Polarized synthetic aperture radar-based vehicle detection method

Abstract

The invention provides a polarized synthetic aperture radar-based vehicle detection method, which belongs to the technical field of radar image signal processing. The method comprises the steps of obtaining a training set and a test set, performing channel-by-channel compression on the obtained coherence matrix of each sample in the training set and the test set through a two-dimensional principalcomponent analysis algorithm of an L1 norm to obtain a training set and a test set after dimension reduction, according to the obtained training set and test set after dimension reduction, detectinga potential target by utilizing a complex Wishart distance metric, carrying out target identification on a potential target detected by the complex Wishart distance metric by using template matching based on a correlation coefficient, and if the plurality of candidate targets obtained after target identification belong to the rectangular frame of one vehicle, performing weighted combination on thecandidate targets according to the importance degree of the candidate targets to obtain a vehicle detection result. By adopting the method and the device, the interference of strong reflectors such as buildings can be eliminated, and the positioning accuracy of dense targets is improved.

Description

technical field [0001] The invention relates to the technical field of radar image signal processing, in particular to a vehicle detection method based on polarization synthetic aperture radar. Background technique [0002] With the rapid development of the economy, the number of private cars in the city is increasing, causing traffic congestion and environmental pollution. The pressure can be alleviated through intelligent vehicle control. [0003] Target detection is a key and difficult problem of Polarimetric Synthetic Aperture Radar (PolSAR), and it is also an important application direction of Polarimetric SAR system. The echo received by polarimetric SAR has four basic characteristics of amplitude, phase, frequency and polarization, which can completely describe the physical scattering process of the target. Since different types of targets have different backscattering intensities, dielectric properties, and geometric properties, after the target modulates and loads ...

AI Technical Summary

Problems solved by technology

[0011] However, many of the above methods need to accurately obtain the polarization scattering information, representation model and statistical characteristics of the clutter

In the background of simple uniform clutter, such as the detection of ships on the sea surface, the type of ground objects is single, and the information estimated by the background clutter is consistent with the actual situation; For target detection, because of the interference caused by clutter edges and multiple targets, the information estimated by using clutter is often inconsistent with the actual situation, so the practicability of many methods will be greatly reduced

Therefore, most of the existing algorithms are aimed at the detection task of sea surface targets, and there are few researches on the detection of ground targets, especially the dense target detection problem in complex environments.

Images