A SAR Target Detection Method Based on Gabor Spectral Feature in Optimal Score Domain

A target detection and spectral feature technology, applied in image analysis, image data processing, instruments, etc., can solve the problems of SAR target azimuth sensitivity, inability to describe contours and details well, radiation features and geometric feature distortion, etc., to achieve Improve aggregation, strong noise resistance, and suppress coherent speckle noise

Active Publication Date: 2016-10-05
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

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

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A SAR Target Detection Method Based on Gabor Spectral Feature in Optimal Score Domain
  • A SAR Target Detection Method Based on Gabor Spectral Feature in Optimal Score Domain
  • A SAR Target Detection Method Based on Gabor Spectral Feature in Optimal Score Domain

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0035] A kind of SAR target detection method based on Gabor spectrum characteristic of optimum score field, this method comprises the following steps:

[0036] Step 1: read in the M×N dimensional SAR image signal;

[0037] Step 2: expand the read-in image signal into 1×MN and MN×1 signals according to the row and column directions;

[0038] Step 3: Design optimal window functions for signals in two directions, and perform GT on them respectively, so that the space-frequency aggregation of GT is significantly improved, thereby suppressing clutter.

[0039] Step 4: Perform FrFT on the space-frequency spectrum obtained in two directions, and search for the optimal transformation order to improve the space-frequency distribution, so as to be sensitive to weak targets and improve the detection rate;

[0040] Step 5: Perform energy attenuation grad...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a SAR target detection method based on the Gabor spectrum feature in the optimal fractional domain, which belongs to the technical field of image processing, and comprises the following steps: reading in SAR image signals; expanding the SAR image signals in row and column directions into and the signal; design the optimal window function for the signals in the two directions, and do GT; do FrFT for the space-frequency spectrum obtained in the two directions; perform energy attenuation gradient feature extraction on the space-frequency spectrum; combine the two directions The feature representation is multiplied by the corresponding spatial position, so as to obtain the feature space of the original SAR image and complete the detection. The present invention combines FrFT with GT, because it has more fractional field parameters than the conventional algorithm, which makes the algorithm more anti-interference, and can detect weak target areas, which is more accurate than the conventional algorithm, and is also applicable to various scenarios , has good versatility.

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 optimal fractional domain Gabor spectral features, which can be used for the detection of SAR targets, which is based on Fractional Fourier Transform (Fractional FourierTransform, FrFT) and time-frequency The analysis method (Time Frequency Analysis, TFA) extracts the Gabor spectral features of the fractional domain of the image, so as to detect 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...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & AuthorityPatents(China)
IPC IPC(8): G06T7/00G06T5/00
Inventor彭真明杨俊涛黄振星魏瑞鹏何艳敏张萍
OwnerUNIV OF ELECTRONICS SCI & TECH OF CHINA