Marine target information fusion method based on satellite infrared and visible light images

Abstract

The invention discloses a marine target information fusion method based on satellite infrared and visible light images, and the method comprises the steps: starting a satellite infrared camera and a visible light camera, carrying out the imaging of a key sea area, and downloading an image to a ground station; and performing ship target detection on the visible light image by using a deep learningalgorithm, and performing ship target detection on the infrared image by using a peak signal-to-noise ratio threshold segmentation algorithm; according to the ship target detection point sets of the visible light image and the infrared image, performing point set matching by using a point mode matching algorithm, screening the point sets, and performing registration of the visible light image andthe infrared image according to the screened point sets; and performing target association by using the interaction ratio of the registered image detection area, integrating target slices, and performing type identification on the ship target by using a deep learning algorithm. According to the marine target information fusion method based on the satellite infrared and visible light images, effective discovery and identification of ship targets can be realized.

Description

technical field [0001] The invention relates to the technical field of satellite detection, in particular to a sea target information fusion method based on satellite infrared and visible light images. Background technique [0002] In marine surveillance, ship target detection and recognition based on satellite remote sensing images has always been a hot research issue. At present, there are many methods for ship target detection and recognition, especially the emergence of deep learning detection and recognition framework, which makes the ship target detection and recognition system more practical, but mainly for high-resolution visible light and synthetic aperture. Radar (SAR) imagery. A single satellite imaging sensor cannot adapt to the complex marine environment. In a good meteorological environment, satellite visible light cameras can obtain rich texture information of maritime targets. However, under complex meteorological conditions, the target feature information i...

AI Technical Summary

Problems solved by technology

On the other hand, the resolution of infrared images is generally lower than that of visible light images, and the ability to identify ship target types is weak

Images