Method and device for automatic labeling of target detection based on moving object detection

A technology for automatic labeling of moving objects, applied in the field of image processing, can solve the problem of high labor cost for labeling

Active Publication Date: 2021-07-06
ECARX (HUBEI) TECHCO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the prior art, regardless of whether machine learning or deep learning is used, the training of the target detection model requires a large number of pictures and labeling operations, and manual labeling is mainly used for labeling. For pictures with small objects, the required The labor cost of labeling is huge, so how to save the labor cost of target detection and labeling is the current problem

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 automatic labeling of target detection based on moving object detection
  • Method and device for automatic labeling of target detection based on moving object detection
  • Method and device for automatic labeling of target detection based on moving object detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0048] In order to solve the above technical problems, an embodiment of the present invention provides a schematic flowchart of a method for automatic labeling of object detection based on moving object detection. figure 1 A schematic flow chart of a method for automatic labeling of target detection based on moving object detection is shown according to an embodiment of the present invention. see figure 1 , the method at least inc...

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 an automatic labeling method and device for target detection based on moving object detection. The method includes using a scene classifier to determine the scene category of the video to be detected, and selecting at least one moving object detection algorithm that has a corresponding relationship with the scene category. The video to be detected includes the same type of moving object; the moving object in the multi-frame picture of the video to be detected is detected by at least one moving object detection algorithm, and the detected moving object is marked with a target frame; the moving object in the multi-frame picture is used to predict Set the target tracking algorithm to track, mark the target frame for the tracked moving object; use the preset algorithm to remove the overlapping target frame on the moving object in multiple frames of pictures, and use the remaining target frame as the final labeling result of the moving object. The automatic labeling method adopted by the present invention can greatly save the labor cost of target detection and labeling, is more efficient than the traditional pure manual labeling method, and effectively saves the labor cost.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an automatic labeling method and device for target detection based on moving object detection. Background technique [0002] At present, target detection based on machine learning or deep learning is very popular and has become the main visual perception method in the field of autonomous driving. In the prior art, regardless of whether machine learning or deep learning is used, the training of the target detection model requires a large number of pictures and labeling operations, and manual labeling is mainly used for labeling. For pictures with small objects, the required Therefore, how to save the labor cost of target detection and labeling is the current problem. Contents of the invention [0003] In view of the above problems, the present invention is proposed to provide a method and device for automatic labeling of objects based on moving object detection, which ...

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): G06T7/20G06K9/00
CPCG06T7/20G06V20/41
Inventor 杨文龙
Owner ECARX (HUBEI) TECHCO LTD
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