Image optical flow calculation method, device and equipment based on embedded GPU (Graphics Processing Unit)

An image light and embedded technology, applied in the field of artificial intelligence, can solve the problems of unbalanced load and low calculation efficiency of optical flow, achieve the effect of improving speed and accuracy, solving uneven load, and reducing the calculation bit width

Pending Publication Date: 2022-03-04
JIANGNAN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The object of the present invention is to provide an image optical flow calculation method, device, equipment and computer-readable storage medium based on an embedded GPU to solve the optical flow calculation process The problem of unbalanced load and low calculation efficiency of optical flow

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
  • Image optical flow calculation method, device and equipment based on embedded GPU (Graphics Processing Unit)
  • Image optical flow calculation method, device and equipment based on embedded GPU (Graphics Processing Unit)
  • Image optical flow calculation method, device and equipment based on embedded GPU (Graphics Processing Unit)

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The core of the present invention is to provide an embedded GPU-based image optical flow calculation method, device, equipment, and multiple computer storage media to improve the efficiency of optical flow calculation and improve the performance and accuracy of the SLAM system in the actual vehicle scene.

[0047] In order to enable those skilled in the art to better understand the solution of the present invention, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. Apparently, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0048] Please refer to figure 1 , figure 1 It is a flow chart of the first specific embodiment of a...

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 image optical flow calculation method, device and equipment based on an embedded GPU and a computer readable storage medium. A Gaussian pyramid model is established for a to-be-detected image collected in a vehicle-mounted process, the size of a detection window is dynamically adjusted and calculated according to the characteristics of an embedded GPU and the number of layers of the Gaussian pyramid model, and a single-precision floating point calculation instruction and a half-precision floating point calculation instruction are converted through the GPU. And calculating the optical flow of the feature points in the to-be-detected image. According to the method, the dynamic window of the pyramid layer is established, the problem that GPU thread loads are uneven when the LK optical flow method is calculated is solved, a single-precision floating point calculation instruction and a half-precision floating point calculation instruction are converted through the GPU, calculation of the LK optical flow method is optimized, and therefore the optical flow calculation efficiency is improved.

Description

technical field [0001] The present invention relates to the field of artificial intelligence, in particular to an image optical flow calculation method, device, equipment and computer-readable storage medium based on an embedded GPU. Background technique [0002] The rapid development of parallel computing in recent years provides a good solution to solve the problems of large amount of calculation and high degree of parallelism. The real-time performance of optical flow calculation can be greatly improved by parallel acceleration of modules that require complex processing in the optical flow algorithm. [0003] By analyzing the optical flow calculation implemented by OpenCV, it can be found that thread blocks are organized into a two-dimensional form, and a thread block is used to process the calculation of a window. When an 8*8 thread block is used to process a 21*21 window When calculating optical flow of different sizes, there will be a problem of uneven thread calculat...

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
IPC IPC(8): G06T7/269G06T1/20
CPCG06T7/269G06T1/20
Inventor 柴志雷孙瑞鑫谢双镱赵海旭姜博文陈世海吴秦刘登峰陈璟肖志勇
Owner JIANGNAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap