Small weak moving target tracking method based on sparse representation

Abstract

A small weak moving target tracking method based on sparse representation comprises the following steps: acquiring the location of an infrared image target based on a detection algorithm, and constructing an initial training sample and an initial particle set; adopting a K-means singular value decomposition method K_SVD to learn the training sample and construct an adaptive morphological ingredient over-complete dictionary of the image, then, constructing an adaptive online classification over-complete dictionary, and carrying out real-time online updating; and finally, establishing a small weak target sparse representation observation model in a particle filter tracking framework, estimating the location of the target based on the size of sparse representation residual of a particle target image block and a particle background image block in the adaptive online classification dictionary, and keeping stable target tracking in subsequent frames through repeated iteration. The method of the invention not only overcomes the defect that it is difficult for an offline structure dictionary to sparsely represent a dynamically changing image signal and improves the difference between a signal and a background in representation sparseness, but also effectively improves the capability of infrared weak small target motion detection tracking.

Description

technical field [0001] The invention belongs to the field of measurement and control of deep-space aircraft, and in particular relates to the detection of infrared weak and small moving targets. Background technique [0002] Moving target detection is a core technology of infrared imaging search and tracking system, target monitoring system, satellite remote sensing system, security inspection system, etc. It can be widely used in various military and civilian systems. 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, and lacks color, structure, texture, etc. Therefore, it is of great significance to study new methods of infrared small and weak target tracking under the conditi...

AI Technical Summary

Problems solved by technology

However, the atoms representing the target signal and the atoms representing the background clutter in the dictionary are mixed together, which means that the interpretability of the coefficients is poor, and it is difficult to distinguish the target signal from the background clutter

However, the existing methods are difficult to capture all the states of the dynamically changing target signal and the fluctuating background clutter in the dictionary constructed by offline learning, resulting in a mismatch between the structure dictionary and the signal state, and the energy is scattered in the adjacent and correlated On a strong dictionary atom, non-zero means that the coefficients are in the form of aggregated blocks, and the performance of matching and tracking and norm algorithms will deteriorate

Images