Infra red detecting and tracing method for weak target under complex background condition

Abstract

In the method, image background is obtained through morphology as demean value image containing target and noise can be obtained by deducting image background from original image, N / S ratio of processing result can be raised by applying pretreatment process based on elliptic paraboloid volume, sing frame detection result can be obtained by selecting detecting threshold with constant false alarm ratio standard, false target is further removed by utilizing solidity of target motion trail, target tracking applies most near neighbour coorelation method and target state is refreshed by applying kalman filtering based on uniform straight-line motion model and trail is utilized to predict possible position of target for carrying on stable tracking if target is lost.

Description

Technical field: [0001] The invention relates to a method for detecting and tracking small and weak infrared targets under complex background conditions, and is an integrated method for infrared search and tracking systems, precision guidance systems, infrared early warning systems, large field of view target monitoring systems, satellite remote sensing systems, safety inspection systems, etc. This core technology can be widely used in various military and civilian systems. Background technique: [0002] Infrared imaging technology is a non-contact testing technology, which can easily detect the invisible thermal radiation emitted by the target and convert it into a visible image technology. A key field involved in information acquisition is the research of infrared detection technology and method, and its important position has become increasingly prominent. Infrared imaging technology is favored due to its advantages of good concealment, wide detection range, high positio...

AI Technical Summary

Problems solved by technology

[0005] 1. The target is small and has no information such as size, shape and texture, so traditional image processing methods cannot be applied;

[0006] 2. The background is complex and the noise characteristics are unknown;

[0007] 3. The signal-to-noise ratio is low, and the target is submerged in the background noise;

[0008] 4. The amount of data is large and difficult to process in real time

[0009] Researchers at home and abroad have proposed some methods for target detection and tracking in low SNR infrared images, such as three-dimensional matched filter, truncated sequential likelihood ratio detection method, dynamic programming method, high-order correlation method, etc., but the amount of calculation is very large. Large, difficult to process video image sequences in real time

The main reason is that there is no effective image preprocessing method to improve the signal-to-noise ratio of the processed image, resulting in increased difficulty in target detection, association, and tracking algorithms; there is no use of the weak mobility of long-distance targets to simplify data Process etc.

Images