Method for detecting SAR image cluster target based on target number posteriority

A target detection and target number technology, applied in the field of radar remote sensing or image processing, can solve the problems that SAR images are difficult to provide training samples, and the posterior probability of the target detection frame is inaccurate, etc.

Active Publication Date: 2018-02-27
UNIV OF ELECTRONIC SCI & TECH OF CHINA
View PDF1 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The model extracted by this method is derived from the real image, which makes full use of the target information, but its shortcomings are also very obvious.
This type of detection method relies on the support of a large amount of training data, and it is difficult for SAR images to provide enough training

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
  • Method for detecting SAR image cluster target based on target number posteriority
  • Method for detecting SAR image cluster target based on target number posteriority
  • Method for detecting SAR image cluster target based on target number posteriority

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0077] Such as figure 2 As shown in (a), the experimental data is a ground scene SAR image acquired by a Ka-band spotlight SAR imaging system, which contains complex ground object information and a large number of target clusters. The image mainly consists of three categories of objects: vehicles, ground and buildings. The image is processed according to step 1 of the technical solution of the present invention to obtain the region of interest in which the target may exist in the SAR image, and most of the regions contain cluster targets. After scatter center extraction, the main background area is deleted, while the target appears as multiple discretely distributed scatter centers. Therefore, after selecting a certain target number assumption, the scattering medium is divided into a corresponding number of target regions. When the number of objects does not match the real value, the segmented object area is also different from the real object. Therefore, the similarity be...

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 belongs to radar remote sensing or image processing technologies, and particularly relates to a method for detecting an SAR image cluster target based on target number posteriority. Themethod comprises the steps of extracting interesting regions from an SAR image and extracting a strong scattering center in each interest region to estimate the range of possible target number; selecting an estimated value of the target number in the range and dividing the scattering center in each interesting region into target regions by using a segmentation algorithm based on the constraint ofthe number; analyzing the similarity of the target regions through the obtained spatial size and intensity distribution of the target regions, and calculating the posterior probability of the estimated value of the target number; finally, finding the estimated value with the largest posterior probability by iteratively comparing detection results under different target numbers, and using the corresponding target region as the cluster target detection result of the method. The method for detecting the SAR image cluster target based on the target number posteriority achieves the detection and segmentation of the cluster target in the SAR image, and can more accurately distinguish different individuals in the target cluster.

Description

[0001] technical field [0002] The invention belongs to the technical field of radar remote sensing or image processing, and in particular relates to a SAR image cluster target detection method based on target quantity posteriori. Background technique [0003] Traditional SAR image target detection methods are used to extract isolated target areas. When there are target clusters in the SAR image scene, this type of detection method cannot correctly extract each target. Therefore, it is of great significance to improve the detection method of the cluster target to improve the signal detection ability of the radar. With the advancement of SAR imaging technology and the increasing application of SAR image detection technology, the algorithm research of target detection in SAR images with more complex scenes has become a hot spot in recent years. A target in a SAR image is generally composed of multiple scattering centers. While extracting the scattering centers of the target, t...

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
IPC IPC(8): G06K9/00G06K9/34G06K9/62
CPCG06V20/13G06V10/267G06F18/2415
Inventor 曹宗杰杨海溢崔宗勇
Owner UNIV OF ELECTRONIC SCI & TECH OF CHINA
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap