Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Ship target detection method based on coastline data and spectral analysis

A target detection and spectrum analysis technology, applied in image analysis, image data processing, instruments, etc., can solve the problems of confusion between ship targets and ground objects, high consumption of ship target detection, and inability to effectively remove noise, etc. Effect

Active Publication Date: 2016-02-03
HARBIN INST OF TECH
View PDF6 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problems in the prior art that the noise cannot be effectively removed and the detection of the ship target in the large-format satellite image consumes large computing resources and time due to the easy confusion of the ship target and the ground object, and the proposed A Ship Target Detection Method Based on Coastline Data and Spectrum Analysis

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
  • Ship target detection method based on coastline data and spectral analysis
  • Ship target detection method based on coastline data and spectral analysis
  • Ship target detection method based on coastline data and spectral analysis

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0046] Specific implementation mode one: a kind of ship target detection method based on coastline data and frequency spectrum analysis of the present implementation mode is specifically prepared according to the following steps:

[0047] Step 1. Land noise removal based on coastline data; obtain coastline vector data and high-resolution satellite remote sensing images at the same location, and complete the unification of the two types of data coordinate systems according to the scale of coastline vector data and the resolution of high-resolution satellite remote sensing images ( That is, to complete the determination of the coastline vector data and the origin of the coordinates of the high-resolution satellite remote sensing image), after manually correcting the tiny details, use the land mask to remove the noise of land features in the high-resolution satellite remote sensing image; The image data whose background is all ocean is the image after the mask;

[0048]Step 2, cl...

specific Embodiment approach 2

[0065] Specific embodiment two: the difference between this embodiment and specific embodiment one is: the coastline vector data and high-resolution satellite remote sensing image of the same place are obtained in step one, and the resolution of the coastline vector data scale and high-resolution satellite remote sensing image is completed The unification of the two types of data coordinate systems, after manually correcting tiny details, use land masks to remove land feature noise in high-resolution satellite remote sensing images; the specific process of forming image data with the background of the ocean, that is, the masked image is as follows:

[0066] (1) Data preparation; the metadata carried by a high-resolution remote sensing satellite image records the basic information when the image is acquired; for the land mask method, the image is required to provide the shooting position information, which is generally expressed in latitude and longitude;

[0067] The coastline ...

specific Embodiment approach 3

[0076] Embodiment 3: This embodiment is different from Embodiment 1 or Embodiment 2 in that: the limit range of the scale is 1:10000 to 1:600000. Other steps and parameters are the same as those in Embodiment 1 or Embodiment 2.

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 provides a ship target detection method based on coastline data and spectral analysis. The invention relates to the ship target detection method. According to the invention, the problems that noise cannot be effectively removed and the detection of a ship target in a large-size satellite image consumes a lot of computing resources and time in the prior art are solved. The invention provides the ship target detection method based on coastline data and spectral analysis The method comprises the steps that an image with background ocean image data is formed, wherein the image is masked; the image without cloud noise is acquired; a binary image is acquired, and a seed point or a seed region is detected in the binary image; according to the detected seed point or seed region, region growing is carried out to acquire a ship body region; and through the area and the length-width ratio feature of the ship body region, screening is carried out to acquire a ship target detection result in the high-resolution satellite image. The method provided by the invention is applied to the field of ship target detection.

Description

technical field [0001] The invention relates to a ship target detection method, in particular to a ship target detection method based on coastline data and frequency spectrum analysis. Background technique [0002] With the development of satellite remote sensing technology, obtaining high-resolution images has become one of the trends. The target details in the high-resolution image are clear and the gray level information is rich, which provides a good data basis for target detection. For the application of high-resolution remote sensing images, target detection is an important application. Ship targets in marine remote sensing images have high economic and military values, and it is meaningful to accurately locate ship targets based on remote sensing images. [0003] The existing detection of ship targets, especially the detection of ship targets in high-resolution images, is often disturbed by more noise. Among them, one kind of noise is the interference introduced by...

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): G06T5/00G06T7/00
Inventor 张钧萍金天明
Owner HARBIN INST OF TECH
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
Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com