Remote-sensing image ship target segmentation method

A target segmentation and remote sensing image technology, applied in the field of remote sensing image processing, can solve the problems of affecting feature extraction and description, inaccurate target extraction, and inability to separate ship targets, so as to avoid the interference of ship targets and achieve a good separation effect. Effect

Active Publication Date: 2018-02-16
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF2 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In SAR imaging, due to factors such as azimuth ambiguity, distance ambiguity, and defocus, there will be crosses and smears on the ship target, and the segmentation method in the optical image cannot completely separate the ship target from the marine SAR image. Causes inaccurate target extraction and affects feature extraction and description

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
  • Remote-sensing image ship target segmentation method
  • Remote-sensing image ship target segmentation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0069] Below to figure 2 Take as an example for further explanation.

[0070] Step 1: In this example, we need to realize the figure 2 The SAR image slice shown in (a) is subjected to ship target segmentation. First, logarithmic domain wavelet filtering is performed according to the method described in step 1.

[0071] Step 2: Carry out median filtering according to the method described in step 2.

[0072] Step 3: Perform guided filtering according to the method described in Step 3.

[0073] Step 4: Perform power-law transformation according to the method described in step 4. figure 2 (b) is the image obtained after the first step, the second step, the third step and the fourth step.

[0074] Step 5: Carry out primary threshold segmentation according to the method described in step 5.

[0075] Step 6: Carry out area marking according to the method described in step 6. figure 2 (c) is the image obtained after region marking.

[0076] Step 7: Perform Randon transform...

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 remote-sensing image ship target segmentation method. The method carries out a filtering enhancement operation on an SAR image, and carries out contour extraction of a ship target on the basis of Randon transform. According to the method, texture details of the image are enhanced while image noises are reduced through using a filtering method of combining log-domain wavelet filtering and guided filtering; and a direction and a boundary of the ship target are also obtained, through using the Randon transform, to mitigate impacts of crosses and trailing on subsequent ship target identification.

Description

technical field [0001] The invention belongs to the field of remote sensing image processing, and in particular relates to a method for segmenting and extracting sea ship targets in SAR remote sensing satellite images. Background technique [0002] SAR images have the characteristics of all-day and all-weather, so they are widely used in marine fishery monitoring, military and civilian ship management, marine development supervision, oil spill detection, immigration control and other fields. In order to accurately and quickly extract the ship targets in the ocean and obtain information such as the position, course, and category of the ship, it is necessary to segment and extract the detected ship targets well to provide a basis for subsequent further information extraction. [0003] In SAR images, due to the influence of coherent speckle noise, the image cannot reflect the characteristics of the target itself well, and it is difficult to describe the features and achieve a g...

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): G06T7/136G06T7/187G06T5/10
CPCG06T5/10G06T7/136G06T7/187G06T2207/10032G06T2207/20024G06T2207/20032
Inventor 陈禾齐保贵王银婷庄胤龙腾
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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