Remote sensing water body target extraction method based on feature dictionary fusion

Abstract

The invention discloses a remote sensing water body target extraction method based on feature dictionary fusion. The method comprises the following steps: firstly, constructing a remote sensing land and water scene image data training set, gridding images of the training set into feature extraction units with preset sizes, and respectively extracting local binary pattern (LBP) features and frequency spectrum features; then, respectively performing K-means clustering on the LBP feature set and the spectrum feature set to obtain a clustering result based on the LBP features and a clustering result based on the spectrum features, and constructing a fusion dictionary based on the LBP and the spectrum features; secondly, performing vectorization representation on the training set images by adopting a fusion dictionary to form a training feature vector set; and finally, inputting a to-be-identified remote sensing land and water scene test image, performing block vectorization and classification on the image according to the fusion dictionary, and performing statistics on a classification result to obtain a remote sensing land and water scene image water body extraction result.

Description

technical field [0001] The invention relates to a remote sensing water target extraction method based on feature dictionary fusion, which belongs to the field of image processing. Background technique [0002] Water resources are an essential resource for human survival. Real-time and accurate access to water body information is of great significance to the effective management and rational use of water resources. Due to the uneven temporal and spatial distribution of water resources and their fluidity, it is difficult for manual detection to obtain information effectively in real time. With the rapid development of remote sensing technology, the extraction of surface water body information through remote sensing images not only has a wide monitoring range, but also has the advantage of real-time performance. [0003] After years of development of remote sensing technology, the spatial resolution of the collected remote sensing images has gradually increased to the sub-mete...

AI Technical Summary

Problems solved by technology

This invention mainly extracts the water body area based on the spectral characteristics of ground objects, and achieves a certain extraction accuracy, but there are deficiencies: the algorithm needs to preset segmentation parameters, and the parameters of the water body information image in different scenarios need to be reset , and the feature group includes features such as spectrum, topology, shape, and aspect ratio, the process of feature extraction and labeling is complex and time-consuming

[0008] (2) The algorithm structure of the threshold-based segmentation method is simple, and it has a good segmentation effect for images with large differences in gray distribution, but it has a poor segmentation effect for images with unimodal or wide-valley histogram characteristics.

Images