Hyperspectral image stripe missing restoring method based on edge constraint and self-adaptive morphological filter

Abstract

The invention discloses a hyperspectral image stripe missing restoring method based on an edge constraint and self-adaptive morphological filtering, belongs to the field of hyperspectral image processing in the remote sensing image processing, and aims to solve the problem of incapability of restoration when stripe missing occurs in continuous spectrum bands in the acquisition process of a hyperspectral image. The hyperspectral image stripe missing restoring method comprises the steps of detecting a stripe and determining a specific position of the stripe missing in the hyperspectral image; restoring the edge and preferably restoring edge information in the stripe missing; generating a self-adaptive structural element based on the edge constraint for each damaged pixel of stripe missing, the self-adaptive structural element being capable of protecting the hyperspectral image information and greater than the width of the stripe missing so as to ensure the structural element can cover an undamaged region; and performing self-adaptive morphological filtering and determining a final restoring value of the damaged pixels of the stripe mission. The invention is used for hyperspectral image restoration.

Description

technical field

[0001] The invention belongs to the field of hyperspectral image processing in remote sensing image processing. Background technique

[0002] The hyperspectral image acquisition device is an imaging spectrometer, and the non-linear response of the sensor CCD in the spectrometer or errors in the data conversion process, improper data correction, or even damage to some functional units will cause the acquired hyperspectral data to produce abnormal pixels. , resulting in the absence of striped areas at the same position in the continuous band of the hyperspectral image. Such degradation not only affects the subjective quality and recognizability of hyperspectral images, but also affects the performance of machine classification and recognition, so restoration of hyperspectral images is important and indispensable. Although there are some recovery methods for this phenomenon, the model-based methods are often ineffective, and many methods can only restore bad li...

Images