End-to-end panoramic image segmentation method based on query vector

A panoramic image and foreground segmentation technology, applied in the field of image processing, can solve problems such as long model training time and complicated calculation process, and achieve the effects of shortening training time, speeding up the training process, and improving performance

Pending Publication Date: 2021-11-26
PEKING UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the deficiencies in the prior art above, the present invention provides an end-to-end panoramic image segmentation method based on query vectors, which is a new model method for panoramic image segmentation based

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
  • End-to-end panoramic image segmentation method based on query vector
  • End-to-end panoramic image segmentation method based on query vector
  • End-to-end panoramic image segmentation method based on query vector

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0033] DRAWINGS Below, the present invention is further described, without limiting the scope of the present invention in any manner by the examples.

[0034] The present invention provides a query vector based on the end of the panoramic image segmentation method, wherein the query vector based on the panoramic frame segmentation is based on literature: target detector Sparse (Sparse R-CNN End-to-End Object Detection withLearnable Proposals) described in -RCNN. Such a detector can quickly converge, and end to end can be detected. For this purpose, the panoramic image segmentation model based on the end of the query vector based on the present invention is to build a detector. The entire process figure 2 Indicated. For image input (Input Image), we use convolution neural network (Convolution Neural Network, CNN) and characteristics of pyramid network (Feature Pyramid Network, FPN) to obtain characteristics of the image (features). Then the prospects for class segmentation, we have...

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 an end-to-end panoramic image segmentation method based on a query vector. The method comprises the following steps: representing a panoramic image segmentation process and an output result by using the query vector; enabling the query vector (Object Query) to comprise a foreground query vector (Thing Query) and a background query vector (Stuff Query); establishing a panoramic image segmentation model, including respectively establishing an image foreground class segmentation model and an image background class segmentation model; respectively mapping the foreground query vector and the background query vector to an image foreground class segmentation result things and an image background class segmentation result stuff; and carrying out detection training based on the foreground query vector and the background query vector, so that the detection training time of the foreground target is shortened, and end-to-end training and foreground segmentation result and background segmentation result output are realized. The method is simpler in process, lower in calculation complexity and better in performance.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to a panoramic image segmentation method, in particular to an end-to-end panoramic image segmentation method based on a query vector. Background technique [0002] Panoptic Segmentation is a challenging task whose goal is to assign a semantic label and unique identity to each image pixel. The image segmentation model method needs to adopt a unified way to represent the image foreground class (things) and the image background class (stuff). A major problem comes from the conflict in the number of image foreground classes and image background classes, because the number of image foreground classes is dynamic and changeable, while the number of image background classes is fixed. Panoramic image segmentation technology is an important technology for comprehensive research and understanding of scenes, and it can solve technical problems in some specific fields, including the perc...

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
IPC IPC(8): G06T7/194G06K9/62G06N3/04G06N3/08
CPCG06T7/194G06N3/08G06N3/045G06F18/253
Inventor 童云海李祥泰
Owner PEKING 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