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

FPGA-based ultra-high-speed target tracking method and computer vision system

A target tracking and ultra-high-speed technology, applied in the field of computer vision, can solve the problems that the target tracking algorithm cannot achieve high speed, is not hardened, and the algorithm structure is difficult, and achieves the effects of reducing computational complexity, easy speed-up, and simple calculation

Active Publication Date: 2021-11-16
XIDIAN UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In summary, the existing problems in the prior art are: the current target tracking algorithm cannot achieve high speed and unhardened
Because FPGA is suitable for parallel computing and pipeline computing, it is difficult for an algorithm architecture to conform to these two forms

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
  • FPGA-based ultra-high-speed target tracking method and computer vision system
  • FPGA-based ultra-high-speed target tracking method and computer vision system
  • FPGA-based ultra-high-speed target tracking method and computer vision system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] In order to make the object, technical solution and advantages of the present invention more clear, the present invention will be further described in detail below in conjunction with the examples. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0048] Aiming at the problem that the current target tracking algorithm cannot reach high speed and is not hardened, the present invention proposes an ultra-high-speed target tracking algorithm suitable for realization on FPGA and its hardware architecture realized on FPGA; the method of the present invention is based on correlation filtering, using target The HSV three-dimensional features, using linear kernel functions, and deep pipeline and parallel operation of complex operations, make the improved algorithm suitable for hardware implementation, and greatly improve the speed of target tracking under the premise of ensuri...

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 belongs to the technical field of computer vision, and discloses an FPGA-based ultra-high-speed target tracking method and a computer vision system; the size of the tracking window is determined and the image of the tracking target is obtained; the three-dimensional HSV feature of the tracking target is obtained; a parallel structure is adopted to convert the three-dimensional Calculate the tracking algorithm according to the features; determine the position of the target in the adjacent frame according to the response value calculated by the tracking algorithm; optimize the structure of the target tracking algorithm, adopt parallel and pipeline structure; design the conversion strategy of floating point value and fixed point value to ensure calculation accuracy. The present invention simplifies the calculation part of the tracking algorithm and optimizes the calculation framework, so that under the premise of ensuring a certain calculation accuracy, the calculation complexity is reduced and is suitable for realization on FPGA hardware; the target tracking algorithm is accelerated to realize ultra-high speed target tracking system.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to an FPGA-based ultra-high-speed target tracking method and a computer vision system. Background technique [0002] At present, the existing technologies commonly used in the industry are as follows: target tracking is a basic research in the field of computer vision, it has a very wide range of applications in real life, for example: in intelligent monitoring to achieve target tracking, in military Precision guidance and optical positioning, etc. In recent years, electronics and computer technology have developed rapidly, and semiconductor technology has also made great progress. FPGA devices can meet the requirements of many practical applications for small and portable platforms. The parallel operation method of FPGA is of great help to the improvement of computing performance. So for compute-intensive systems, FPGAs are an ideal choice for the target applic...

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): G06T7/246G06T1/20G06T5/40
CPCG06T1/20G06T5/40G06T2207/10016G06T7/246
Inventor 贾媛张泽群宋锐李云松王养利
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com