Optical remote sensing image ship detection method based on knowledge distillation

Abstract

The invention discloses an optical remote sensing image ship detection method based on knowledge distillation, belongs to the field of remote sensing image target detection, and solves the problem of low ship detection speed caused by large model parameter quantity and high calculation complexity in the prior art. According to the technical scheme, the method comprises the following steps: collecting or downloading a disclosed optical remote sensing image ship detection data set; building a ship detection network framework based on knowledge distillation, and enabling a student network to fully imitate behaviors of a teacher network in a training process by adopting Hint loss; jointly training the teacher network and the student network, and storing model parameters of the trained student network; and testing by using a student network to obtain a final ship detection result. The teacher network with high detection accuracy is used for guiding training of the student network, the original detection speed of the student network is kept, the detection accuracy of the student network is improved, and therefore rapid and accurate optical remote sensing image ship detection is achieved.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image target detection, and in particular relates to a knowledge distillation-based optical remote sensing image ship detection method. Background technique [0002] Ship targets are the key targets of maritime monitoring and wartime strikes. Accurate detection of them can effectively judge the enemy's military movements, and provide important information support for winning wars, defending territorial waters, and ensuring the lives of the country and people. With the rapid development of optical remote sensing technology, the spatial resolution and spectral resolution of optical remote sensing satellite images have been greatly improved, and richer image details and target information have made ship detection using optical remote sensing images more and more popular. much attention. In the prior art, ship detection technology based on deep convolutional neural network has become an import...

AI Technical Summary

Problems solved by technology

[0005] Although the above method improves the detection accuracy of ships in optical remote sensing images, the number of convolutional neural network layers used is large, which leads to a sharp increase in model parameters and computational complexity, and ignores the impact on ship detection speed. It is difficult to realize real-time ship detection in practical applications

Images