Method and system for converting anchor-free algorithm into anchor-based algorithm

A technology for transforming relationships and algorithms, applied in the field of image processing, can solve problems such as different algorithm support and different algorithm post-processing, and achieve the effect of quick deployment and convenient use in subsequent applications

Pending Publication Date: 2022-06-21
CHENGDU VISION ZENITH TECH DEV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the model deployment stage, different device-side frameworks have different support for the two algorithms, and the post-processing of the two algorithms is completely different.

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 and system for converting anchor-free algorithm into anchor-based algorithm
  • Method and system for converting anchor-free algorithm into anchor-based algorithm
  • Method and system for converting anchor-free algorithm into anchor-based algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be further described with reference to the accompanying drawings and embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art should fall within the protection scope of the embodiments of the present invention.

[0035] see figure 1 , the present invention provides an embodiment of a method for converting an anchor-free algorithm into an anchor-based algorithm, which includes:

[0036] S101: Calculate all grid information in the anchor-free algorithm, and obtain the predicted value of the anchor-free algorithm;

[0037] S102: Generate anchors with the same shape and quantity as the grid in the anchor-free algorithm according to the specific rules for generating anchors in the anchor-based algorithm;

[0038] S103: According to the grid prediction value of the anchor-free algorithm and the...

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 and system for converting an anchor-free algorithm into an anchor-based algorithm, and the method comprises the steps: 1, calculating all grid information in the anchor-free algorithm, and obtaining a predicted value of the anchor-free algorithm; step 2, according to a specific rule of generating anchors by an anchor-based algorithm, generating anchors of which the shape and the number are the same as those of grids in the anchor-free algorithm, and according to the anchor-based algorithm, generating anchors of which the shape and the number are the same as those of grids in the anchor-free algorithm; step 3, according to the grid predicted value of the anchor-free algorithm and the anchor predicted value of the anchor-based algorithm, establishing a conversion relation for converting the anchor-free algorithm into the anchor-based algorithm; and step 4, according to the conversion relationship, setting a corresponding layer in the neural network, and realizing conversion of the anchor-free predicted value into an anchor-based predicted value. According to the method, the anchor-free algorithm can be deployed more quickly, the anchor-free algorithm and the anchor-based algorithm are unified into one set of operation, and subsequent application and use are facilitated.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method and system for converting an anchor-free algorithm into an anchor-based algorithm. Background technique [0002] In the field of image processing, object detection has always been the most researched and widely used branch direction. In traditional image algorithms, sliding window technology, support vector machine and other means are used to find the position of the target. Taking RCNN as a starting point, deep learning technology has also had a huge impact in the direction of object detection. [0003] The deep learning technology in the field of target detection can be divided into different types from different perspectives: from the perspective of model structure, it is divided into one-stage algorithm and two-stage algorithm; from the perspective of whether it is based on anchor frame, it can be divided into anchor-based algorithm and anchor-free algorit...

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): G06V10/82G06N3/04G06N3/08
CPCG06N3/08G06N3/045
Inventor 陶福煜周卓立任鹏
Owner CHENGDU VISION ZENITH TECH DEV
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