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

Single-pixel infrared target detection method

A technology of infrared target and detection method, which is applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve the problems of high false alarm rate, weak target, low detection accuracy rate, etc., to improve contrast and reduce false alarm rate Effect

Active Publication Date: 2018-10-02
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

As a key technology in the field of infrared early warning, the detection of small infrared targets is an important research direction. The difficulties are: 1) the target is weak and there is no texture information, which leads to low detection accuracy; 2) background noise interference leads to false detection High alert rate
Several methods based on the human visual system use median filtering and other methods to filter out noise during the target detection process, and smooth the target while eliminating noise, resulting in the inability to distinguish between the target and the background in the subsequent target enhancement and extraction process. Therefore, single-pixel infrared target detection cannot be realized
Therefore, the difficulty of single-pixel infrared target detection lies in: 1) the noise of the imager or the gray value of the blind pixel is higher than the target pixel, causing great interference; 2) the target is extremely weak, the signal-to-noise ratio is extremely low, and it is almost submerged in the background
From the above two technical difficulties, we can see that the existing single-pixel infrared target detection method has a high false alarm rate.

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
  • Single-pixel infrared target detection method
  • Single-pixel infrared target detection method
  • Single-pixel infrared target detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] see figure 1 , which is a flowchart of a single-pixel infrared target detection method provided in this embodiment. A single-pixel infrared target detection method, comprising the following steps:

[0045]S1: Obtain the contrast map M of the infrared image.

[0046] S2: Obtain the contrast image M and its filtered image M F The pixel difference value of each pixel, where the filtered image M F An image obtained after performing Gaussian filtering on the contrast map M; if the pixel difference value is not less than 1, then retain the pixel difference value, if the pixel difference value is less than 1, then replace the pixel difference value with 1, Thus, the difference image B is obtained.

[0047] Wherein, the specific calculation method of the difference image B is:

[0048] B=max{M-M F ,1}

[0049] S3: Perform a dot product operation on the contrast image M and the difference image B to obtain an enhanced filtered image H, and a pixel in the enhanced filtered...

Embodiment 2

[0053] In order to eliminate noise and effectively retain the information of a single-pixel infrared target, based on the above embodiment, before obtaining the contrast map M of the infrared image in this embodiment, the original infrared image is first updated based on the neighborhood gray scale ratio ratio to obtain the updated After the infrared image, the contrast map M is obtained again. A method for updating an infrared image is described in detail below, including the following steps:

[0054] Get the neighborhood grayscale ratio ratio(i,j) of the original infrared image pixel (i,j), if the neighborhood grayscale ratio ratio(i,j) is within the preset range, keep the pixel point (i,j) If the neighborhood grayscale ratio ratio(i,j) is not in the preset range, update the pixel value of the pixel point (i,j) to the median filter centered on the pixel point (i,j) As a result, an updated infrared image is acquired, and then subsequent steps are performed.

[0055] Optiona...

Embodiment 3

[0078] Based on the above embodiments, this embodiment can also further enhance the single-pixel infrared target, that is, to realize target enhancement and background suppression by using the property that the radiation-weighted contrast between the single-pixel infrared target and surrounding four neighboring points is large. The method for obtaining the contrast map M will be described in detail below.

[0079] The method of obtaining the contrast map M of the infrared image is:

[0080] A window of a set size is used to slide on the infrared image until the entire infrared image is traversed, and the radiation-weighted contrast R of the pixel is determined, thereby obtaining the contrast map M; wherein, the determination method of the radiation-weighted contrast R of the pixel includes the following steps :

[0081] S101: Obtain the contrast c of the window center pixel point and its eight neighbor points k , where k=1,2,3,...,8. specifically:

[0082]

[0083] Amon...

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 single-pixel infrared target detection method. Dot product operation is performed on a contrast image M and a difference image B so as to acquire an enhanced filtering image H. The single-pixel infrared target can be enhanced by the high frequency enhancement method so that the contrast of the single-pixel target and the background can be enhanced and thus the false alarmrate of single-pixel target detection can be effectively reduced.

Description

technical field [0001] The invention belongs to the technical field of infrared target detection, and in particular relates to a single-pixel infrared target detection method. Background technique [0002] With the rapid development of infrared imager technology, infrared imaging systems are widely used in military or civilian fields such as target detection, air defense early warning, and security monitoring. They have the advantages of good concealment and strong anti-interference performance. As a key technology in infrared early warning and other fields, infrared weak and small target detection is an important research direction. The difficulties are: 1) the target is weak and there is no texture information, which leads to low detection accuracy; 2) background noise interference leads to false detection. The alert rate is high. The above problems pose serious challenges to the accurate detection of small infrared targets. [0003] In the field of small infrared target...

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): G06K9/00
CPCG06V20/00G06V2201/07
Inventor 唐林波南京宏邓宸伟张增铄赵保军
Owner BEIJING INSTITUTE OF TECHNOLOGYGY