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

Automatic Detection Method of Aerial Targets Based on Multi-subregion Background Fitting

An automatic detection and aerial target technology, applied in image analysis, image enhancement, instruments, etc., can solve the problems of unsatisfactory background removal, unsatisfactory practical effect, and inapplicability, and achieve the effect of reducing the generation of false targets

Active Publication Date: 2020-06-02
HEBEI HANGUANG HEAVY IND
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the practical effect of this method is not ideal. The main reason is that it is disturbed by the angle of light and clouds, etc. In most cases, the aerial background of visible light video or infrared video is not uniform. When we randomly select the average value of a certain row as the benchmark When , the removal of the background is not ideal, which will cause more "false" targets
Therefore, this method also does not work

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
  • Automatic Detection Method of Aerial Targets Based on Multi-subregion Background Fitting
  • Automatic Detection Method of Aerial Targets Based on Multi-subregion Background Fitting
  • Automatic Detection Method of Aerial Targets Based on Multi-subregion Background Fitting

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The present invention will be described in detail below with reference to the accompanying drawings and examples.

[0022] The basic principle of the present invention is to use a certain contrast difference between the target and the background, that is, the gray level difference, to remove the background accurately and in real time through a certain method to obtain the target.

[0023] Step 1. Divide the entire image into P sub-regions. Generally, the larger P is, the more accurate the background acquisition is and the better the effect is. In this embodiment, P=16 is selected.

[0024] Step 2. For each sub-region, place a Q×Q square template on any position of the sub-region, and take the average gray value of each pixel in the template as the average gray value A(m) of the sub-region , m=1,2,...,P. The value of Q requires Q×Q to be smaller than the size of the sub-region, preferably more than 50% of the area of ​​the sub-region. In this preferred embodiment, Q=10...

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 aerial target automatic detection method based on background fitting of multiple sub-regions. The method comprises steps of dividing a to-be-detected image into P sub-regions and solving average gray scale values A(1)-A(P) of the sub-regions; then, ranking the average gray scale values A(1)-A(P) of the sub-regions according in a descending order so as to obtain new average gray scale values A'(1)-A'(P) of the sub-regions; according to the A'(1)-A'(P), selecting the average gray scale value of the second black or the second white sub-region to be a segmentation threshold value, carrying out proper scaling down or scaling up according to the image contrast ratio and carrying out image binaryzation so as to obtain a segmentation image; and carrying out target positioning on the segmentation image. According to the invention, generation of false targets can be reduced and the method is advantaged by conciseness and easy achieving of hardware of the current algorithm.

Description

technical field [0001] The invention relates to the technical field of automatic detection of aerial targets on visible light television images or infrared images, in particular to an automatic detection method of aerial targets based on multi-subregion background fitting. Background technique [0002] With the development of information technology, the intelligent detection and recognition of targets by means of video image processing has been greatly developed, especially in the military field, the automatic detection and tracking of targets can greatly shorten the reaction time of weapon systems, This is critical to improving the performance metrics of the overall system. [0003] The traditional real-time detection methods for aerial targets mainly include target detection based on background difference and aerial target detection based on image line correlation. However, these methods have certain limitations. [0004] The basic idea of ​​the target detection method b...

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): G06T7/246G06T7/254G06T7/11G06T7/66
CPCG06T7/11G06T7/248G06T7/254G06T7/66G06T2207/10016G06T2207/20021
Inventor 方勇尹晓琳丁洋坤
Owner HEBEI HANGUANG HEAVY IND