Automatic target recognition method based on load pre-training convolutional network

Abstract

The invention provides an automatic target recognition method based on a load pre-training convolutional network. The automatic target recognition method mainly comprises the steps of network reconstruction, network characteristic synthesis, classifier conversion and network model fine-adjustment, and the process of the method is that module splitting is performed by using a trained convolutionalnetwork framework, reconstruction is performed according to a target recognition task on the premise of weight retaining, and meanwhile the last layer of all original connecting layers is retained toserve as extracted characteristics, is attached with a response label and then is sent to a support vector machine based on a Gaussian kernel for training test. By adopting the method, target form recognition of only small sample databases can be processed, a network migration frame is provided for weight retaining and fine adjustment, and meanwhile the training speed and transferability of targetrecognition tasks are improved.

Description

technical field [0001] The invention relates to the field of target recognition, in particular to an automatic target recognition method based on loading a pre-trained convolutional network. Background technique [0002] The automatic target recognition method is a technology that uses artificial intelligence technology to realize the classification and intelligent recognition of target features obtained by machine sensors. It is an extended development of pattern recognition and one of the research hotspots in recent years. As one of the core technologies of intelligent weapons and equipment, automatic target recognition is widely used in the field of military operations, providing strong support for target detection, reconnaissance and surveillance, and precision guidance in information warfare. But as civilian technology develops, these technologies also serve people well in everyday life. For example, in traffic facilities, it can automatically identify whether the vehi...

AI Technical Summary

Problems solved by technology

[0005] Aiming at solving the problem of performing target recognition tasks in a small amount of sample data, the purpose of the present invention is to provide an automatic target recognition method based on loading pre-trained convolutional networks, and propose a traditional classification based on convolutional network extraction features new frame

Images