Method for automatically extracting vehicle targets in SAR (Synthetic Aperture Radar) image

An automatic extraction and image-based technology, applied in image analysis, image enhancement, image data processing, etc., can solve the problem that SAR images cannot describe the overall shape of the target more completely, cannot realize the automatic extraction of vehicle targets in SAR images, and cannot be effective Extracting SAR images and other problems to achieve the effect of facilitating visual observation and solving filtering problems

Pending Publication Date: 2022-07-22
中国电波传播研究所
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the difference in optical and SAR imaging mechanisms, SAR images cannot describe the overall shape of the target more completely.
After testing, the existing commonly used edge detection algorithms cannot effectively extract the contours of vehicle targets in SAR images, and cannot automatically extract vehicle targets in SAR images.

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 automatically extracting vehicle targets in SAR (Synthetic Aperture Radar) image
  • Method for automatically extracting vehicle targets in SAR (Synthetic Aperture Radar) image
  • Method for automatically extracting vehicle targets in SAR (Synthetic Aperture Radar) image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] Example 1, automatic extraction of vehicle targets based on the MSTAR open source database:

[0047] figure 2 is the visible light image of the vehicle target in Example 1; image 3 is the SAR image f(x, y) of the vehicle target in Example 1; Figure 4 is the denoised image g(x, y) of the vehicle target in Example 1; Figure 5 is the scattering center map of the vehicle target in Example 1; Image 6 is the pseudo-color image k of the vehicle target in Example 1 1 (x, y, z); Figure 7 is the filtered image k of the vehicle target in Example 1 2 (x, y); Figure 8 is the binarized image k of the vehicle target in Example 1 3 (x, y); Figure 9 is the target image T(x, y) extracted in Example 1;

Embodiment 2

[0048] Embodiment 2, automatic extraction based on actual data vehicle target:

[0049] Figure 10 is the visible light image of the vehicle target in Example 2; Figure 11 is the actual SAR image f(x, y0 of the vehicle target in Example 2; Figure 12 is the denoised image g(x, y) of the vehicle target in Example 2; Figure 13 is the scattering center map of the vehicle target in Example 2; Figure 14 is the pseudo-color image k of the vehicle target in Example 2 1 (x, y, z); Figure 15 is the filtered image k of the vehicle target in Example 2 2 (x, y); Figure 16 is the binarized image k of the vehicle target in Example 2 3 (x, y); Figure 17 is the target image T(x, y) extracted in Example 2.

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 method for automatically extracting a vehicle target in an SAR image. The method comprises the following steps: step 1, filtering an input two-dimensional SAR image; 2, carrying out local maximum value judgment on the filtered image; step 3, recording the maximum value coordinates obtained in each window, and marking the maximum value coordinates in the SAR image; and step 4, performing Taylor expansion on the peak point common and then converting the peak point common into a quadratic paraboloid equation. According to the method disclosed by the invention, automatic segmentation of vehicle targets and backgrounds such as land and grassland can be realized, and the extracted pure target SAR image (the background is pure black) is output. Meanwhile, the method can also output a pseudo-color image of the target after linear mapping and a target scattering center point marking graph, so that visual observation of personnel is facilitated.

Description

technical field [0001] The invention belongs to the field of SAR image processing, and particularly relates to an automatic extraction method of vehicle-type targets in SAR images in the field. Background technique [0002] Synthetic Aperture Radar (SAR) is an active microwave sensor, which has the characteristics of all-weather, all-day, multi-view, strong penetrating ability and independent of the operating distance, etc. It has been widely used in urban planning, forest detection and Military reconnaissance and other fields. In the process of vehicle target detection and recognition in SAR images, it is necessary to achieve the segmentation of target and background to further analyze the difference between target and background. However, due to the different imaging mechanisms of optics and SAR, SAR images cannot fully describe the overall shape of the target. After experiments, the existing commonly used edge detection algorithms cannot effectively extract the contours...

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): G06T7/194G06T5/00
CPCG06T7/194G06T5/002G06T2207/10044G06T2207/20032G06T2207/30248
Inventor 李嘉俊徐威曲晓杰郭宇荃
Owner 中国电波传播研究所
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