Domain self-adaptive method and system for remote sensing image classification

Abstract

The invention relates to the field of remote sensing images, and discloses a domain self-adaptive method and system for remote sensing image classification. The domain self-adaptive method comprises the steps of selecting an unmarked sample having the largest amount of information with respect to a current classifier from a target field through active learning, marking the selected sample and adjusting the current classifier in accordance with the marked sample and a current training sample set; and adjusting the current classifier after active learning adjustment through semi-supervised learning. The domain self-adaptive method and system of the invention are suitable for migration of priori knowledge of images in the same region or in different regions at different times, solve the domain self-adaptive problem through active learning and semi-supervised learning, and allow mutual transmission and utilization of knowledge of different images.

Description

technical field [0001] The present invention relates to the technical field of remote sensing images, in particular to a domain adaptive method and system for classification of remote sensing images. Background technique [0002] At present, using the automatic classification technology of remote sensing images to obtain land cover type maps usually uses supervised learning methods and machine learning methods. [0003] Supervised learning typically relies on a set of labeled reference examples to train a classification algorithm. These supervised learning methods require a new set of training samples each time a new remote sensing image is processed, resulting in high time and labor costs. At the same time, when classifying some areas where site surveys cannot be implemented and historical data are not available for reference, the difficulty of obtaining training samples has become a severe limitation for the use of supervised learning to achieve classification. [0004] ...

AI Technical Summary

Problems solved by technology

[0005] To sum up, in general engineering applications, supervised learning classification is generally used to ensure accuracy when performing remote sensing image classification, but it consumes a lot of time and manpower, and generates a large number of redundant samples

Images