Image super-resolution reconstruction method and device based on multi-angle and multi-resolution

Abstract

The invention provides a multi-angle and multi-resolution ratio-based image super-resolution reconstruction method and device. The image super-resolution reconstruction method comprises the following steps: executing global radiation registering processing on multiple reconstructed images; determining a geometric corresponding relationship of pixels of multi-resolution ratio-based images in the multiple images, and acquiring images subjected to geometric correction which correspond to non-front view angle images; and respectively acquiring the multi-resolution ratio reconstruction image of each non-front view angle image and front view image through image extrapolation based on a preset spatial constraint criterion. According to the technical scheme provided in the invention, multi-resolution ratio and multi-angle image super-resolution reconstruction is realized, and the information integrity of the super-resolution reconstruction image reconstruction is improved.

Description

technical field [0001] The present invention relates to the communication field, in particular, to a multi-angle and multi-resolution image super-resolution reconstruction method and device. Background technique [0002] Remote sensing refers to the theory, method and application of science and technology that use sensors to detect the electromagnetic radiation and reflection characteristics of objects for non-contact and long-distance detection, and analyze the properties, characteristics and states of objects according to their characteristics. With the continuous development of sensor technology, aerospace technology and data communication technology, modern remote sensing technology has entered a new stage of providing earth observation data dynamically, rapidly, multi-platform, multi-temporal and high-resolution. [0003] With the development of society and economy, remote sensing technology has been applied in many industries such as urban development and surface monit...

AI Technical Summary

Problems solved by technology

[0006] At present, for image super-resolution reconstruction methods, due to the different conditions used, there are insufficient practicability for specific situations. It often processes multiple images with the same resolution, even if it is processing images with different shooting angles or Images with different resolutions are often reconstructed using conventional methods after conventional image registration, which does not make full use of the complementary information on resolution or angle differences between original images

In particular, for the recent multi-angle three-dimensional satellites (such as the National Resource No. 3 high-resolution three-dimensional mapping satellite, it adopts a three-line array structure of front, rear, and front, and three sensors simultaneously record images from three angles of the same scene at the same time. ), image super-resolution reconstruction based on existing methods is insufficient in making full use of useful information

Images