Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Visual attention model SAR ship detection algorithm for self-adaptive threshold

A visual attention model and adaptive threshold technology, applied in the field of SAR remote sensing, can solve the problems of poor adaptability of the algorithm

Inactive Publication Date: 2018-03-09
CHINESE ACAD OF SURVEYING & MAPPING +1
View PDF4 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0027] However, the existing SAR image ship detection algorithm based on the visual attention model needs to determine the initial segmentation threshold and the final segmentation threshold based on manual experience in the ship detection stage, resulting in poor adaptability of the algorithm.

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
  • Visual attention model SAR ship detection algorithm for self-adaptive threshold
  • Visual attention model SAR ship detection algorithm for self-adaptive threshold
  • Visual attention model SAR ship detection algorithm for self-adaptive threshold

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] The technical solutions of the present invention will be further specifically described below through examples.

[0056] The present invention proposes an adaptive threshold visual attention model SAR ship detection algorithm, introduces the maximum inter-class variance (ie OTSU) method for adaptive threshold initial segmentation, after obtaining salient images, because salient images are more in line with Gaussian distribution, according to The statistical properties of the image get the final adaptive segmentation threshold, which avoids manual intervention and improves the automation of ship target detection. The present invention is described in detail below.

[0057] 1. PCT-based human vision computing model

[0058] The human visual computing model based on the PCT (Pulsed Cosine Transform) model adopts a bottom-up visual attention mechanism (that is, when the attention is generated by external stimuli, only the external stimuli have an impact on the object effec...

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 visual attention model SAR ship detection algorithm for a self-adaptive threshold. According to the algorithm, firstly, a visual attention model is used as a core, and an OTSUmethod is introduced to obtain an adaptive threshold value for initial segmentation. Secondly, a visual attention mechanism is introduced to obtain a visual saliency image. Due to the fact that the visual saliency image conforms to gaussian distribution, a final self-adaptive segmentation threshold value is obtained according to the statistical characteristics of the saliency image. That means, aship target is detected according to the gaussian distribution constant false alarm rate algorithm. According to the invention, the manual intervention is avoided, and the automation degree of the ship target detection is improved.

Description

technical field [0001] The invention relates to the field of SAR remote sensing, in particular to an adaptive threshold visual attention model SAR ship detection algorithm. Background technique [0002] my country is a large maritime country. Ships from certain neighboring countries have entered my country's territorial waters to conduct illegal activities such as surveying, monitoring, poaching, etc., seriously endangering my country's maritime security and maritime rights and interests. Therefore, ocean ship target detection is of great significance. With the rapid development of Synthetic Aperture Radar (SAR) systems and technologies, ship target detection in SAR images is becoming more and more common. Usually, the backscattering coefficient of the ship is larger when the SAR system is imaging, and the ship presents a brighter gray value in the SAR image; while in a stable sea state, the backscattering coefficient of the sea clutter is small, and the sea surface appears...

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 & Authority Applications(China)
IPC IPC(8): G06T7/11G06T7/136
CPCG06T2207/10044
Inventor 赵争张忠芳魏钜杰程春泉杨书成卢丽君郗晓菲
Owner CHINESE ACAD OF SURVEYING & MAPPING
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap 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