Fused panchromatic image and multispectral image classifying method and device

Abstract

The invention provides a fused panchromatic image and multispectral image classifying method and device. The fused panchromatic image and multispectral image classifying method comprises the steps of acquiring panchromatic images and multispectral images in a region to be detected, segmenting the panchromatic images to obtain over-segmentation bodies of the panchromatic images, merging the over-segmentation bodies of the panchromatic images to determine segmentation body units, classifying the multispectral images according to the segmentation body units to obtain classifying labels of the multispectral images, wherein each segmentation body unit comprises at least one over-segmentation body. By means of the fused panchromatic image and multispectral image classifying method and device, space information of the panchromatic images can be utilized in the multispectral image classifying process, the space information of the panchromatic images and the space information of the multispectral images can be fully and effectively utilized, the dependency on spectral information of image classification can be reduced, classifying accuracy can be improved, and the classifying labels can be clear.

Description

technical field [0001] The invention relates to the technical field of image recognition and classification, in particular to a classification method and device for fusing panchromatic images and multispectral images. Background technique [0002] Classification of remote sensing images is to use computers to analyze the spectral information and spatial information of various ground objects in remote sensing images, select features, and use certain technical means to divide the feature space into subspaces that do not overlap with each other, and then divide each feature space in the image into non-overlapping subspaces. Pixels are assigned to each subspace. [0003] At present, many surface observation platforms can obtain panchromatic images and multispectral images at the same time. For example, the images collected by the IKONOS satellite are panchromatic images with a resolution of 1 meter, and multispectral images with a resolution of 4 meters. The images collected by ...

AI Technical Summary

Problems solved by technology

[0004] Many sensors in the prior art can simultaneously obtain panchromatic images and multispectral images, but there are limited methods for comprehensively and effectively utilizing these two images for image analysis and processing. Color sharpening can generally effectively improve the visual information of images, but because panchromatic sharpening often introduces spectral loss or spectral reversal, it sometimes has a negative impact on the classification process that relies on image spectral information, and even makes classification worse result

Moreover, most of the sharpening-classification and classification-sharpening methods in the prior art regard classification and sharpening as two independent processes, which cannot be organically unified and mutually promoted.

In the existing technology, classifying and labeling panchromatic images and multi-spectral images will result in unclear classification and errors in the results of image classification

Images