A Data Augmentation Method Based on Object Overlap Calculation and Adaptive Adjustment

An adaptive adjustment and overlapping technology, applied in computing, image enhancement, image data processing, etc., can solve problems such as improper configuration of target positions, and achieve the effect of increasing diversity, improving balance, and increasing the number of samples

Active Publication Date: 2022-07-26
NANHU LAB
View PDF15 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to address the above problems and provide a data enhancement method based on target overlap calculation and adaptive adjustment, which can increase the number of pictures in the data set, the number of targets, and the diversity of backgrounds, and can be applied to most target detection Dataset addresses misconfiguration of target locations

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
  • A Data Augmentation Method Based on Object Overlap Calculation and Adaptive Adjustment
  • A Data Augmentation Method Based on Object Overlap Calculation and Adaptive Adjustment
  • A Data Augmentation Method Based on Object Overlap Calculation and Adaptive Adjustment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] In order to enable those skilled in the art to better understand the solution of this embodiment, the technical solution in this embodiment will be described clearly and completely below with reference to the accompanying drawings.

[0041] like figure 1 and figure 2 As shown in the present embodiment, a data enhancement method based on target overlap calculation and adaptive adjustment includes:

[0042] S1. Use the marked data set of the target detection task as the object;

[0043] S2. Select the target to be expanded: select one or more target categories as the category to be expanded, the targets of the category to be expanded tend to be sparse in number in the entire data set, and the method of this embodiment can perform data expansion for the target of this category ; According to the category information of the label file of the data set, filter out all the sets of pictures containing the categories to be expanded in the entire data set as the set to be expa...

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 provides a data enhancement method based on target overlap calculation and adaptive adjustment, including: S1, taking the marked target detection task data set as an object; S2, selecting the target to be expanded: selecting one or more targets target categories are used as categories to be expanded, a set of pictures containing the categories to be expanded in the entire data set is screened out as a set to be expanded, and a certain percentage of pictures are randomly selected from the entire data set to form a set as a set to be generated; S3, the described The to-be-expanded set and the pictures in the to-be-generated set are randomly combined, and new pictures and new labels are generated by means of overlapping degree calculation and adaptive adjustment for data enhancement. The present invention can improve the number of pictures, the number of targets, and the diversity of combinations of targets and backgrounds in the data set, and improve the training efficiency and performance of the deep neural network model.

Description

technical field [0001] The invention belongs to the technical field of image processing data enhancement, and in particular relates to a data enhancement method based on target overlap calculation and adaptive adjustment. Background technique [0002] The purpose of the object detection task is to identify, classify and locate objects appearing in images or videos. This task is achieved by training the model constructed by the deep neural network in the deep learning technology. In the training process, it is necessary to use the labeled data set, that is, the data set after the category and position of the target to be identified in the picture are marked. The degree and so on will affect the training effect of the model. Object detection tasks often require data augmentation, which can also be called data expansion. Before the target detection model is trained, the data enhancement process on the data set is to improve the detection ability of the model trained with the ...

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): G06T5/00G06T7/73G06V10/774G06K9/62
CPCG06T5/007G06T7/73G06T2207/20004G06T2207/20081G06F18/214
Inventor 仇祎诚廖佳纯牛力沙枫宋文杰张磊勾鹏唐攀攀刘昊
Owner NANHU LAB
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