Sea surface ship candidate region detection method based on visual saliency

Abstract

The invention discloses a sea surface ship candidate region detection method based on visual saliency. The method comprises the following steps: step 1, acquiring a frequency domain feature map of anoptical remote sensing image containing a sea surface ship target by adopting an FT visual saliency model; step 2, acquiring an edge gradient feature map of the optical remote sensing image by adopting a Scharr edge detection operator; step 3, fusing the frequency domain feature map and the edge gradient feature map by adopting a Gaussian mixture function to obtain a fused feature map; and step 4,based on an otsu adaptive threshold segmentation algorithm, carrying out binarization on the fusion feature map, so that an area containing a ship target can be extracted from the image, and a sea surface ship candidate area can be obtained. The advantages of the FT visual saliency model and the Scharr edge detection operator in sea surface ship detection are fused, the influence of background noise is effectively suppressed, ship targets of all sizes are highlighted, and the candidate region extraction result is more accurate; the detection speed of the fusion model for extracting the sea surface ship candidate area is high.

Description

Technical field [0001] The invention relates to a method for detecting sea surface vessel candidate area based on visual saliency, and belongs to the technical field of image processing. Background technique [0002] At present, countries in the world are paying more and more attention to the protection of their maritime interests. Due to the advantages of optical remote sensing satellites, such as large observation area, periodic revisiting, and freedom from national boundaries, the detection technology of sea ships based on optical remote sensing images of optical remote sensing satellites has gradually become The important monitoring methods of various countries on the maritime situation are 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 extract the ship target candidate area, a...

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

Images