A small-sample remote sensing target detection method and system based on weight dictionary learning

Abstract

The invention discloses a small-sample remote sensing target detection method and system based on weight dictionary learning. The method acquires remote sensing image data to be classified, and brings the data into a pre-trained target detection model to obtain the target corresponding to the remote sensing image. category, the target detection model is obtained by using small sample data based on weight dictionary learning and training. The method uses weight dictionary learning to construct a lightweight small-sample remote sensing target detection model, which can effectively reduce the number of learnable parameters, prevent the model from overfitting when it is trained with small data, and improve the small-sample learning performance of the model ; and can well retain the knowledge learned by the model in the source domain, avoiding the problem of catastrophic forgetting. The remote sensing target detection method based on the weight dictionary proposed by the present invention has good versatility, and can be used to improve other remote sensing target detection models based on deep learning, and improve their small-sample learning ability.

Description

Technical field [0001] The present invention relates to remote sensing image target detection, and specifically, a small sample remote sensing target detection method and system based on weight dictionary learning. Background technique [0002] Automated remote sensing image target detection technology can automatically locate, identifying the target of interest in static remote sensing images. Remote sensing image target detection method based on deep learning has achieved rapid development, but such a deep learning-based remote sensing image target detection method still has certain limitations. [0003] Remote sensing image target detection model based on deep learning relying on a large number of training samples. These models have only tens of thousands or even more training iterations in a large number of training materials can achieve good performance, and when the training samples are insufficient, these models are prone to fit, and the performance of the test data will c...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem that the remote sensing target detection model based on deep learning relies on a large amount of training data and has poor scalability for new tasks, the present invention provides a small-sample remote sensing target detection method based on weight dictionary learning, including:

Images