLOV5s network, the recognition accuracy is improved without reducing the magnitude of model parameters, and the characteristics of high real-time processing are retained. The experimental results show that the generative adversarial network model designed based on this project can process the visible image and generate the near-infrared image. After adding the training data, the model accuracy is effectively improved. The improved YOLOV5s model is 2% higher than the original model map 0.5, and is easier to be embedded.