A semi-automatic labeling method and system based on human-computer interaction

A human-computer interaction, semi-automatic technology, applied in the field of target detection, can solve problems such as error-prone detection or missed detection, and achieve the effect of getting rid of time-consuming and laborious, good migration effect, and improving detection effect.

Active Publication Date: 2021-11-30
TSINGHUA UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method can give the picture a position information to detect the target when the Faster rcnn misses the target, and overcomes the influence of the Faster rcnn when detecting the target due to lighting conditions, occlusion, shadows, etc. question

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 semi-automatic labeling method and system based on human-computer interaction
  • A semi-automatic labeling method and system based on human-computer interaction
  • A semi-automatic labeling method and system based on human-computer interaction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] In order to make the purpose, technical solution and advantages of the application clearer, the technical solution of the application will be clearly and completely described below in conjunction with specific embodiments of the application and corresponding drawings. It should be understood that the described embodiments are only some of the embodiments of the present application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

[0045] Before introducing the embodiments of the present invention, the relevant terms involved in the embodiments of the present invention are first explained as follows:

[0046] RGB image: refers to the color image collected by a monocular camera, which is a three-channel image.

[0047] Label: Indicates the category label used for the supervised training of ...

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 semi-automatic labeling method and system based on human-computer interaction. The method includes: fusing the RGB image to be marked with the generated first Gaussian heat map; preprocessing the fused image; Input the pre-established and trained semi-automatic labeling model of the fused image, and mark multiple prediction boxes for the RGB image to be labeled; when a prediction box does not meet the requirements, the prediction box that does not meet the requirements is corrected by generating a second Gaussian heat map. The method of the present invention uses the Gaussian heat map as prior information to detect the target, and then achieves the expected effect of semi-automatic labeling; it can get rid of the time-consuming and labor-intensive disadvantages of manual labeling, and improve the accuracy of labeling.

Description

technical field [0001] The invention belongs to the field of target detection, and in particular relates to a method for using additional clicks as prior information to achieve labeling purposes through fusion with RGB images, and in particular to a semi-automatic labeling method and system based on human-computer interaction. Background technique [0002] With the rapid development of technologies such as the Internet, machine learning, big data, and cloud computing, all kinds of information data continue to grow at an exponential rate. industry applications. Labeling data sets is an important step for deep learning, but labeling data is a tedious task, and semi-automatic labeling can reduce the workload. Even though there are open source semi-automatic labeling tools, the premise of using them is that the higher the accuracy of the model, the better. If the detection results are inaccurate, it will increase the workload and make it unusable. Moreover, the use of semi-aut...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/40G06F18/241
Inventor 张新钰李骏李志伟刘宇红王力卢一倩
Owner TSINGHUA 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