Near-infrared and visible light remote sensing image registration method based on reinforcement learning

Abstract

The invention discloses a near-infrared and visible light remote sensing image registration method based on reinforcement learning, and the method comprises the following steps: S1, trimming infrared and visible light images to the same size, and carrying out the stacking processing; S2, inputting the stacked images into a residual error improved dense neural network for processing, and outputting a Q value required by registration; S3, reasoning according to the Q value to predict probability distribution of each action in the strategy action space; S4, selecting an action with the maximum probability in the strategy action space according to the probability distribution of each action, and executing the action by the image to be registered; S5, after the to-be-registered image and the reference image reach a set similarity threshold value, carrying out greedy algorithm reasoning sampling on current image registration; and S6, carrying out moving resampling on the current image to be registered, and outputting a final registration result. According to the image registration method, all parts of the registered image are connected naturally and smoothly, multi-modal image registration is more stable, and the effect is better.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a registration method for near-infrared and visible light remote sensing images based on reinforcement learning. Background technique [0002] Visible and infrared sensors are two types of sensors that are commonly used and often used together in different tasks, such as face detection, object tracking, land cover classification, and self-driving cars. For remote sensing images, the captured panchromatic or RGB images are closest to human vision, but will be severely affected by lighting and atmospheric conditions; near-infrared images will be more robust to weather conditions and less susceptible to them . But because they are acquired by different imaging mechanisms in different wavelength bands, there are large geometric differences and different radiation intensities between visible and infrared images. This discrepancy may invalidate conventional registration meth...

AI Technical Summary

Problems solved by technology

But it is not ideal in recent learning-based optical image registration and specific near-infrared and visible remote sensing image registration

Images