Multi-feature fusion based infrared small dim moving target track starting method

Abstract

The invention provides a multi-feature fusion based infrared small dim moving target starting track detection method and relates to the technical field of measurement and control. The method comprises the following steps of: estimating an image background by utilizing gray morphological filtering to acquire mean removal images; extracting targets by adopting constant false-alarm rate single-framedetection, and removing a false-alarm area to suppress stray noise; looking for suspected targets with most similar properties by adopting a nearest neighbor correlation method; estimating the movingspeed of the targets, and carrying out moving superposition on the mean removal images of two adjacent frames to accumulate energy; and determining a target track by utilizing an M / N logical method. The invention sufficiently utilizes the consistency of target features in a space domain and a time domain, improves the starting property of the target track, can be widely applied to various military and civil systems and has wide market prospect and application value.

Description

technical field [0001] The invention belongs to the field of measurement and control of deep-space aircraft, and specifically relates to a method for detecting the initial track of an infrared weak and small moving target. It is a core technology of an infrared imaging search and tracking system, a target monitoring system, a satellite remote sensing system, and a safety inspection system. It can be widely used in various military and civilian systems. Background technique [0002] In various imaging detection and tracking systems, it is required to be able to intercept and lock the tracking target as soon as possible. When the distance between the detector and the target is long, the target appears as a small target with only a few pixels in imaging, and is easy to be submerged in various clutter backgrounds and strong noise, which brings great difficulties to target detection and tracking. It is very difficult. Affected by many factors, even after clutter suppression and...

AI Technical Summary

Problems solved by technology

[0003] The detection methods of these initial moving target tracks mainly use the target feature of its motion continuity, that is, its continuity in the time domain, but seldom use other attributes of the target, such as its aggregation degree in the air domain, That is, airspace correlation, which causes the detection platform to be unstable, and the target trajectory projected into the sequence image is not a regular straight line, and the traditional track initiation method is not effective.

Images