Multi-frame infrared image weak and small target detection method and device, equipment and storage medium

Abstract

The invention discloses a multi-frame infrared image weak and small target detection method and device, equipment and a storage medium. The method comprises the steps of acquiring multiple frames of continuous infrared images; extracting feature data from the current frame of infrared image through a weak target detection network model, and obtaining a current frame of initial target segmentationimage through automatic combination and analysis of the feature data; inputting the initial target segmentation image of the current frame into the inter-frame association network model, and correcting the initial target segmentation image of the current frame by taking the pre-stored initial target segmentation images of the first N frames as a reference to obtain a target segmentation image of the current frame. A target detection problem is converted into an image segmentation problem through a weak and small target detection network model, detection of multiple frames of infrared images isachieved through an inter-frame association network model, and the problems of false alarm, missing detection and the like in single-frame infrared image detection are solved.

Description

technical field [0001] The present application relates to the field of information technology, and in particular to a method, device, equipment and storage medium for detecting weak and small targets in multi-frame infrared images. Background technique [0002] When the sensor performs long-distance detection, the target of interest often shows the characteristics of small area and low signal-to-noise ratio, which we call weak targets. The detection of weak and small targets in complex backgrounds is a classic problem in the fields of automatic target recognition such as precision guidance, infrared early warning, and shooting range measurement. In recent years, with the surge in the number of consumer drones, weak target detection has become a key technology that needs to be broken through for low-altitude security and key point protection. [0003] In recent years, deep learning technology has achieved great success in computer vision fields such as image classification, ...

AI Technical Summary

Problems solved by technology

[0008] The main purpose of this application is to solve the technical problems of low accuracy and poor efficiency of the existing multi-frame infrared image weak target detection method

Images