Hyperspectral image classification method and system based on lightweight neural architecture search

Abstract

The invention discloses a hyperspectral image classification method and system based on lightweight neural architecture search. A hypernetwork is built through modular lightweight candidate operations, the serialization of the discrete candidate operations is carried out on the edge through a weighted mixing operation,double-layer optimization of the hypernetwork is carried out in a gradient optimization mode, and meanwhile, the model search speed is increased through subnet weight sharing. Then, in the optimization process, a greedy decision is utilized to select an undispersed edge, an operation with the maximum framework parameter on the edge is reserved, other operations in the edge are deleted, the remaining network forms a new super-network, the new super-network is iteratively optimized in the mode, the super-network is continuously simplified along with continuous dispersion of the edge and deletion of the operations on the edge, and finally a lightweight deep neural network architecture for hyperspectral image classification is obtained. The lightweight module is fully utilized to construct the super network, the neural architecture search method based on sequential greedy is realized, and the network architecture with less parameter quantity and higher classification precision can be automatically generated.

Description

technical field [0001] The invention belongs to the technical field of image information processing, and in particular relates to a hyperspectral image classification method and system based on lightweight neural architecture search. Background technique [0002] Hyperspectral remote sensing images are digital images captured by hyperspectral imagers in hundreds of continuous narrow spectral bands from visible light to infrared bands to generate three-dimensional hyperspectral images containing spectral and spatial information. The spatial and spectral information of hyperspectral images is very rich. Compared with ordinary images, it has more bands and extremely high resolution. At present, the application of hyperspectral remote sensing to earth observation technology is very common, and it has been widely used in geological mapping and exploration, atmospheric or vegetation ecological monitoring, product quality inspection, precision agriculture, urban remote sensing and ...

AI Technical Summary

Problems solved by technology

[0007] The technical problem to be solved by the present invention is to provide a hyperspectral image classification method and system based on lightweight neural architecture search to solve the problem of manual design of convolutional neural networks limited to human subjective cognition. , it is difficult to design the optimal model structure, resulting in the problem that the classification accuracy is difficult to further improve

Images