A Hyperspectral Urban Water Detection Method Based on Adaptive Sample Selection

Abstract

The present invention provides a hyperspectral urban water body detection method based on adaptive sample selection. In the preprocessing of hyperspectral near-infrared band images, the noise band images are removed through the quality evaluation SSIM method, and the noise is further eliminated by using two average operations. , can obtain a more stable mean image of the near-infrared spectrum, compared with the traditional single-band threshold segmentation method, there is no need to manually select the image to be segmented; the invention uses the unsupervised threshold segmentation method to extract the suspected water body area, and then through the supervised Feature learning and classifier training, remove building shadows, building roof asphalt and other ground objects that are similar to water in the near-infrared spectrum from the suspected water body area; therefore, the present invention combines the unsupervised threshold segmentation method with supervised feature learning Combined with the classifier training method, it has the self-adaptive ability of the urban observation scene, and can realize the "real-time collection and real-time processing" of the measured scene data, and the false alarm is low.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing, and in particular relates to a hyperspectral urban water body detection method based on adaptive sample selection. Background technique [0002] With the rapid development of hyperspectral remote sensing technology, hyperspectral applications in military affairs and people's livelihood are becoming more and more extensive, which leads to higher and higher requirements for hyperspectral data processing for specific application environments. Among them, the detection of urban waters in hyperspectral remote sensing images is an important research direction, which is of great significance in urban hydrological monitoring, urban water network planning, urban ecology, and environmental monitoring. However, the urban background features are diverse and complex, which brings challenges to the accurate extraction of urban water bodies. [0003] The existing hyperspectral urban wat...

AI Technical Summary

Problems solved by technology

However, the urban background features are diverse and complex, which brings challenges to the accurate extraction of urban water bodies.

[0003] The existing hyperspectral urban waters detection method directly applies the existing deep learning method, transforming the detection of urban water bodies into the classification of object types for processing, ignoring the prior information of the types of urban background objects, and the training time is extremely long and cumbersome. It needs to consume a large number of training samples and rely on large-scale parallel computing resources, which has not been fully proved in theory, and the black box attribute is still obvious

In addition, the hyperspectral urban image features are complex and diverse. Due to the influence of factors such as shooting angle, environment, and the phenomenon of the same object and different spectra, the detection rate of ground features directly using the original hyperspectral data is usually not high, and building shadows, building shadows, etc. Ground objects such as roof asphalt have similar spectral properties to water bodies in the near-infrared spectrum, which leads to the problem of excessive false alarms in existing hyperspectral urban water detection methods.

Images