Marine infrared target detection method based on visual attention mechanism

A visual attention mechanism and infrared target technology, applied in the field of maritime infrared target detection based on the visual attention mechanism, can solve the problems of time-consuming detection of the entire area and unknown prior information, and achieve the reduction of significance, suppression of noise, and improvement of The effect of accuracy

Active Publication Date: 2018-01-09
西安广角智创电子科技有限公司
View PDF8 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the above method is time-consuming to detect the entire area, and in the complex background, due to the interference of redundant information, the detection s

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
  • Marine infrared target detection method based on visual attention mechanism
  • Marine infrared target detection method based on visual attention mechanism
  • Marine infrared target detection method based on visual attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0044] The present invention will now be further described in conjunction with the embodiments and accompanying drawings:

[0045]The hardware environment used for implementation is: Intel(R) Core(TM) i3-2350M CPU, 4GB RAM, 2.30GHz, and the running software environment is: Mat1abR2012a and Win7 64-bit operating system. We use Matlab language programming to realize the new algorithm proposed by the present invention. Experiments were carried out with images of infrared vessels at sea, with image sizes ranging from 384×288 to 3086×2865.

[0046] The present invention is specifically implemented as follows:

[0047] Step 1: Obtain the background pixels of the infrared image, and determine the path from the image pixels to the background pixels: first, resize the input image I so that the maximum number of pixels does not exceed 300, and extract the border area with a width of γ as the background pixel. Considering that the proportion of target pixels in the infrared image is 30...

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 relates to a marine infrared target detection method based on a visual attention mechanism. The method, for marine infrared image features, introduces a target detection algorithm basedon the visual attention mechanism, and determines the position of a target in the image by calculating a salience value of each pixel. The method is characterized by, to begin with, extracting an infrared image boundary as a background pixel; then, iteratively updating maximum and minimum pixel values in all paths from a background point to pixel points through a raster scanning algorithm to obtain auxiliary graphs; next, calculating path cost according to the auxiliary graphs to obtain a saliency graph; serving Mahalanobis distance as an image boundary contract image and adding the contract image and the saliency graph obtained in the last step; and then, obtaining the target region position through morphological close operation and binarization operation. The method obtains target saliency information according to the pixel features, thereby greatly reducing marine small target missed detection probability; and the method can effectively suppress noise caused by sea level ripples andsky cloud layers, can highlight the target uniformly and has higher detection accuracy.

Description

technical field [0001] The invention belongs to computer vision image processing methods, and relates to a sea infrared target detection method based on a visual attention mechanism. It can be widely used in sea surface infrared target detection system and air target detection system. Background technique [0002] With the continuous development of modern science and technology, infrared imaging technology has been widely used in precision guidance, infrared early warning, infrared search system and other military and civilian fields, as a key technology for infrared search and tracking, infrared early warning, precision guidance, etc. Infrared target detection technology has become a research hotspot in the field of infrared image processing. On the modern military battlefield, the infrared target detection system relies on the infrared radiation characteristics of the passive detection target. Detection and positioning processing, therefore, infrared target detection tec...

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): G06K9/32G06K9/20G06K9/34G06T7/11
Inventor 赵天云周碧菡郭雷谢星星
Owner 西安广角智创电子科技有限公司
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