Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Rapid Extraction System of Small Infrared Targets

An extraction system and target extraction technology, which are applied in the field of infrared small target rapid extraction systems, can solve the problems of high resource occupancy, hardware cost, complex operation logic, and inability to implement operations well, meet real-time requirements, and improve computing power. Efficiency, the effect of avoiding division operations

Active Publication Date: 2022-04-22
XIDIAN UNIV
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the process of transplanting the infrared small target fast extraction algorithm directly to the FPGA hardware platform, its operation logic is relatively complicated, and the entire operation cannot be well realized. Its resource occupancy rate and hardware cost are high, and fast data processing cannot be realized. Therefore, it is urgently needed Design an image extraction system with high detection efficiency and good real-time performance

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
  • A Rapid Extraction System of Small Infrared Targets
  • A Rapid Extraction System of Small Infrared Targets
  • A Rapid Extraction System of Small Infrared Targets

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] See figure 1 , figure 1 The embodiment of the present invention provides a block diagram of a fast infrared small target extraction system module, including:

[0030] An image acquisition module, configured to acquire an image of a target to be detected;

[0031] At least one image scaling module, connected to the image acquisition module, for reducing the image of the target to be detected;

[0032] The target extraction module is connected to the image scaling module, and is used to extract target points from the reduced target image to be detected, and extract the feature value of the target points;

[0033] A target judgment module, connected to the target extraction module, for judging whether the target point is a target to be extracted according to the feature value, and if so, recording the position of the target to be extracted;

[0034] A data cache module, connected to the image acquisition module, for storing the image of the target to be detected.

[00...

Embodiment 2

[0051] This embodiment uses a specific example to illustrate how the system performs hardware processing corresponding to the extraction algorithm. First, the algorithm applied to the system of the present invention is described. Wherein the method comprises the following steps:

[0052] S1. Select the target image to be detected, determine the template according to the size of the target unit in the target image to be detected, and map the template to the detection window of the target image to be detected, wherein the template is a window with a size of M*M pixels , where M≤20;

[0053] S2. Divide the template into a first annular area, a second annular area, and a third annular area in sequence from the inside to the outside, and make the second annular area include at least 8 sub-pixels;

[0054] S3. Divide the second annular area into 8 consecutive first sub-areas, and correspondingly, divide the third annular area into 8 continuous second sub-areas;

[0055] S4. Calcul...

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 a system for quickly extracting small infrared targets, comprising: an image acquisition module for acquiring an image of a target to be detected; at least one image scaling module connected to the image acquisition module for performing an image acquisition on the image of the target to be detected Narrowing down; the target extraction module is connected to the image scaling module, and is used to extract the target point from the reduced target image to be detected, and extracts the feature value of the target point; the target judgment module is connected to the target extraction module for Judging whether the target point is a target to be extracted according to the feature value, if so, recording the position of the target to be extracted; a data cache module connected to the image acquisition module for storing the image of the target to be detected. The invention adopts an image scaling module to shrink the image of the target to be detected, so that it can be adapted to a preset template, thereby improving calculation efficiency, realizing rapid extraction of small infrared targets, and meeting real-time requirements.

Description

technical field [0001] The invention belongs to the field of infrared image processing, and in particular relates to a fast extraction system for small infrared targets. Background technique [0002] Because the infrared small target fast extraction algorithm of the multi-directional circular gradient method requires a large amount of calculation to simulate and process one frame on a PC, the processing speed is slow, and it cannot meet the requirements of real-time processing, so the application range is limited. FPGA, on the other hand, can perform interface expansion and high-speed parallel computing, can collect and capture signals of various interfaces, realize massive data storage, and simultaneously perform large data volume operations with high parallelism and low logic complexity to realize hardware acceleration. On the basis of the infrared small target fast extraction algorithm based on the multi-directional circular gradient method, the advantage of FPGA parallel...

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): G06V10/20G06T3/40
CPCG06T3/40G06V10/255
Inventor 赵小明袁胜春李召白杨陈星安凯王博洋邵晓鹏
Owner XIDIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products