Method for inhibiting infrared image background based on PDE (Partial Differential Equation)

Abstract

The invention provides a method for inhibiting an infrared image background based on a PDE (Partial Differential Equation), concretely comprising the following steps of: (1) carrying out noise filtering background estimation on an initial image by using a PDE theory based filtering model to obtain a background image; and (2) carrying out neighboring difference on the initial image and a background image to obtain a result image of which the background is inhibited. Test data show that the method can be used for remaining the target property, lowering the target segmenting difficulty, facilitating later target detection and identification, increasing the target detection rate and realizing good adaptability of a filtering method while effectively inhibiting strong clutter backgrounds in the images.

Description

technical field [0001] The invention belongs to the technical field of digital image processing, in particular to an infrared image background suppression method based on a partial differential equation (PDE). Background technique [0002] Target detection and recognition using infrared imaging technology is a key technology in many civil and military fields. Because the infrared sensor is affected by factors such as the atmosphere, sea surface thermal radiation, long working distance and detector noise, the detected target appears as a low-contrast target on the infrared image, especially when the detection signal is relatively weak and the background In the case of smooth undulating interference, the edge of the target may even be completely submerged by a large amount of complex noise (clutter), the signal-to-noise ratio of the image is low, and the information of shape and structure is insufficient, which increases the difficulty of target detection and recognition. The...

AI Technical Summary

Problems solved by technology

[0003] In the existing published literature, the background suppression methods mentioned have the following disadvantages: (1) Most of them are aimed at some special scenes, such as only applicable to the sea-sky background, downward-looking imaging or long-distance target detection, such methods are not adaptable powerful

However, when the distance between the ship and the ship target needs to be further recognized, due to the large size of the ship target, using the traditional background suppression method for this type of image may cause the segmented ship target to appear hollow and broken , loss of details; or it will lead to excessive smoothing of the image, and it is easy to connect part of the hull with the background, which will lead to difficulty in target recognition in subsequent processing

(2) Complex interference backgrounds such as land and islands are not considered, resulting in low segmentation accuracy and difficult target extraction

Images