Unlock instant, AI-driven research and patent intelligence for your innovation.

Method and device for tracking and labeling multiple targets in video

A video-targeted technology, applied in the field of data labeling, can solve the problems of high complexity of labeling tasks, high time and labor costs required for labeling tasks, and achieve the effect of improving execution efficiency and accuracy.

Active Publication Date: 2020-06-26
BEIJING HORIZON ROBOTICS TECH RES & DEV CO LTD
View PDF14 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] These methods need to consider the correlation between different frames, the complexity of the labeling task is high, and often require a large number of repeated modifications
When the video is very long or the number of frames extracted from the video is large, the time and labor costs required for the labeling task are very high

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 device for tracking and labeling multiple targets in video
  • Method and device for tracking and labeling multiple targets in video
  • Method and device for tracking and labeling multiple targets in video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] figure 1 A flowchart of a method for tracking and labeling multiple targets in a video according to an embodiment of the present disclosure is shown.

[0020] Such as figure 1 As shown, the method according to the embodiment of the present disclosure may include step S110. For the current labeled frame in each labeled frame in the current section in each part obtained in step S110 , the method according to the embodiment of the present disclosure may further include step S210 , step S220 and step S230 .

[0021] In step S110, annotated frames of one or more parts may be obtained by initially annotating multiple temporally consecutive frames extracted from the video, wherein each part may include one or more annotated frames, and Each annotation object in each annotation frame may be assigned a corresponding identifier.

[0022] In step S210, the identifier of each labeling object to be modified in the current labeling frame may be modified according to the label chan...

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

Disclosed are a method and a device for tracking and labeling multiple targets in a video. The method includes obtaining one or more partial annotated frames by initially annotating a plurality of temporally consecutive frames extracted from a video. For the current labeled frame in each labeled frame in the current section in each section, the method further includes modifying and adjusting each labeled frame in the current labeled frame according to the label change table, label deletion table, and label target reference set of the current section. An identifier for a label object. Through this method, the efficiency and accuracy of the labeling task can be improved.

Description

technical field [0001] The present disclosure generally relates to data labeling, and in particular to a method and device for tracking and labeling multiple objects in a video. Background technique [0002] In the video tagging task of multi-target tracking, each frame extracted from the video can be tagged first, and then the two frames before and after are manually compared, and a unique identifier is assigned to the tagged object in each frame; A completely manual method is used to assign a unique identifier to the marked target while marking the target in each frame. [0003] These methods need to consider the correlation between different frames, the complexity of the labeling task is high, and often require a large number of repeated revisions. When the video is very long or the number of frames extracted from the video is large, the time and labor costs required for the labeling task are very high. [0004] It is expected to be able to efficiently and accurately as...

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): G06K9/00
CPCG06V20/42
Inventor 耿益锋
Owner BEIJING HORIZON ROBOTICS TECH RES & DEV CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com