SAR target detection method based on optimal fractional domain Gabor spectrum features

Abstract

The invention discloses an SAR target detection method based on optimal fractional domain Gabor spectrum features, and belongs to the technical field of image processing. The SAR target detection method comprises the following steps: reading in an SAR image signal, expanding the SAR image signal to be 1*MN signals and MN*1 signals in the row direction and the column direction, designing optimal window functions for the signals in the two directions, conducting GT on the signals, conducting FrFT on space-frequency spectrums obtained in the two directions, conducting energy attenuation gradient feature extraction on the space-frequency spectrums, conducting the product on the spatial positions corresponding to feature representations in the two directions, therefore, obtaining the feature space of an original SAR image, and completing the detection. Due to the fact that the FrFT and the GT are combined, and compared with a conventional algorithm, the algorithm in the method is additionally provided with fractional domain parameters, the anti-interference performance of the algorithm is stronger, a weak target region can be detected, compared with the conventional detection algorithm, the algorithm is higher in accurate, and the SAR target detection method is also suitable for various scenarios and has better universality.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a SAR target detection method based on the optimal fractional domain Gabor spectrum feature, which can be used for the detection of SAR targets, which is based on Fractional Fourier Transform (Fractional Fourier Transform, FrFT) and time Time Frequency Analysis (TFA), which extracts the fractional domain Gabor spectral features of the image, thereby detecting the target with high precision. Background technique [0002] SAR has the characteristics of all-day, all-weather, strong penetrating ability, and high resolution. It has been widely used in military reconnaissance, topographic mapping, geological exploration, marine applications, agricultural and forestry monitoring, water resource utilization, and scientific research. SAR is developing rapidly, and the information acquisition technology of SAR image system is obviously ahead of the information processing t...

AI Technical Summary

Problems solved by technology

[0006] Due to the imaging mechanism of the SAR image, it cannot describe the outline and details well; secondly, the SAR target is sensitive to the azimuth angle. Therefore, the SAR image formed under different targets and different illumination azimuths has the same background scattering intensity as the target scattering intensity. Intensities are also different; moreover, SAR images have specific speckle noise, and radiation and geometric features are distorted during the imaging process. Conventional image detection methods are not suitable for SAR target detection, so a high-precision, noise-resistant strong detection method

Images