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

Airplane segmentation method and device for remote sensing image, readable storage medium and equipment

A remote sensing image and aircraft technology, applied in computer parts, instruments, characters and pattern recognition, etc., can solve the problems of complex matching process and inaccurate results, and achieve accurate segmentation results, accurate segmentation results, and simple segmentation methods.

Active Publication Date: 2020-07-03
BEIJING TECHSHINO TECH +1
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the variability of aircraft shapes, sizes and directions, the matching process is complex and the results are inaccurate, and the template library must be updated in real time to ensure that it contains all types of aircraft

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
  • Airplane segmentation method and device for remote sensing image, readable storage medium and equipment
  • Airplane segmentation method and device for remote sensing image, readable storage medium and equipment
  • Airplane segmentation method and device for remote sensing image, readable storage medium and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0075] The implementation of the present invention provides an aircraft segmentation method of a remote sensing image, and the aircraft segmentation refers to segmenting an aircraft on a remote sensing image. Such as figure 1 As shown, the method includes:

[0076] Step S100: Perform preprocessing including binarization on the remote sensing image, the preprocessed image includes multiple highlighted connected regions, and obtain aircraft candidate frames on the preprocessed image.

[0077] The preprocessed image is a binary image, and the binary image includes a plurality of highlighted connected regions. The aircraft candidate box is the initially determined rectangular area including the image of the aircraft.

[0078] Step S200: According to the proportion of connected areas in the aircraft candidate frame, find out the connected area where the aircraft is located and determine the shape of the aircraft included in the connected area where the aircraft is located. The sh...

example 1

[0128] Step S310: Thinning the preprocessed image in the aircraft candidate frame into a skeleton map and expanding it into an edge map, and mixing the skeleton map and the edge map to obtain a mixed map.

[0129] In this step, the preprocessed image P of the aircraft is refined into a skeleton map P1, and the preprocessed image P of the aircraft is subjected to a morphological expansion operation to obtain an expanded edge map P2, and the above-mentioned skeleton map and edge map are combined to obtain a mixed map P ',in:

[0130] .

[0131] Such as Figure 4 As shown, (a) is a remote sensing image, (b) is a skeleton image, (c) is an edge image, and (d) is a mixed image.

[0132] It should be noted that the above-mentioned thinning process is performed on the preprocessed image P to obtain the skeleton map P1, the expansion operation is performed on the preprocessed image P to obtain the expanded edge map P2, and the skeleton map P1 and the edge map P2 are mixed. Obtaining...

example 2

[0158] Compared with Example 1, this example only uses the skeleton map and does not use the edge map.

[0159] Step S310': refine the preprocessed image in the aircraft candidate frame into a skeleton image.

[0160] Step S320': Perform straight line detection on the skeleton diagram to obtain multiple line segments, which are the center line segments of the fuselage and the center line segments of the wings.

[0161] Step S330': Merge the line segments that meet the merging conditions among the multiple line segments to obtain the inverted fuselage axis segment and the wing axis segment, which are the candidate line segments; where the acute angle between the two line segments to be merged is The angle is less than the set angle, and when the distance between the two line segments to be merged is less than the set distance, the merge condition is satisfied. The specific merge condition and merge method are as in Example 1.

[0162] Step S340': Find the candidate fuselage ax...

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 an airplane segmentation method and device for a remote sensing image, a computer readable storage medium and equipment, and belongs to the field of image processing and pattern recognition. The method comprises the steps that binarization preprocessing is carried out on a remote sensing image, and an airplane candidate box is obtained on the preprocessed image; finding outa communication area where the aircraft is located according to the proportion of the communication areas in the aircraft candidate box, and judging the form of the aircraft included in the communication area where the aircraft is located, wherein the form of the aircraft comprises completeness, lack of one wing and lack of an aircraft body; when the aircraft lacks one wing or a fuselage, executing a first completion operation or a second completion operation, and completing the lacked part to a communication area where the aircraft is located by utilizing the symmetry of the aircraft; and marking the connected region of the aircraft on the remote sensing image to complete aircraft segmentation. According to the method, the aircraft in the picture can be segmented without a template library, and the method has high generalization and an accurate segmentation result.

Description

technical field [0001] The invention relates to the field of image processing and pattern recognition, in particular to an aircraft segmentation method, device, computer-readable storage medium and equipment for remote sensing images. Background technique [0002] With the development of aerospace technology, the amount of data and image data provided by various aerospace sensors is increasing, and manual visual interpretation can no longer meet the needs of modern information warfare. In order to adapt to future high-tech warfare, military intelligent software has been widely used. The development of computer vision technology, especially the development of pattern recognition technology, makes image interpretation possible. Use the characteristics of the target to find and discover the target, and judge the position of the target. Only in an automated system can the timeliness and accuracy of intelligence be guaranteed. [0003] Target recognition is a research focus in ...

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): G06K9/00G06K9/34
CPCG06V20/13G06V10/267Y02A90/10
Inventor 周军丁松江武明周芳汝
Owner BEIJING TECHSHINO TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com