Method, device and system for processing captured image in non-reduction correction mode and artificial intelligence

An artificial intelligence and correction method technology, applied in the field of image recognition, can solve the problems of missing small target features or signals, consuming large computing resources, and increasing costs

Pending Publication Date: 2020-12-29
NATIONAL TAIWAN OCEAN UNIVERSITY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] In the implementation of artificial intelligence image recognition in the prior art, since the prior art only performs convolution and / or feature extraction with a feature map of a single pixel size, the features or signals of small objects are often missed when processing large and small objects.
In addition, because the previous technology only uses a single convolution kernel to process images, it often consumes a lot of computing resources, so it can only be processed by high-end processors instead of low-end chips such as GPUs, which leads to a significant increase in costs

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, device and system for processing captured image in non-reduction correction mode and artificial intelligence
  • Method, device and system for processing captured image in non-reduction correction mode and artificial intelligence
  • Method, device and system for processing captured image in non-reduction correction mode and artificial intelligence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] In order to fully understand the purpose, characteristics and effects of the present invention, the present invention will be described in detail through the following specific embodiments, and in conjunction with the attached drawings, as follows:

[0066] Please refer to figure 1 , a flow chart of the method for processing captured images in a non-restorative correction manner and artificial intelligence according to the present invention, the steps of which include step S10 to step S12. In step S10 , an initial image can be captured, specifically, the initial image can be captured with a fisheye lens. In step S11, the initial image can be processed in a non-restorative correction method and artificial intelligence, or can be referred to as processing the initial image in a non-distortion correction method and artificial intelligence, that is, the initial image captured by the fisheye lens can not be used in the present invention. Image restoration (distortion / dewarp...

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 method, device and system for processing a captured image in a non-reduction correction mode and artificial intelligence. The method comprises the following steps of a) capturing an initial image; b) processing the initial image in the non-reduction correction mode and artificial intelligence; and c) performing feature extraction on the processed image. According to the invention, a smaller target is not missed, and the method, device and system is applied to devices or assemblies with fewer resources.

Description

technical field [0001] The present invention relates to the field of image recognition, and more particularly relates to a method, device and system for processing captured images in a non-restorative way and artificial intelligence. Background technique [0002] In the implementation of artificial intelligence image recognition in the prior art, since the prior art only performs convolution and / or feature extraction with a feature map of a single pixel size, the features or signals of small objects are often missed when processing large and small objects. In addition, because the previous technology only uses a single convolution kernel to process images, it often consumes a lot of computing resources, so that only high-end processors can be used for processing instead of low-end chips such as GPUs, which leads to a significant increase in cost. [0003] In view of this, the present invention proposes a method, device and system for processing captured images with non-resto...

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): G06K9/46G06N3/04
CPCG06V10/40G06N3/045
Inventor 谢君伟陈平扬
Owner NATIONAL TAIWAN OCEAN UNIVERSITY
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