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

Percentage hit-or-miss transform-based infrared dim-small target detection method

A technology for hitting weak and small targets that cannot be hit. It is applied in the field of infrared weak and small target detection to achieve good anti-noise performance, high detection rate, and solve the problem of infrared weak and small target detection.

Inactive Publication Date: 2017-10-27
HARBIN ENG UNIV
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The object of the present invention is to provide a kind of infrared weak and small target detection method based on percentage hit and miss conversion to solve how to improve effective detection effect under low signal-to-noise ratio conditions

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
  • Percentage hit-or-miss transform-based infrared dim-small target detection method
  • Percentage hit-or-miss transform-based infrared dim-small target detection method
  • Percentage hit-or-miss transform-based infrared dim-small target detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0050] Experiments were carried out on the actual shooting infrared small target video under the Matlab R2012a operating environment. The sequence image has a total of 350 frames, the image size is 320×256 pixels, the target size is about 30 pixels, the signal-to-noise ratio is about 2, and the background is Sky, select frame 50, frame 150, frame 250, frame 350 ( figure 2 (a) to (d)), detected by the method provided by the present invention.

[0051] According to the training result, the minimum matching degree (P) of the video to be detected and the structural element is determined as 93, and the experiment is carried out for the infrared weak target sequence image of actual shooting, and the small target in each frame image can be detected by the method provided by the present invention. target, and no false targets are detected, by figure 2 (a)~(d) and it can be seen that the method provided by the present invention can realize the detection of the target at a low signal...

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 belongs to the field of unmanned aerial vehicle target detection methods, and specifically relates to a percentage hit-or-miss transform-based infrared dim-small target detection method. The method specifically comprises the following steps of: 1) selecting a training sample; 2) determining a foreground structure element FG and a background structure element BG of the selected sample; 3) determining a minimum matching degree P between a to-be-detected target and the structure elements; 4) reading a to-be-detected video and calculating a maximum matching degree Per; 5) comparing the minimum matching degree with the maximum matching degree Per, and separating an image target and a background; and 6) displaying a detection result, reading the next frame of image and repeating the steps 4-5. According to the method, detection is carried out on infrared dim-small targets by utilizing percentage hit-or-miss transform, so that the anti-noise performance is good, and the detection effects of high detection rate and low false alarm rate are achieved.

Description

technical field [0001] The invention belongs to the field of detection methods for unmanned aerial vehicle targets, in particular to a detection method for weak and small infrared targets based on percentage hit-to-miss conversion. Background technique [0002] With the rapid development of military high-tech, all kinds of precision-guided weapons represented by precision-guided missiles have exerted more and more powerful power in the modern battlefield, which has a great impact on the security of important military sites and high-value combat platforms such as aircraft and warships. serious threat. A large number of facts show that if the attacking target cannot be detected and confronted in time, no matter how powerful the combat platform is, it can only be the target of the missile. It can be seen that in order to ensure the security of important military sites and high-value combat platforms and enhance their survivability, it is necessary to effectively detect, track ...

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): G06K9/46G06T7/194
CPCG06T7/194G06T2207/20081G06T2207/10016G06T2207/10048G06V10/443G06V2201/07
Inventor 汲清波郜丽鹏李柯游世勋杜旭华
Owner HARBIN ENG UNIV