Incremental learning method and system for multi-frame image spectrum dictionary construction

Abstract

The invention provides an incremental learning method for multi-frame image spectrum dictionary construction, and relates to the technical field of remote sensing image processing, and the method comprises the steps: obtaining a plurality of frames of spectrum images; performing dictionary learning by using the first frame of spectral image to obtain a spectral dictionary expressing the first frame of spectral image; dividing the spectrum dictionary expressing the first frame of spectrum image into a universal spectrum dictionary and a specific spectrum dictionary of the first frame of spectrum image through the activity ratio; solving a specific spectrum dictionary of the second frame of spectral image by using the specific information of the second frame of spectral image and an outlier removal strategy; using common information of the first frame of spectral image and the second frame of spectral image to update the universal spectral dictionary; and performing iterative processing on the multiple frames of spectral images to obtain an incremental dictionary composed of the specific spectral dictionary of the multiple frames of spectral images and the updated universal spectral dictionary. According to the invention, while the original spectral image dictionary expression performance is considered, the dictionary expression precision of the newly added spectral image is effectively improved.

Description

technical field [0001] The present application relates to the technical field of remote sensing image processing, and in particular to an incremental learning method and system for building a multi-frame image spectral dictionary. Background technique [0002] Hyper / multispectral images in remote sensing images can provide rich spectral information, which makes it possible to distinguish different materials through spectral information, and can be widely used in environmental monitoring, ground object classification and other fields. The method based on dictionary learning can effectively extract the effective spectral information in hyper / multispectral images, so as to model the background, and then distinguish and identify spectral targets. However, as the number of spectral images continues to increase, the dictionary learning for multi-frame spectral images has high complexity, and cannot make full use of the learned dictionary information for incremental processing. Th...

AI Technical Summary

Problems solved by technology

[0005] For this reason, the first purpose of this application is to propose an incremental learning method for multi-frame image spectral dictionary construction, which solves the problem that the existing methods cannot obtain satisfactory dictionary incremental learning results and dictionary expression accuracy. By introducing the activity rate ratio into the incremental dictionary learning, the incremental dictionary is modeled as a universal spectral dictionary and a specific spectral dictionary, and the shared information and unique information of multi-frame spectral images are simultaneously mined under the constraints of sparseness and low rank. The specific information of the newly added spectral image is used to optimize the specific spectral dictionary, and the common information of multiple frames of spectral images is used to update the universal spectral dictionary, which realizes the effective improvement of the newly added spectral image while taking into account the expression performance of the original spectral image dictionary. The dictionary expression precision of

Images