Infrared image weak and small target detection method based on continuous finite frames

Abstract

The invention relates to an infrared image weak and small target detection method based on continuous finite frames, and the method comprises the steps: firstly carrying out the optical flow field calculation of two continuous frames of infrared original images through employing a Lucas-Kanade optical flow method, and building an infrared image optical flow field; then, carrying out suspected motion area detection on the obtained infrared image optical flow field, wherein under the condition that the detection precision is guaranteed, the number of processing frames is smaller, the processingspeed is higher, and redundant information is less; decomposing the region of interest into smaller infrared image blocks, performing background suppression based on SVD decomposition, and reconstructing the processed target set and background set respectively; and finally, detecting the position of the infrared weak and small target through adaptive filtering. Verification is carried out in the constructed modis infrared weak and small target image library, three groups of infrared weak and small target sequence images are selected for experimental analysis, and the detection accuracy of themethod is verified.

Description

technical field [0001] The invention belongs to the field of infrared weak and small target detection, and relates to a weak and small target detection method based on continuous limited frame infrared images. Background technique [0002] Infrared weak and small target detection system has been widely used in space situation awareness, space detection and air navigation because of its all-weather and passive surveillance characteristics. As an important embodiment of the country's near-space detection capabilities, the detection of small infrared targets has always been a hot research topic in infrared image processing. However, with the development of infrared imaging systems, the application environment of the detection system for small infrared targets is more complex, and the distance between the focal plane of the imaging camera and the target is farther, making the target appear as a point or close to a point on the image phase plane, without texture. , shape, size a...

AI Technical Summary

Problems solved by technology

[0004] Traditional infrared small target detection methods mostly use the single-frame detection and multi-frame inspection scheme under the pre-tracking detection framework, or the multi-frame tracking and detection scheme under the pre-detection tracking framework. In this way, whether it is multi-frame inspection or multi-frame tracking There are large limitations in the detection accuracy

Among them, the single-frame detection and multi-frame inspection scheme is too dependent on the accuracy of the detection algorithm, and the motion information cannot be effectively used during single-frame detection, which will cause a large amount of redundant calculations for multi-frame inspection; the multi-frame tracking scheme requires multiple frames of images as input. Large detection delay

Images