Compound method for classifying multiresolution remote sensing images based on context

Abstract

The invention relates to a compound method for classifying multiresolution remote sensing images based on context. The method comprises the following steps of: firstly, registering in a local training area; secondly extracting classification characteristics from a low-resolution image; then establishing a context based on a conditional random field model by utilizing the classification characteristics in a training area based on the previous two steps; and finally, carrying out global classification on the conditional random field model obtained by the previous three steps, popularizing the trained model to the entire coverage area of low-resolution images, and classifying the wide area low-resolution images. In the invention, the multi-resolution remote sensing images are comprehensively utilized, the context between pixels is constructed, the space continuity of ground object distribution is considered, and the conditional random field model provides support for multi-classification characteristics, thus the high-accuracy classification problem of wide-area low-resolution remote sensing images is solved.

Description

technical field [0001] The invention belongs to the fields of pattern recognition and computer vision, and also relates to the fields of remote sensing and agriculture, in particular to a compound classification method for multi-resolution remote sensing images based on contextual relations. Background technique [0002] Land cover classification is the basic technology to obtain land cover and land use status, and has important application value in environmental assessment, map update, crop yield estimation and other fields. In recent years, remote sensing data sources have been increasing, and remote sensing images with different spatial resolutions provide more surface information at different scales. How to make full use of remote sensing data with multiple spatial resolutions in the same area and with different spatial coverages to further improve the classification accuracy of wide-area land cover has become a challenge for remote sensing image analysis. [0003] For ...

AI Technical Summary

Problems solved by technology

The existing multi-resolution remote sensing image composite classification method guides the classification process of the global low spatial resolution data by selecting several small coverage high spatial resolution data in the large coverage area of ​​the low spatial resolution data. The method assumes that the pixels are independent in the classification process, that is, it is carried out at the pixel level or sub-pixel level, and ignores the influence of the spatial position of the pixel and the object category of the pixel neighborhood on the classification result, so the classification result is easily affected by the noise of the remote sensing image.

Images