Unlock instant, AI-driven research and patent intelligence for your innovation.

A fast target detection method in sar images based on saliency detection and clustering

A detection method and image technology, which is applied in the field of aircraft to quickly and effectively detect ground vehicles, can solve the problems of high false alarm rate, long detection time, inaccurate estimation of clutter statistical model parameters, etc. The effect of high alert rate

Active Publication Date: 2017-10-27
XIDIAN UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Because the statistical distribution model of the background clutter does not necessarily obey the Gaussian distribution, it takes time to estimate the parameters of the background clutter, and each pixel in the SAR image is treated the same, resulting in the inaccurate estimation of the parameters of the clutter statistical model in this method. The shortcomings of accuracy, long detection time, and high false alarm rate

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 fast target detection method in sar images based on saliency detection and clustering
  • A fast target detection method in sar images based on saliency detection and clustering
  • A fast target detection method in sar images based on saliency detection and clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] refer to figure 1 , the implementation steps of the present invention are as follows:

[0035] Step 1, build an intensity channel Gaussian pyramid for a SAR image A.

[0036] 1a) Initialization: take a SAR image A as the input image Z for the next step;

[0037] 1b) performing downsampling processing on the input SAR image Z to be downsampled, that is, taking the pixels of the even columns and even rows in the SAR image Z to obtain the downsampled SAR image B;

[0038] 1c) performing a Gaussian low-pass filtering operation on the down-sampled SAR image B to obtain a filtered SAR image L;

[0039] 1d) using the filtered SAR image L as the input SAR image Z to be down-sampled in 1a), and repeating steps 1b)-1c), until the number of rows or columns of the filtered SAR image L is 1;

[0040] 1e) Add the SAR image obtained through steps 1a)-1d) to the original SAR image A to obtain a total of m images, arrange these images in descending order of size, and obtain an m-laye...

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 image target rapid detection method based on saliency detection and clustering, which mainly solves the problems of slow detection speed and high clutter false alarm in the existing SAR image target detection technology. The implementation steps are: establishing an intensity channel Gaussian pyramid for the SAR image A; selecting the scale of the Gaussian pyramid according to the target size; establishing an intensity saliency map for the SAR image at the selected scale according to the selected scale; determining the intensity saliency map in turn. The current most salient area is obtained, and a binary image that marks all salient areas is obtained; the binary image is subjected to morphological filtering and clustering operations, and area culling is performed according to the area of ​​the target area; The SAR image target detection process is finally completed. The invention has the advantages of fast detection speed and low false alarm rate, and is suitable for fast detection of SAR image targets.

Description

technical field [0001] The invention belongs to the field of radar target detection, in particular to a method for quickly and effectively detecting ground vehicles and aircraft in synthetic aperture radar SAR images. Background technique [0002] Radar imaging technology was developed in the 1950s, and has been developed by leaps and bounds in the next 60 years. At present, it has been widely used in military, agriculture, forestry, geology, ocean, disaster, mapping and many other fields. [0003] Synthetic aperture radar (SAR) is an active sensor that uses microwaves for perception. Compared with other sensors such as infrared and optical, SAR imaging is not limited by conditions such as light and weather. observation. Therefore, SAR has become an important means of earth observation and military reconnaissance, and the automatic target recognition of SAR images has attracted more and more attention. [0004] The ATR method of SAR automatic target recognition usually ado...

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 Patents(China)
IPC IPC(8): G06K9/54G06K9/62
CPCG06V20/13G06V2201/07
Inventor 杜兰王兆成王斐刘宏伟
Owner XIDIAN UNIV