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

Method realized by parallel pipeline for performing real-time marking and identification on connected domains of point targets

A technology of connected domain marking and identification methods, applied in the field of real-time marking and identification, can solve the problems of not realizing real-time, increasing system cost, delay, etc., and achieve the effects of reducing processing volume, improving safety, saving resources and system cost

Active Publication Date: 2010-06-09
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF0 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Using this method will bring at least one frame time delay, which does not realize real-time; and this method will consume a lot of memory resources, increasing the system cost

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
  • Method realized by parallel pipeline for performing real-time marking and identification on connected domains of point targets
  • Method realized by parallel pipeline for performing real-time marking and identification on connected domains of point targets
  • Method realized by parallel pipeline for performing real-time marking and identification on connected domains of point targets

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] The present invention will be further described below in conjunction with the accompanying drawings and embodiments. For the parallel pipeline example realized in the FPGA, the present invention is further explained, and the technical scheme of the present invention comprises the steps:

[0050] (1) Filtering and denoising

[0051] Gaussian filter (Gaussian filter) is used to smooth the image. Through filtering, the image can be effectively denoised and smoothed, and the edge burrs of the target area will be effectively reduced. The benefit of filtering is that it can reduce the initial marking. conflicts that arise. figure 1 is the Gaussian filter mask window constructed by FIFO. The FIFO has a width of 8 bits and a depth of 1024, that is, there are 1024 8-bit storage units. The two FIFOs are connected end to end to extract nine pixel data Pi (i=1, 2, 3...9) required by the filter window, where P5 is pixel grayscale data corresponding to the current pixel clock. Th...

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 relates to a method realized by a parallel pipeline for performing real-time marking and identification on connected domains of a plurality of point targets, which comprises the following steps of: adopting a Gauss filter to carry out noise smoothing on images; providing an adaptive threshold calculation method so that a system can work in different light environments and under different target luminous intensities; aiming at the characteristics of the connected domains formed from the point targets, providing a scanning window for marking the connected domains; and establishing equivalence marks for mark conflict areas in the same connected domain, and performing weighted accumulation and accumulation again on gray scales of pixel positions to realize identification of centre-of-gravity positions of the targets when solving a mark conflict. The method realizes real-time marking and identification of the connected domains of the point targets in parallel by adopting a multi-level pipeline logical algorithm. The method has the advantages that: the method can perform real-time marking on the plurality of point targets in different light environments and identify two-dimensional positions of the targets in the images; only seven pixel clock delay is reserved between original image data and processing results; and identification precision is correct to sub-pixel level.

Description

technical field [0001] The invention relates to a method for real-time marking and recognition of connected domains of point targets, in particular to a method for realizing high-speed real-time marking and recognition of multiple point targets in a parallel assembly line, which belongs to the technical field of target recognition and visual measurement. Background technique [0002] The recognition and marking of point targets has important practical significance in the fields of aircraft target recognition, starlight point target detection, infrared guidance, medical image navigation and so on. Point targets in space (such as aircraft, starlight, missiles, and circular markers) are imaged by a camera, and a block-like region can be formed on the camera image plane, which is called the connected domain formed by the point target on the image plane. The feature recognition of connected domains includes two aspects. One is to mark multiple connected domains in the image, that...

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): G06T1/20G06T5/00
Inventor 周平刘越王涌天翁冬冬
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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