Airport Target Detection Method Based on Edge Feature in SAR Image

An edge feature and edge detection technology, applied in image analysis, image enhancement, image data processing and other directions, can solve the problems of inaccurate positioning of airport runways, uneven image brightness, reduced running time, etc., to reduce a large number of false inspections, reduce Storage space, the effect of reducing runtime

Active Publication Date: 2019-05-21
XIDIAN UNIV
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to propose a method to reduce false detection and make target positioning more accurate in view of the problems in the above-mentioned prior art that false detection, missed detection and inaccurate airport runway positioning occur when the image brightness is uneven and when there is a lot of noise. , at the same time reduce the amount of calculation and reduce the running time of the airport target detection method based on edge features 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
  • Airport Target Detection Method Based on Edge Feature in SAR Image
  • Airport Target Detection Method Based on Edge Feature in SAR Image
  • Airport Target Detection Method Based on Edge Feature in SAR Image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030]For this reason, the present invention proposes a kind of SAR image airport target detection method based on edge feature, see figure 1 , including the following steps:

[0031] (1) Use the airborne radar to obtain the image of the airport target including the airport runway, and input the SAR image I of the airport target to be detected, such as figure 2 , Figure 7 (a), Figure 8 (a), Figure 9 (a), Figure 10 (a) shows the SAR image containing the airport runway. In actual operation, the SAR image containing the entire airport can be input, or the SAR image of the local airport to be detected can be input.

[0032] (2) Use the mean ratio detector to perform edge detection on the image I, and use an 8-direction sliding window w with a size of N×N (N=2×n-1, n=1, 2,…), such as image 3 As shown, the size of the sliding window can be selected according to the size of the image in actual operation. In this example, an 8-direction sliding window with a size of 13×13 i...

Embodiment 2

[0039] The SAR image airport target detection method based on edge features is the same as embodiment 1, wherein in step (3), edge is carried out feature extraction and cluster screening, including the following steps:

[0040] (3.1) Use 8-direction Freeman chain code to track the edge detection result graph, and obtain the edge set L={l 1 , l 2 , l 3 ,... l n}, where l n Indicates the nth edge subset composed of edge pixels.

[0041] (3.2) Extract edge set L={l 1 , l 2 , l 3 ,... l n} the characteristics of each subset in the set, the present invention adopts the gray value set G with the maximum occurrence probability of edge pixels, the gradient direction set T with the maximum occurrence probability of edge pixels, the gray mean value set A on both sides of the edge, and the gray value set A on both sides of the edge The features of the variance set S and the feature vector set H of the gray level co-occurrence matrix on both sides of the edge pixel are combined to...

Embodiment 3

[0046] The SAR image airport target detection method based on edge features is the same as embodiment 1-2, wherein in step (4), the candidate edge pixels are fitted and connected, including the following steps:

[0047] (4.1) According to the least squares method to the edge clustering result set Lr={lf 1 ,lf 2 ,...lf p} in each subset of the edge pixels to carry out straight line fitting, to obtain the fitted straight line edge set Ls={ls 1 , ls 2 ,... ls p}, in actual operation, different straight line fitting algorithms can be used according to the requirements;

[0048] (4.2) For the fitted straight line edge set Ls={ls 1 , ls 2 ,... ls p} in the mth subset ls m ={line m1 ,line m2 ,...line mn}, connect them in pairs according to the gray feature rules of the runway, that is, connect the straight line segments if they meet the gray feature rules of the runway, and don’t connect them if they don’t meet the gray feature rules of the runway. ={s 1 ,s 2 ,...,s t}...

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 SAR image airport target detection method based on edge features. The technical problems of false and missing detection and inaccurate airport runway location caused by uneven image brightness and large noise are solved when an airport target is detected. The method comprises the steps that the SAR image of an airport target to be detected is input; a mean value ratio edge detector is used to acquire an edge image; the method proposed by the invention is used to carry out feature extraction and cluster selection on the edge; the method proposed by the invention is used to connect candidate edge points; and a parallel line detection technology is used to detect an airport runway to detect the airport target. According to the invention, the SAR image airport target can be accurately detected; the method has the advantages of accurate runway location, small calculation quantity, reduced false detection and reduced running time; and the method can be applied to a spaceborne and airborne SAR image processing system and related target detection systems.

Description

technical field [0001] The invention belongs to the technical field of SAR image processing, and mainly relates to airport target detection, in particular to a method for detecting airport targets in SAR images based on edge features, which can be used for detecting airport targets in SAR images. Background technique [0002] SAR image target detection is an important content in the research of SAR image processing, and its purpose is to detect the target according to the principle of digital image processing combined with the prior information of SAR image. [0003] Airport target recognition is an important branch of SAR image-aided target recognition system, and the detection of airport runway is the basis of the whole airport target recognition. Since the object detection of SAR images is widely used in the military field, SAR image object detection occupies a pivotal position in the field of SAR image processing and has become one of the most basic technologies in this ...

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): G06T7/13
CPCG06T2207/10032G06T2207/30256
Inventor 钟桦张舒侯彪
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

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