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

NEON acceleration engine of Prewitt operator

An engine and operator technology, applied in the field of NEON acceleration engine, can solve the problems of difficult real-time processing, large amount of calculation, and low calculation efficiency, and achieve low power consumption, less hardware resources, and meet energy consumption requirements Effect

Active Publication Date: 2019-02-15
FUZHOU UNIV
View PDF9 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The Prewitt operator has a good detection effect on gray-scale gradient low-noise images, but the disadvantages are that the calculation amount is large and the calculation efficiency is low. It is difficult to realize real-time processing on the current intelligent terminal equipment.

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
  • NEON acceleration engine of Prewitt operator
  • NEON acceleration engine of Prewitt operator
  • NEON acceleration engine of Prewitt operator

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The technical solution of the present invention will be specifically described below in conjunction with the accompanying drawings.

[0036] The present invention provides the NEON acceleration engine of the Prewitt operator, which utilizes 32 64-bit D registers and 16 128-bit Q registers included in the NEON coprocessor to read and write optimization and data calculation units from the data storage unit Optimize the two parts for parallel acceleration operations, and build the input and output channels of the video data stream based on FPGA to realize the construction of the entire acceleration system; among them, the data calculation unit optimization part includes RGB three-channel to grayscale single-channel calculation acceleration and gradient calculation acceleration And root mean square and binarization calculation acceleration three parts.

[0037] The implementation mode of the read and write optimization process of the data storage unit is: adopting a vectori...

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 present invention relates to a NEON acceleration engine of a Prewitt operator. This method uses NEON co-processor and single instruction multi-data acceleration strategy to compute the input imagedata in a vectorized manner. And through pipelining, data splicing and multiplexing and other means to improve computing efficiency. Compared with the existing intelligent terminal core processor, the invention can effectively improve the calculation speed and reach the requirement of image real-time processing. Compared with a dedicated image processing unit (GPU), the invention has lower powerconsumption, can save hardware resources, and is more conducive to popularizing on a portable intelligent terminal.

Description

technical field [0001] The present invention relates to the NEON acceleration engine of Prewitt operator. Background technique [0002] With the rapid development of information technology, machine vision and artificial intelligence have become one of the important technologies of intelligent terminals. At present, the images that smart terminals need to process are mainly high-definition images, such as 1080p or 2k images, which contain a large amount of data information, which poses a huge challenge to the storage and calculation of the device. The core processor adopted by the current intelligent terminal is MCU, ARM or DSP. Although the main frequency of these core processors is gradually increasing, it is still far from meeting the requirements of real-time image processing. [0003] The current smart terminal mainly uses a graphics processing unit (GPU) for real-time image processing tasks. The GPU can perform image processing algorithms in parallel through Single I...

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): G06F15/80
CPCG06F15/8007
Inventor 钱慧林晨熹
Owner FUZHOU 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