Fast high-resolution SAR (synthetic aperture radar) image ship detection method based on feature fusion and clustering

A feature fusion and ship detection technology, applied in the field of image processing, can solve the problems of time-consuming and labor-intensive training data, difficult to characterize data, etc., and achieve the effect of overcoming time and computing overhead, reducing the search range, and improving the distinguishing performance.

Active Publication Date: 2014-09-10
西安维恩智联数据科技有限公司
View PDF4 Cites 43 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In practice, the acquisition of training data is time-consuming and labor-intensive, and the training data itself is acqu

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
  • Fast high-resolution SAR (synthetic aperture radar) image ship detection method based on feature fusion and clustering
  • Fast high-resolution SAR (synthetic aperture radar) image ship detection method based on feature fusion and clustering
  • Fast high-resolution SAR (synthetic aperture radar) image ship detection method based on feature fusion and clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] The existing technology mentioned in the background technology has problems such as too much data acquisition and calculation overhead, and is restricted by training samples. In order to make up for these technical defects and achieve the purpose of efficient target detection and positioning, the present invention provides A fast ship target detection method in SAR images based on feature fusion and clustering is proposed.

[0055] The technical idea of ​​realizing the present invention is: in the preprocessing stage, combine the differences of the scattering characteristics of different ground objects and the prior information of the target size to remove the area where the target cannot exist; Local contrast features are used to achieve pre-screening to obtain potential target areas; after morphological processing, the region of interest slices are proposed from the original image and the detected binary image; effective features are designed and based on feature prior...

Embodiment 2

[0087] The effects of the present invention are further illustrated by the following simulation experiments.

[0088] (1) Experimental simulation conditions:

[0089] The data used in this experiment are TerraSAR high-resolution synthetic aperture radar images. The data is a synthetic aperture radar image with a resolution of 1m of the coastline of a region in the Strait of Gibraltar obtained by TerraSAR satellite in the HH polarization mode and X-band, including oceans, mountains, buildings, rivers, ports, ships and other features Types, among which there are 21 ship targets to be detected and the target types are different. The scene size covered by the experimental data is 2987m×4134m, which is a grayscale image with 8bits per pixel. This experiment uses 32-bit MATLAB2012a for simulation on the WINDOWS7 operating system with Intel(R) Core(TM) i5-3470 CPU, 3.2GHz main frequency and 4G memory.

[0090] (2) Target detection and discrimination performance evaluation criteria...

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 fast high-resolution SAR (synthetic aperture radar) image ship detection method based on feature fusion and clustering. The fast high-resolution SAR image ship detection method comprises the following steps: on the basis of the back scattering characteristics of each ground object and the prior information of a ship target in an SAR image, positioning a target potential position index map by an Otsu algorithm and range constraint; on the index map, pre-screening to obtain a detection binary segmentation map by a CFAR (constant false alarm rate) algorithm based on a local contrast; carrying out morphological processing to a detection result, and extracting a potential target slice from the SAR image and a detected binary segmentation map according to a processing result; and carrying out K-means clustering to the extracted slice by a designed identification feature to obtain a final identification result. According to the fast high-resolution SAR image ship detection method based on feature fusion and clustering, the data volume of a detection stage is effectively reduced by pre-processing, and point-to-point detection is not needed/the time of point-to-point detection is saved. Meanwhile, a target identification problem under the condition of insufficient training samples at present can be solved by the designed characteristic and a non-supervision clustering method, the target can be effectively positioned, and the size of the target can be estimated.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to a fast ship target detection method in SAR images based on feature fusion and clustering, which is used for understanding and interpretation of synthetic aperture radar images. Background technique [0002] Synthetic Aperture Radar (SAR) is an active sensor that uses microwaves for imaging. Its imaging is not limited by weather, light and other conditions, and it can observe objects of interest all day and all weather. The emergence of SAR systems with multi-band, full polarization, and different working modes has made it possible to observe the earth in all directions. At present, the interpretation ability of SAR images cannot meet the needs of processing a large number of collected images, which directly leads to the development of SAR image interpretation technology. The use of SAR images for ship target detection is an important means to achieve ocean surveillance an...

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): G06K9/00G06K9/34G06K9/46
Inventor 杨淑媛焦李成王士刚侯彪刘芳刘红英马晶晶马文萍熊涛刘赵强
Owner 西安维恩智联数据科技有限公司
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap