Supercharge Your Innovation With Domain-Expert AI Agents!

A real-time localization method for key points of typical non-cooperative targets under high frame rate conditions

A non-cooperative target, real-time positioning technology, applied in image analysis, image enhancement, instruments, etc., can solve problems such as huge resource consumption, complex background, low false alarm rate, etc.

Active Publication Date: 2022-03-15
WUHAN INSTITUTE OF TECHNOLOGY
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These methods have a good detection rate and a low false alarm rate, and can basically meet the requirements of target detection and recognition in the civilian field. However, due to the complexity of the algorithm design, the algorithm consumes resources (whether it is time or space) Huge, it is difficult to meet some special requirements in military applications, such as high frame rate, wide format, complex background, key point detection, etc.

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 real-time localization method for key points of typical non-cooperative targets under high frame rate conditions
  • A real-time localization method for key points of typical non-cooperative targets under high frame rate conditions
  • A real-time localization method for key points of typical non-cooperative targets under high frame rate conditions

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0082] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0083] A typical non-cooperative target key point real-time positioning algorithm under high frame rate conditions based on DSP parallel processing in the embodiment of the present invention, the DSP chip uses TMS320C6678, and the algorithm flow is as follows figure 1 shown, including the following steps:

[0084] S1, the current frame image is recorded as I0 (such as figure 2 ), the size of the image is 640*480. Down-sampling I0, reducing it by 16 times to obtain down-sampling image I1, the size is 160*120, the down-sampling method adopts the dot method, and takes every three points in the row ...

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 real-time positioning method for key points of typical non-cooperative targets under the condition of high frame frequency, comprising the following steps: performing down-sampling processing on the current frame image to obtain the down-sampled image; performing horizontal and vertical projection operations on the down-sampled image, Calculate the range of the target area; within the range of the obtained target area, perform a circle projection calculation operation on the current frame image to obtain the image after the circle projection; perform adaptive threshold processing on the image after the circle projection to obtain the threshold for segmenting the edge of the target; according to the obtained Calculate the edge information of the image after the circular projection; for the edge information, use parallel computing to calculate its curvature; smooth the obtained curvature; find the maximum value of the smoothed curvature, and mark the maximum value corresponding to The image pixel serial number of the target key point in the current frame image is obtained through coordinate conversion. The invention can locate the key points of typical non-cooperative targets under the complex background with high frame rate.

Description

technical field [0001] The invention relates to the fields of target recognition and multi-core parallel processing, in particular to a real-time positioning method for key points of typical non-cooperative targets under high frame rate conditions. Background technique [0002] In recent years, with the maturity of flight control technology and the reduction of electronic integration costs, aerial vehicles (such as drones, balloons, etc.) have become more and more widely used in military fields such as reconnaissance and strike. Once these aircraft of the enemy enter our country's airspace, they will certainly pose a great threat to our country's national security and people's lives and property. Relevant countermeasure technologies (such as reconnaissance, shooting, net capture, control interference, etc.) must be used to quickly discover and monitor them , control and destroy. Among them, how to quickly and effectively find the enemy's small air targets and precisely loca...

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): G06T7/70G06T7/12G06T7/136
CPCG06T7/12G06T7/136G06T7/70G06T2207/10004
Inventor 洪汉玉陈辉远张耀宗王维祥赵书涵石教炜张天序
Owner WUHAN INSTITUTE OF TECHNOLOGY
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More