Unlock instant, AI-driven research and patent intelligence for your innovation.

Infrared weak and small target identification method based on adaptive modeling

A technology of weak and small targets and identification methods, applied in character and pattern recognition, instruments, computer parts and other directions, can solve the problems of no identification and analysis, and the problem of infrared weak and small target identification has not been solved, and achieve accurate and reliable identification.

Inactive Publication Date: 2019-06-07
SUZHOU CHANGFENG AVIATION ELECTRONICS
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] However, most of the algorithms only effectively detect weak and small infrared targets, and do not carry out recognition and analysis, or only detect and identify and classify weak and small targets in simple backgrounds, and the recognition of weak and small infrared targets in complex backgrounds has not yet been solved.

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 weak and small target identification method based on adaptive modeling
  • Infrared weak and small target identification method based on adaptive modeling
  • Infrared weak and small target identification method based on adaptive modeling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The invention provides an infrared weak and small target recognition method based on adaptive modeling. The technical solution of the present invention will be described in detail below in conjunction with the accompanying drawings, so as to make it easier to understand and grasp.

[0037] Acquire an image sequence from an IR detector device, refer to figure 1 , the image resolution is recorded as M×N, background modeling is performed on each pixel position of the image, the background model of each pixel is initialized with the pixel value of the first frame image, and a certain pixel is marked as i, V( i) indicates the pixel value of the point, and N sample values ​​are randomly selected within the range of |V(i)±10|, then the initialization of the background model M(i) at the pixel position can be expressed as:

[0038]M(i)={s 1 (i), s 2 (i),...,s N (i)} (1)

[0039] Starting from the second frame image, detect the foreground target in the image (including infra...

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 an infrared weak and small target recognition method based on adaptive modeling. Adaptive background modeling, background model reconstruction, infrared weak and small target detection and HOG feature matching recognition are adopted. According to the invention, a pixel-level adaptive modeling method is adopted to carry out accurate modeling on a complex background, and adaptive modeling adopts dynamic parameters to carry out reconstruction of different degrees on each frame of image according to image changes, and an image background state is accurately described in real time; according to the pixel-level modeling mode theory, infrared targets of the size of a single pixel can be detected, and infrared targets of all sizes can be almost detected, and missing detection cannot be caused. Based on infrared target detection area marking, accurate HOG feature extraction is carried out on a target area, and classification and recognition of weak and small targets canbe achieved by matching a target feature database, and recognition is accurate and reliable.

Description

technical field [0001] The invention relates to an infrared weak and small target recognition method based on adaptive modeling, and belongs to the technical field of infrared image processing and recognition. Background technique [0002] Infrared weak and small target recognition is a hot issue in the field of computer vision research. It is widely used in military and civilian fields. It can be integrated into target recognition, air defense early warning, security monitoring and other systems, which has important application significance. [0003] The development of infrared imaging technology has laid a hardware foundation for weak and small target recognition technology. High-resolution infrared imaging equipment can clearly image weak and small targets, thereby improving the recognition of small and weak infrared targets. However, in complex scenes, due to the interference of complex background noise, the detection and recognition rate of small infrared targets is sti...

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): G06K9/00G06K9/32G06K9/46G06K9/62
Inventor 王东京张婷婷祁伟曹峰
Owner SUZHOU CHANGFENG AVIATION ELECTRONICS
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More