Method for identifying infrared movement small target based on significance and structure

Abstract

The invention provides a method for identifying an infrared movement small target based on significance and structure, and belongs to the application technical fields such as computer vision, pattern recognition and image processing. In order to identify a small movement target from an infrared scene sequence image under the condition of no priori knowledge, the target identification method based on the significance and structure is provided. The method comprises the following steps: firstly, performing significance detecting to an image of each frame as per the significance characteristics; secondly, excluding non-targets through the structure of the movement target; performing the automatic identification of the target through a continuous track of the movement target. According to the invention, the method can be used for identifying the infrared small target quickly and precisely in the premise that no priori knowledge is provided.

Description

technical field [0001] The present invention relates to a fast recognition method for small infrared targets without any prior knowledge, specifically a method for recognizing small infrared moving targets based on salience and structure, which belongs to cross-application technologies such as computer vision, pattern recognition and image processing field. Background technique [0002] The processing of infrared target images is a very critical technology in military and civilian fields such as early warning, target positioning, security monitoring, and missile guidance. In modern warfare technology and military applications, weapon systems are required to have the ability to detect, identify and track long-distance suspicious targets, so as to gain more time to respond and gain the initiative in the battlefield. When the target is too far away from the infrared detector, the size of the infrared target is very small, the contrast is very low, and there is no obvious textu...

AI Technical Summary

Problems solved by technology

However, the clutter of infrared images in the existing methods is a major interference to the patching and learning of features, especially for some infrared images with relatively large clutter, the patched features lack credibility

In addition, the existing methods all recognize some relatively large targets. In actual scenes, especially when the recognized targets are far away, it is inevitable to encounter such a problem: the size of the target is very small, and the signal low noise ratio

In practical applications, for some infrared images and small targets, their prior knowledge cannot be obtained. On the one hand, the characteristics of the target cannot be obtained, that is, the recognition cannot be realized by modeling methods; on the other hand, due to the imaging conditions of infrared images And the limitation of low signal-to-noise ratio makes the small target have no obvious texture, structure and other characteristics, which brings great difficulties to the detection and recognition of the target

Images