Candidate Region Detection Method for Sea Vessels Based on Visual Saliency

A candidate area and ship technology, applied in the field of image processing, can solve the problems of large influence, large number of ship image detection environment, slow detection speed, etc., to achieve the effect of suppressing the influence of background noise, fast detection speed, and accurate extraction results

Active Publication Date: 2021-06-08
PLA PEOPLES LIBERATION ARMY OF CHINA STRATEGIC SUPPORT FORCE AEROSPACE ENG UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] In order to solve the problems of slow detection speed, need for a large number of ship images and great influence of the detection environment in the existing target detection technology when detecting sea surface ship targets in optical remote sensing images, the present invention provides a sea surface based on visual saliency The ship candidate area detection method is a fast detection algorithm for sea ship candidate areas based on optical remote sensing images. It combines the FT visual saliency model (Frequency-tuned) and the Scharr edge detection operator without prior information. The advantages of sea ship detection, using the Gaussian mixture function to fuse the image feature maps extracted by the two models, to achieve rapid extraction of sea ship candidate areas in remote sensing 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
  • Candidate Region Detection Method for Sea Vessels Based on Visual Saliency
  • Candidate Region Detection Method for Sea Vessels Based on Visual Saliency
  • Candidate Region Detection Method for Sea Vessels Based on Visual Saliency

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] Embodiment 1 of the present invention provides a visual saliency-based detection method for candidate areas of ships on the sea surface, including:

[0063] Step 1, using the FT visual saliency model to obtain the frequency domain feature map of the optical remote sensing image containing the ship target on the sea;

[0064] Step 2, using the Scharr edge detection operator to obtain the edge gradient feature map of the optical remote sensing image;

[0065] Step 3, using a Gaussian mixture function to fuse the frequency domain feature map and the edge gradient feature map to obtain the fusion feature map;

[0066] Step 4. Based on the otsu adaptive threshold segmentation algorithm, binarize the fused feature map to extract the area containing the ship target from the image to obtain the candidate area of ​​​​the ship on the sea surface.

[0067] The present invention assumes that the input image of each step is a color image in RGB color space. If the input image is a ...

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 detecting candidate areas of sea ships based on visual saliency, comprising: step 1, using FT visual saliency model to obtain frequency-domain feature maps of optical remote sensing images containing sea ship targets; step 2, using Scharr edge The detection operator obtains the edge gradient feature map of the optical remote sensing image; Step 3, uses the Gaussian mixture function to fuse the frequency domain feature map and the edge gradient feature map to obtain the fusion feature map; Step 4, based on the otsu adaptive threshold segmentation algorithm, the The fusion feature map is binarized, which is used to extract the area containing the ship target from the image, and obtain the candidate area of ​​​​the sea ship. Integrating the advantages of FT visual saliency model and Scharr edge detection operator in sea ship detection, it effectively suppresses the influence of background noise and highlights ship targets of all scales, making the candidate area extraction results more accurate; the fusion model extracts sea ships The detection speed of the candidate area is fast.

Description

technical field [0001] The invention relates to a visual saliency-based detection method for candidate areas of ships on the sea surface, which belongs to the technical field of image processing. Background technique [0002] At present, countries all over the world are paying more and more attention to the protection of their maritime interests. Due to the advantages of large observation area, periodic revisit and no national boundaries, optical remote sensing satellites have gradually become an important technology for detecting ships on the sea surface based on optical remote sensing images of optical remote sensing satellites. It is an important monitoring method for countries to monitor the situation at sea, and it is widely used in humanitarian rescue and combating illegal maritime activities such as drug trafficking and illegal fishing. [0003] Traditional ship detection methods usually use a sliding window to traverse the entire optical remote sensing image to extra...

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 & AuthorityPatents(China)
IPC IPC(8): G06K9/00G06K9/40G06K9/46G06K9/62G06T7/13
CPCG06T7/13G06V20/13G06V10/30G06V10/44G06V10/462G06V2201/07G06F18/253
Inventor李智刘俊琦张学阳胡敏方宇强张雅声张刚刘思彤霍俞蓉程文华
OwnerPLA PEOPLES LIBERATION ARMY OF CHINA STRATEGIC SUPPORT FORCE AEROSPACE ENG UNIV