Multi-source Remote Sensing Image Classification Method Based on Robust Deep Semantic Segmentation Network

Abstract

The invention discloses a multi-source remote sensing image classification method (Robust Loss Function of Remote Sensing Imagery, RSRLF) based on a robust deep semantic segmentation network. The method is composed of a fault-tolerant loss function and an adaptive category weight. Remote sensing semantic segmentation based on the open source land cover classification dataset can greatly reduce the sample labeling work, but the open source land cover classification dataset contains certain labeled wrong samples. The fault-tolerant loss function in the present invention can restrain the model from learning noise labels, and avoid the model from overfitting the noise labels; the category balance constraint module can solve the problems of large differences in sample size of ground object categories in the global distribution and inconsistent confusion between categories. The combination of the two can effectively solve the problem of imbalance between noise labels and category samples in remote sensing semantic segmentation using open source land cover classification datasets, and improve the accuracy of ground object classification based on open source land cover classification datasets.

Description

technical field [0001] The invention belongs to the intersection field of remote sensing interpretation and artificial intelligence, and relates to a multi-source remote sensing image classification method based on a robust deep semantic segmentation network, specifically including fault-tolerant deep learning and self-adaptive class balance weight collaborative learning remote sensing semantic segmentation robust Great way to learn. Background technique [0002] Changes in land use and land cover directly affect climate and biodiversity worldwide. Rapid and effective acquisition of real and reliable land cover data can provide important support for global climate change research, land cover change detection, and ecological model establishment. With the continuous improvement of the spatial resolution of remote sensing images, the resolution of large-scale land cover classification mapping is also continuously improved. How to quickly and accurately obtain land cover class...

AI Technical Summary

Problems solved by technology

[0005] The present invention mainly solves the problem of low accuracy of classification results existing in the process of classification of remote sensing images based on open source land cover classification data in the prior art, and provides a multi-source remote sensing image classification method based on robust deep semantic segmentation network (Robust Loss Function of Remote Sensing Imagery, RSRLF), which consists of a fault-tolerant loss function and adaptive category equalization weights, can effectively improve the classification accuracy of remote sensing images based on open source land cover classification datasets

Noisy labels can adversely affect model learning

Images