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

Optical remote sensing image ship detection method based on feature fusion convolutional network

An optical remote sensing image and convolutional network technology, applied in the field of image processing, can solve the problems of small-sized ship detection accuracy and low detection speed, and achieve the effect of increasing speed, increasing feature information, and improving detection accuracy

Active Publication Date: 2018-11-30
XIDIAN UNIV
View PDF8 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to address the above-mentioned deficiencies in the prior art, and propose a ship detection method for optical remote sensing images based on feature fusion convolution network, which is used to solve the detection accuracy and detection speed of small-sized ships in the prior art lower technical issues

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
  • Optical remote sensing image ship detection method based on feature fusion convolutional network
  • Optical remote sensing image ship detection method based on feature fusion convolutional network
  • Optical remote sensing image ship detection method based on feature fusion convolutional network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0038] refer to figure 1 , a ship detection method for optical remote sensing images based on feature fusion convolutional network, including the following steps:

[0039] Step 1) Construct feature fusion convolutional network:

[0040]Step 1a) replace the fully connected layer and the softmax classification layer in the VGG-16 network by setting m convolutional layers, m≥1, and use the replaced VGG-16 network as the backbone of the feature fusion convolutional network;

[0041] The number of new convolutional layers m≥1, increasing the number of convolutional layers in the network is to obtain deeper semantic information of optical remote sensing images, but the value of m should not be too large, too many convolutional layers will make the network structure too Deep results in too much calculation;

[0042] In a specific embodime...

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 optical remote sensing image ship detection method based on a feature fusion convolutional network, and mainly solves the problems of relatively detection precision and relatively low detection speed of a small-sized ship in the prior art. The method comprises the following specific steps of (1) constructing the feature fusion convolutional network; (2) constructing a training image set and a training class label set; (3) training the feature fusion convolutional network; (4) performing sea-land separation on a to-be-tested optical remote sensing image; and (5) detecting the ship in the to-be-tested optical remote sensing image. By fusing feature images with different resolutions, feature information of the small-sized ship is added; the ship is detected on the feature images with the different resolutions, so that the detection precision of the small-sized ship is improved; and the sea-land separation is realized in combination with gray information and gradient information of the optical remote sensing image, so that the ship detection speed is increased. The method can be applied to the identification and detection of ships in optical remote sensing images.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to a ship detection method for optical remote sensing images, in particular to a ship detection method for optical remote sensing images based on feature fusion convolution network, which can be applied to identify ships in optical remote sensing images and detection. Background technique [0002] Target detection technology is one of the core issues in the field of computer vision. Optical remote sensing image ship detection uses the optical remote sensing image data collected by remote sensing satellites as the data source, and uses image processing technology to locate the ship in the image. Optical remote sensing image ship detection is an important research direction in remote sensing application technology, and has broad application prospects in maritime rescue, port traffic management, sea area security, etc. [0003] Due to the large differences in scale and shape of...

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): G06K9/00G06K9/62
CPCG06V20/13G06F18/241G06F18/253G06F18/214
Inventor 马文萍陈小波武越焦李成杨惠熊云塔
Owner XIDIAN UNIV