Synthetic aperture radar (SAR) target detection method based on improved visual attention model

A visual attention model and target detection technology, which is applied in the field of image processing, can solve the problems of slow gray level changes of SAR images and failure of visual attention methods, etc., and achieve fast calculation speed, effective detection results, and good robustness

Inactive Publication Date: 2013-03-27
XIDIAN UNIV
View PDF1 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to address the above-mentioned deficiencies in the prior art, and propose a SAR target detection method based on an improved visual attention model, to solve the problem that the visual attention method fails due to the slow change of the gray level of the SAR image and the inconspicuous target area , to make the target area in the image appear better, and provide useful information for later target recognition and classification

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
  • Synthetic aperture radar (SAR) target detection method based on improved visual attention model
  • Synthetic aperture radar (SAR) target detection method based on improved visual attention model
  • Synthetic aperture radar (SAR) target detection method based on improved visual attention model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] refer to figure 1, the specific implementation steps of the present invention are as follows:

[0034] Step 1: Perform 4 times downsampling on the SAR image to be detected, that is, the SAR image to be detected according to The size of is reduced to obtain the sampled image I.

[0035] The purpose of this step is to simulate the visual biological mechanism of the human eye, and achieve the purpose of target detection in low-resolution SAR images by downsampling the SAR images to be detected by 4 times.

[0036] Step 2: Carry out gabor wavelet transform on the sampled image I, and extract it at 0 0 ,45 0 ,90 0 ,135 0 The component texture features in the direction are linearly added to obtain the texture features.

[0037] This step uses gabor wavelet to extract the component texture features of the sampled image I, so that the sampled image I is at 0 0 ,45 0 ,90 0 ,135 0 The texture detail information and contour information on the image are well preserved to...

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 synthetic aperture radar (SAR) target detection method based on an improved visual attention model and belongs to the technical field of image processing. The SAR target detection method mainly solves the problem of failure of a traditional visual attention model in the aspect of SAR image processing. The SAR target detection method includes: under-sampling is performed on an SRA image to be detected, texture features and wavelet features are extracted from the sampled image, linear superposition is performed on the features, and normalization and significance processing is performed on the features to obtain an initial significant figure; visual receptive field template filtering is performed on the initial significant figure to obtain a final significant figure; at last the final significant figure adopts bilinear interpolation to be the same as the size of an original SAR image, and a light area in the interpolated significant figure is used as a target area. The SAR target detection method based on the improved visual attention model has the advantages of being rapid in calculating speed, remarkable in detection effect, accurate in positioning and capable of being used for early detection of an SAR image target.

Description

technical field [0001] The invention belongs to the field of image processing, in particular to a method for detecting a SAR image target, which can be applied to the detection of the SAR target. Background technique [0002] When faced with a complex scene, human attention will quickly focus on a few salient visual objects and prioritize these objects. This process is called visual attention. The visual attention model uses the visual biological mechanism of the human eye and simulates it with mathematical calculation methods to form an important direction in the field of image processing. This model can be used for target detection and recognition, image compression and coding, image retrieval , surveillance systems, active vision, etc. [0003] The classic visual attention model was proposed by Itti. He used mathematical methods to simulate the human visual attention mechanism for the first time and achieved good results. Later, it attracted the attention of many scholar...

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 & Authority Applications(China)
IPC IPC(8): G06T7/00
Inventor 侯彪侯小瑾刘彦甲焦李成方相如翁鹏马文萍马晶晶
Owner XIDIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products