Infrared small target detection method based on multi-scale mean filtering and saliency detection

A technology of small target detection and mean value filtering, which is applied in character and pattern recognition, image data processing, instruments, etc., can solve problems such as weak robustness, and achieve the effect of low false alarm rate

Active Publication Date: 2018-02-02
中科顶峰智能科技(重庆)有限公司
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is suitable for infrared images with relatively simple backgrounds, but it is not robust when dealing with infrared images with complex backgrounds.
In conclusion, the detection of small infrared targets in complex backgrounds is still a challenging subject

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
  • Infrared small target detection method based on multi-scale mean filtering and saliency detection
  • Infrared small target detection method based on multi-scale mean filtering and saliency detection
  • Infrared small target detection method based on multi-scale mean filtering and saliency detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

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 an infrared small target detection method based on multi-scale mean filtering and saliency detection. Firstly, multi-scale mean filtering is used to achieve the effects of target enhancement and background suppression. Second, using the saliency detection algorithm, small infrared targets in complex backgrounds can be effectively detected while maintaining a low false alarm rate. The beneficial effect is that the signal energy of the real small target is strengthened after multiple filtering, and the effect of target enhancement and background suppression is achieved. Using the saliency detection algorithm, it can effectively detect small infrared targets in complex backgrounds while maintaining a low false alarm rate.

Description

technical field The invention belongs to an infrared small target detection method, in particular to an infrared small target detection method based on multi-scale mean filtering and saliency detection. Background technique Infrared small target detection in complex background is the core technology of infrared guidance system and an important means of military defense. Due to the characteristics of the infrared image itself, it is very difficult to detect small infrared targets: firstly, due to the generally long imaging distance, the target only occupies a small number of pixels in the image; secondly, due to the noise of the imaging system and the influence of background clutter, the target The signal is weak, and it is easy to be overwhelmed by complex backgrounds, such as overlapping in the background of clouds; finally, infrared targets lack effective shape and texture information. Regarding infrared small target detection, predecessors have done a lot of work. For e...

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 Patents(China)
IPC IPC(8): G06T7/00G06K9/00
Inventor 李映董浩陈昕
Owner 中科顶峰智能科技(重庆)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