A method and system for all-sky aurora image classification and key local structure location

Abstract

The invention belongs to the technical field of data identification and data representation, and discloses a method and system for all-sky aurora image classification and key local structure positioning. In the training stage, an image block scale model is constructed on the all-sky aurora image data with image tags ;Use the image block scale model to convert the image label into a region bounding box label; on the whole sky aurora image database with bounding box labels, train the image region scale model; inference stage: use the image region scale model to input the whole sky aurora Image classification and bounding box-level coarse positioning of key local structures; image block scale model is used to further perform pixel-level precise positioning of key local structures on all-sky auroral images. The present invention uses all-sky aurora images with image-level labels as training samples, and obtains good image-level classification and pixel-level key local structure positioning effects, which can be used for automatic analysis of the evolution process of aurora forms and spatial positions in all-sky aurora images .

Description

technical field [0001] The invention belongs to the technical field of data identification and data representation, and in particular relates to a method and system for all-sky aurora image classification and key local structure positioning. Background technique [0002] The aurora is produced by the excitation of high-energy charged particles from the magnetosphere or the sun to excite molecules or atoms in the upper atmosphere. It reflects changes in solar activity and the Earth's magnetosphere, and is an important means of monitoring and exploring physical processes in near-Earth space. Among the many aurora observation equipment, the ground-based optical all-sky imager can capture the two-dimensional shape information of the aurora, and has good spatial and temporal resolution. The all-sky aurora images captured by it are widely used to study the physical evolution of the aurora. Since the shape of the aurora is related to the specific state of the magnetosphere and dyna...

AI Technical Summary

Problems solved by technology

[0004] In summary, the problems in the prior art are: Existing technologies such as classification and segmentation of all-sky aurora images cannot simultaneously realize the classification of aurora images and the location of key local structures; most weakly supervised semantic segmentation methods cannot be directly used for automatic analysis of all-sky aurora images; they can be directly applied to The weakly supervised semantic segmentation method for all-sky auroral images cannot capture the overall morphological features and local detail differences at the same time, resulting in low classification and key local structure positioning accuracy

Images